[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-microsoft-win-loss-pattern-analyzer":3,"mdc--eqwd3q-key":36,"related-repo-microsoft-win-loss-pattern-analyzer":1382,"related-org-microsoft-win-loss-pattern-analyzer":1485},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":26,"repoUrl":27,"updatedAt":28,"license":29,"forks":30,"topics":31,"repo":32,"sourceUrl":34,"mdContent":35},"win-loss-pattern-analyzer","analyze win-loss patterns in sales deals","Analyzes closed opportunities to identify patterns between won and lost deals. Compares sales cycles, activities, stakeholder engagement, and deal characteristics for actionable playbook insights. Use when user asks \"why are we losing deals\", \"win loss analysis\", \"what makes deals win\", \"analyze lost opportunities\", \"sales pattern analysis\", \"compare won vs lost deals\", or \"improve win rate\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"microsoft","Microsoft","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fmicrosoft.png",[12,14,17,20,23],{"name":9,"slug":8,"type":13},"tag",{"name":15,"slug":16,"type":13},"CRM","crm",{"name":18,"slug":19,"type":13},"Sales","sales",{"name":21,"slug":22,"type":13},"Analytics","analytics",{"name":24,"slug":25,"type":13},"Dataverse","dataverse",41,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fdataverse-business-skills","2026-04-06T18:36:27.189308",null,9,[],{"repoUrl":27,"stars":26,"forks":30,"topics":33,"description":29},[],"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fdataverse-business-skills\u002Ftree\u002FHEAD\u002Fskills\u002Fwin-loss-pattern-analyzer","---\nname: win-loss-pattern-analyzer\ndescription: Analyzes closed opportunities to identify patterns between won and lost deals. Compares sales cycles, activities, stakeholder engagement, and deal characteristics for actionable playbook insights. Use when user asks \"why are we losing deals\", \"win loss analysis\", \"what makes deals win\", \"analyze lost opportunities\", \"sales pattern analysis\", \"compare won vs lost deals\", or \"improve win rate\".\nmetadata:\n author: Dataverse\n version: 1.0.0\n category: sales-analytics\n---\n\n# Win\u002FLoss Pattern Analyzer\n\nSales teams need to understand why they win and lose deals. This skill analyzes historical closed opportunities to identify patterns, highlight what winners do differently, recognize common loss signals, and provide data-driven playbook recommendations.\n\n## Instructions\n\n### Step 1: Define Analysis Scope\nWhen user asks \"Why are we losing enterprise deals in manufacturing vertical?\":\n\n**1.1 Parse Analysis Criteria:**\nExtract filters from user query:\n- Deal size segment (enterprise, mid-market, SMB)\n- Industry\u002Fvertical (manufacturing, financial services, etc.)\n- Time period (last 6 months, last year, etc.)\n- Sales stage of loss (if applicable)\n- Competitor (if mentioned)\n- Owner\u002Fteam (if specified)\n\n**1.2 Build Analysis Query:**\n\n**Important: Dataverse SQL Limitations**\nDataverse SQL does NOT support: DATEADD(), GETUTCDATE(), subqueries, HAVING, DISTINCT, UNION, CASE, DATEDIFF.\nCalculate date filters and durations programmatically (e.g., use '2025-03-01' for last year).\n\n```\nSELECT opportunityid, name, accountid, customerid, estimatedvalue, actualvalue,\n createdon, actualclosedate, statecode, statuscode,\n salesstage, closeprobability, budgetstatus, need, \n purchasetimeframe, purchaseprocess, decisionmaker,\n description, qualificationcomments, msdyn_forecastcategory,\n ownerid\nFROM opportunity\nWHERE actualclosedate > '2025-03-01'\n```\n\nThen filter programmatically for statecode = 1 (Won) or statecode = 2 (Lost).\n\n**Add Segment Filters:**\n```\n-- Enterprise deals (example threshold)\nSELECT opportunityid, name, accountid, estimatedvalue, actualvalue,\n createdon, actualclosedate, statecode, statuscode\nFROM opportunity\nWHERE actualclosedate > '2025-03-01'\nAND estimatedvalue >= 100000\n\n-- Industry filter (via account join)\nSELECT o.opportunityid, o.name, o.estimatedvalue, a.industrycode\nFROM opportunity o\nJOIN account a ON o.accountid = a.accountid\nWHERE o.actualclosedate > '2025-03-01'\nAND a.industrycode = 12\n```\n\n#### Step 2: Segment Won vs Lost Deals\n\n**2.1 Basic Segmentation:**\n```\nWON DEALS:\n- Count: [N]\n- Total Value: $[X]\n- Average Value: $[Y]\n- Win Rate: [Z%]\n\nLOST DEALS:\n- Count: [N]\n- Total Value: $[X]\n- Average Value: $[Y]\n- Common Loss Reasons (statuscode):\n - Out-Sold (5): [N]\n - Canceled (4): [N]\n```\n\n**2.2 Query Won Deals:**\n```\nSELECT opportunityid, name, accountid, actualvalue, actualclosedate,\n createdon, salesstage, closeprobability,\n budgetstatus, need, purchasetimeframe, decisionmaker, ownerid\nFROM opportunity\nWHERE statecode = 1\nAND actualclosedate > '2025-03-01'\n```\n\n**2.3 Query Lost Deals:**\n```\nSELECT opportunityid, name, accountid, estimatedvalue, actualclosedate,\n createdon, statuscode, salesstage,\n budgetstatus, need, purchasetimeframe, decisionmaker, ownerid\nFROM opportunity\nWHERE statecode = 2\nAND actualclosedate > '2025-03-01'\n```\n\n#### Step 3: Analyze Sales Cycle Patterns\n\n**3.1 Calculate Sales Cycle Length:**\n```\nFor each opportunity (calculate programmatically):\nsales_cycle_days = actualclosedate - createdon (in days)\n```\n\nNote: DATEDIFF is not supported in Dataverse SQL. Calculate durations in your application logic.\n\n**3.2 Compare Won vs Lost Cycles:**\n```\nWON DEALS:\n- Average Sales Cycle: [X] days\n- Median Sales Cycle: [Y] days\n- Shortest: [Z] days\n- Longest: [W] days\n\nLOST DEALS:\n- Average Sales Cycle: [X] days\n- Median Sales Cycle: [Y] days\n- Shortest: [Z] days\n- Longest: [W] days\n\nINSIGHT:\n- Deals that drag [X]+ days are [Y]x more likely to lose\n- Sweet spot for wins: [A] - [B] days\n```\n\n**3.3 Analyze Stage Duration:**\n```\nFor each deal, calculate time in each stage:\n- Time in Qualify\n- Time in Develop\n- Time in Propose\n- Time in Close\n\nCompare averages between won and lost:\n| Stage | Won Avg Days | Lost Avg Days | Difference |\n|-------|--------------|---------------|------------|\n| Qualify | [X] | [Y] | [+\u002F-Z] |\n| Develop | [X] | [Y] | [+\u002F-Z] |\n| Propose | [X] | [Y] | [+\u002F-Z] |\n| Close | [X] | [Y] | [+\u002F-Z] |\n```\n\n#### Step 4: Analyze Activity Patterns\n\n**4.1 Query Activities for Won Deals:**\n```\nSELECT o.opportunityid, a.activitytypecode, COUNT(*) as count\nFROM opportunity o\nJOIN activitypointer a ON o.opportunityid = a.regardingobjectid\nWHERE o.statecode = 1\nAND [segment filters]\nGROUP BY o.opportunityid, a.activitytypecode\n```\n\n**4.2 Query Activities for Lost Deals:**\n```\nSELECT o.opportunityid, a.activitytypecode, COUNT(*) as count\nFROM opportunity o\nJOIN activitypointer a ON o.opportunityid = a.regardingobjectid\nWHERE o.statecode = 2\nAND [segment filters]\nGROUP BY o.opportunityid, a.activitytypecode\n```\n\n**4.3 Compare Activity Metrics:**\n```\n| Metric | Won Avg | Lost Avg | Delta | Insight |\n|--------|---------|----------|-------|---------|\n| Total Activities | [X] | [Y] | [+\u002F-Z] | Winners have more touchpoints |\n| Phone Calls | [X] | [Y] | [+\u002F-Z] | Calls correlate with wins |\n| Meetings | [X] | [Y] | [+\u002F-Z] | Face time matters |\n| Emails | [X] | [Y] | [+\u002F-Z] | Similar email volume |\n| Tasks Completed | [X] | [Y] | [+\u002F-Z] | Execution discipline |\n\nACTIVITY PATTERNS:\n- Won deals average [X] activities, lost deals average [Y]\n- [Z]% more phone calls in won deals\n- Won deals have [W]x more in-person meetings\n```\n\n**4.4 Activity Frequency Analysis:**\n```\nCalculate activities per week throughout sales cycle:\n\nWon Deals Activity Curve:\nWeek 1: [avg activities]\nWeek 2: [avg activities]\nWeek 3: [avg activities]\n...\n\nLost Deals Activity Curve:\nWeek 1: [avg activities]\nWeek 2: [avg activities]\nWeek 3: [avg activities]\n...\n\nINSIGHT:\n- Winners maintain consistent engagement\n- Losers often show activity gaps in weeks [X-Y]\n- Key difference at [stage]: winners have [X] more activities\n```\n\n#### Step 5: Analyze Stakeholder Engagement\n\n**5.1 Count Contacts Engaged:**\n\nContacts involved in activities are stored in `activityparty`, not `activitypointer`. Run per opportunity:\n```\nSELECT ap.partyid, ap.participationtypemask\nFROM activityparty ap\nJOIN activitypointer a ON ap.activityid = a.activityid\nWHERE a.regardingobjectid = '[opportunityid]'\nAND a.statecode = 1\n```\nDeduplicate `partyid` values programmatically per opportunity to count unique contacts engaged.\n\n**5.2 Analyze Contact Roles:**\n```\nIdentify roles of engaged contacts:\n- Economic Buyers (C-level, VP)\n- Technical Evaluators (Directors, Managers)\n- End Users (Individual Contributors)\n- Procurement\u002FLegal\n```\n\n**5.3 Compare Stakeholder Engagement:**\n```\n| Metric | Won Deals | Lost Deals | Insight |\n|--------|-----------|------------|---------|\n| Avg Contacts Engaged | [X] | [Y] | Wider engagement wins |\n| Economic Buyer Engaged | [X%] | [Y%] | Must engage decision maker |\n| Multi-threaded (3+ contacts) | [X%] | [Y%] | Don't single-thread |\n| Champion Identified | [X%] | [Y%] | Internal advocates matter |\n\nKEY FINDING:\n- Won deals engaged [X] contacts on average vs [Y] for lost\n- [Z%] of won deals had economic buyer engagement vs [W%] for lost\n- Single-threaded deals ([1 contact]) have [X%] lower win rate\n```\n\n#### Step 6: Analyze Qualification Patterns\n\n**6.1 Compare BANT Completion:**\n```\n| Qualification Factor | Won % Complete | Lost % Complete | Gap |\n|---------------------|----------------|-----------------|-----|\n| Budget Confirmed | [X%] | [Y%] | [Z%] |\n| Decision Maker ID'd | [X%] | [Y%] | [Z%] |\n| Need Validated | [X%] | [Y%] | [Z%] |\n| Timeline Defined | [X%] | [Y%] | [Z%] |\n| Process Understood | [X%] | [Y%] | [Z%] |\n\nINSIGHT:\n- Biggest qualification gap: [Factor] ([X%] difference)\n- Deals without confirmed budget are [X]x more likely to lose\n- Decision maker engagement is strongest predictor of win\n```\n\n**6.2 Analyze by Sales Stage at Loss:**\n```\nFor lost deals, at which stage did they lose?\n\n| Stage at Loss | Count | % of Losses | Value Lost |\n|---------------|-------|-------------|------------|\n| Qualify | [N] | [X%] | $[Y] |\n| Develop | [N] | [X%] | $[Y] |\n| Propose | [N] | [X%] | $[Y] |\n| Close | [N] | [X%] | $[Y] |\n\nINSIGHT:\n- [X%] of losses happen at [Stage]\n- Late-stage losses (Propose\u002FClose) indicate [specific issue]\n- Early losses (Qualify) may indicate poor lead quality\n```\n\n#### Step 7: Analyze Deal Characteristics\n\n**7.1 Compare Deal Attributes:**\n```\n| Attribute | Won Avg\u002FMode | Lost Avg\u002FMode | Pattern |\n|-----------|--------------|---------------|---------|\n| Deal Size | $[X] | $[Y] | [Larger\u002Fsmaller lose more?] |\n| Company Size | [X] employees | [Y] employees | [Sweet spot?] |\n| Industry Mix | [breakdown] | [breakdown] | [Industry patterns] |\n| Source | [top sources] | [top sources] | [Source quality] |\n\nDEAL SIZE ANALYSIS:\n- Win rate by deal size:\n $0-25K: [X%]\n $25K-100K: [Y%]\n $100K-500K: [Z%]\n $500K+: [W%]\n \nINSIGHT: Win rate drops significantly above $[threshold]\n```\n\n**7.2 Competitive Analysis:**\n```\nAnalyze mentions of competitors in descriptions and notes:\n\n| Competitor | Times Faced | We Won | We Lost | Win Rate vs Them |\n|------------|-------------|--------|---------|------------------|\n| Competitor A | [N] | [W] | [L] | [X%] |\n| Competitor B | [N] | [W] | [L] | [X%] |\n| Competitor C | [N] | [W] | [L] | [X%] |\n| No Competitor | [N] | [W] | [L] | [X%] |\n\nINSIGHT:\n- We struggle against [Competitor] (only [X%] win rate)\n- We dominate against [Competitor] ([Y%] win rate)\n- Deals with no competition have [Z%] win rate\n```\n\n#### Step 8: Identify Differentiating Factors\n\n**8.1 Statistical Analysis:**\nCalculate correlation between each factor and win probability:\n\n```\nFACTORS MOST CORRELATED WITH WINNING:\n1. Economic buyer engagement (r = 0.72)\n2. Number of meetings (r = 0.65)\n3. Multi-threading (3+ contacts) (r = 0.61)\n4. Budget confirmation (r = 0.58)\n5. Response time to inquiries (r = 0.54)\n\nFACTORS MOST CORRELATED WITH LOSING:\n1. Single-threaded relationship (r = -0.68)\n2. Extended time in Propose stage (r = -0.55)\n3. Competitor [X] involvement (r = -0.52)\n4. Activity gaps > 10 days (r = -0.48)\n5. Missing decision maker engagement (r = -0.45)\n```\n\n**8.2 What Winners Did Differently:**\n```\nWINNING BEHAVIORS:\n✓ Engaged economic buyer by [X] stage in [Y%] of won deals\n✓ Averaged [X] in-person\u002Fvideo meetings\n✓ Multi-threaded with [X]+ stakeholders\n✓ Confirmed budget before Propose stage\n✓ Maintained [X] activities per week minimum\n✓ Closed within [X] days of proposal submission\n✓ Had internal champion identified\n\nLOSING BEHAVIORS:\n✗ Single-threaded with only one contact\n✗ Skipped discovery, went straight to proposal\n✗ Long gaps between activities (10+ days)\n✗ Never engaged economic buyer\n✗ Let proposal sit for [X]+ days without follow-up\n✗ Didn't qualify budget until late stage\n```\n\n#### Step 9: Generate Playbook Insights\n\n**Output Format:**\n\n```\n════════════════════════════════════════════════════════════════\nWIN\u002FLOSS PATTERN ANALYSIS\n════════════════════════════════════════════════════════════════\n\nAnalysis Criteria:\n• Segment: Enterprise deals (>$100K)\n• Industry: Manufacturing\n• Time Period: Last 12 months\n• Total Deals Analyzed: [N] (Won: [W], Lost: [L])\n\n════════════════════════════════════════════════════════════════\nEXECUTIVE SUMMARY\n════════════════════════════════════════════════════════════════\n\nOverall Win Rate: [X%]\nAverage Deal Size - Won: $[X] | Lost: $[Y]\nAverage Sales Cycle - Won: [X] days | Lost: [Y] days\n\nTOP 3 REASONS WE'RE LOSING:\n1. Single-threaded relationships (72% of losses)\n2. Late-stage competitor entry (48% of losses)\n3. Extended time in Propose stage (43% of losses)\n\nTOP 3 THINGS WINNERS DO DIFFERENTLY:\n1. Engage economic buyer before Propose stage\n2. Multi-thread with 4+ stakeholders\n3. Maintain weekly touchpoints throughout cycle\n\n════════════════════════════════════════════════════════════════\nDETAILED ANALYSIS\n════════════════════════════════════════════════════════════════\n\n📊 SALES CYCLE COMPARISON\n────────────────────────────────────────────────────────────────\n\n WON LOST INSIGHT\nAverage Cycle: 68 days 92 days Winners close 26% faster\nTime in Qualify: 12 days 18 days Faster qualification\nTime in Develop: 28 days 35 days Efficient discovery\nTime in Propose: 18 days 32 days ⚠️ Key difference\nTime in Close: 10 days 7 days Similar (losses give up)\n\nKEY INSIGHT: Deals in Propose stage >25 days have 67% lower win rate.\nACTION: If no progress after 20 days, escalate or re-qualify.\n\n📊 ACTIVITY PATTERN COMPARISON\n────────────────────────────────────────────────────────────────\n\n WON AVG LOST AVG DELTA\nTotal Activities: 24 16 +50%\nPhone Calls: 8 4 +100% ⬆️\nMeetings: 5 2 +150% ⬆️\nEmails: 10 9 Similar\nTasks: 6 3 +100%\n\nACTIVITY FREQUENCY:\n- Won deals: 3.2 activities\u002Fweek average\n- Lost deals: 1.8 activities\u002Fweek average\n- Gap widens in weeks 3-6 of sales cycle\n\nKEY INSIGHT: Winning deals have 2x the phone calls and meetings.\nACTION: Minimum 2 calls and 1 meeting per week during active pursuit.\n\n📊 STAKEHOLDER ENGAGEMENT\n────────────────────────────────────────────────────────────────\n\n WON LOST DELTA\nContacts Engaged: 4.2 1.8 +133% ⬆️\nEconomic Buyer Met: 78% 23% +55% ⬆️⬆️\nChampion Identified: 85% 34% +51% ⬆️⬆️\nMulti-threaded (3+): 72% 18% +54% ⬆️⬆️\n\nCONTACT ROLE ANALYSIS:\n- Won deals engage VP+ in 78% of cases\n- Lost deals often stuck at Manager level\n- Single-threaded deals win only 12% of the time\n\nKEY INSIGHT: Economic buyer engagement is the #1 predictor of winning.\nACTION: Do not move to Propose without executive meeting scheduled.\n\n📊 QUALIFICATION ANALYSIS\n────────────────────────────────────────────────────────────────\n\n WON LOST GAP\nBudget Confirmed: 82% 41% +41%\nDecision Maker ID: 91% 52% +39%\nNeed Validated: 88% 67% +21%\nTimeline Defined: 76% 48% +28%\nProcess Understood: 84% 35% +49% ⬆️\n\nKEY INSIGHT: Understanding the buying process is critical but often skipped.\nACTION: Always ask \"Walk me through your decision process\" in discovery.\n\n📊 COMPETITIVE ANALYSIS\n────────────────────────────────────────────────────────────────\n\nCOMPETITOR WIN RATES:\n• vs. Acme Corp: 35% (significant weakness)\n• vs. GlobalTech: 62% (slight advantage) \n• vs. No competitor: 78% (best scenario)\n• Multi-vendor evaluation: 42%\n\nACME CORP PATTERN:\n- They win on price (mentioned in 80% of losses to them)\n- We win on service\u002Fsupport (mentioned in wins against them)\n- They entered late-stage in 60% of their wins\n\nKEY INSIGHT: When Acme is involved, emphasize support\u002Fservice early.\nACTION: If Acme detected, proactively address price with ROI analysis.\n\n════════════════════════════════════════════════════════════════\nPLAYBOOK RECOMMENDATIONS\n════════════════════════════════════════════════════════════════\n\nSTAGE: QUALIFY\n────────────────────────────────────────────────────────────────\n□ Confirm budget status in first substantive call\n□ Identify and map all stakeholders by role\n□ Understand buying process and timeline\n□ Ask about other solutions being evaluated\n\nBenchmark: Complete Qualify in ≤14 days\nRed Flag: Can't identify economic buyer after 2 weeks\n\nSTAGE: DEVELOP\n────────────────────────────────────────────────────────────────\n□ Schedule meeting with economic buyer\n□ Engage minimum 3 stakeholders\n□ Identify and enable champion\n□ Complete technical validation\n□ Address competitive positioning proactively\n\nBenchmark: Minimum 3 activities per week\nRed Flag: Only one contact engaged; no exec access\n\nSTAGE: PROPOSE\n────────────────────────────────────────────────────────────────\n□ Proposal walk-through meeting (don't just email)\n□ Economic buyer reviews proposal directly\n□ Address objections within 48 hours\n□ Negotiate with decision-maker present\n\nBenchmark: Decision within 21 days of proposal\nRed Flag: >25 days in Propose without progress\n\nSTAGE: CLOSE\n────────────────────────────────────────────────────────────────\n□ Verbal commitment from economic buyer\n□ Legal\u002Fprocurement engaged early\n□ Implementation timeline discussed\n□ Success criteria defined\n\nBenchmark: Contract signed within 14 days of verbal\nRed Flag: Legal delays without clear timeline\n\n════════════════════════════════════════════════════════════════\nEARLY WARNING SIGNALS\n════════════════════════════════════════════════════════════════\n\nWatch for these loss indicators:\n⚠️ Single contact engagement after 3 weeks\n⚠️ Can't schedule economic buyer meeting\n⚠️ Activity gap >10 days in active stage\n⚠️ Competitor mentioned in late stage\n⚠️ Budget discussion deferred repeatedly\n⚠️ Proposal sitting without response >14 days\n⚠️ \"We need more time\" without specific next step\n\n════════════════════════════════════════════════════════════════\n```\n\n### Dataverse Tables Used\n| Table | Purpose |\n|-------|---------|\n| `opportunity` | Primary entity for win\u002Floss data |\n| `account` | Industry and firmographic filters |\n| `contact` | Stakeholder engagement analysis |\n| `activitypointer` | Activity pattern analysis |\n| `phonecall` | Call frequency analysis |\n| `appointment` | Meeting frequency analysis |\n| `email` | Email engagement |\n| `annotation` | Notes for competitive intelligence |\n\n### Key Fields Reference\n**opportunity:**\n- `statecode` (STATE) - Open(0), Won(1), Lost(2)\n- `statuscode` (STATUS) - In Progress(1), On Hold(2) [Open]; Won(3) [Won]; Canceled(4), Out-Sold(5) [Lost]\n- `createdon` (DATETIME) - Start of sales cycle\n- `actualclosedate` (DATE) - End of sales cycle (when closed)\n- `estimatedvalue` (MONEY) - Expected deal size\n- `actualvalue` (MONEY) - Actual won value\n- `salesstage` (CHOICE) - Stage at close: Qualify(0), Develop(1), Propose(2), Close(3)\n- `budgetstatus` (CHOICE) - No Budget(0), May Buy(1), Can Buy(2), Will Buy(3)\n- `need` (CHOICE) - Must have(0), Should have(1), Good to have(2), No need(3)\n- `purchasetimeframe` (CHOICE) - Immediate(0), This Quarter(1), Next Quarter(2), This Year(3), Unknown(4)\n- `decisionmaker` (BIT) - Was decision maker engaged\n- `closeprobability` (INT) - Final win probability (0-100)\n- `msdyn_opportunityscore` (INT) - AI predictive score at close\n- `msdyn_opportunitygrade` (CHOICE) - Grade A(0), B(1), C(2), D(3)\n\n**account:**\n- `industrycode` (CHOICE) - Industry classification (Accounting(1), Agriculture(2), etc.)\n- `numberofemployees` (INT) - Company size\n- `revenue` (MONEY) - Annual revenue\n\n### Analysis Best Practices\n\n1. **Sufficient sample size:** Need minimum 20-30 deals for meaningful patterns\n2. **Control variables:** Compare similar deal sizes and industries\n3. **Time relevance:** Focus on recent data (last 12-18 months)\n4. **Qualitative context:** Numbers show what, notes show why\n5. **Action-oriented:** Every insight should drive specific behavior change\n6. **Regular refresh:** Re-run analysis quarterly to update playbook\n\n## Examples\n\n### Example 1: Why Are We Losing Enterprise Deals?\n\n**User says:** \"Why are we losing enterprise deals in manufacturing?\"\n\n**Actions:**\n1. Filter opportunities: estimatedvalue > $100K, industry = manufacturing\n2. Segment into won (statecode=1) vs lost (statecode=2)\n3. Compare sales cycles, activity patterns, stakeholder engagement\n4. Identify statistically significant differentiators\n\n**Result:**\n```\nWIN\u002FLOSS ANALYSIS: Enterprise Manufacturing\nPeriod: Last 12 months | Won: 12 | Lost: 18 | Win Rate: 40%\n\nKEY DIFFERENTIATORS:\n\n1. SALES CYCLE\n Won: 65 days avg | Lost: 98 days avg\n Insight: Deals dragging past 80 days are 3x more likely to lose\n\n2. STAKEHOLDER ENGAGEMENT\n Won: 3.2 contacts engaged avg | Lost: 1.4 contacts\n Insight: Multi-threading increases win rate by 45%\n\n3. ACTIVITY PATTERNS\n Won: 2.1 meetings per deal | Lost: 0.8 meetings\n Insight: Face-to-face engagement critical in manufacturing\n\nRECOMMENDATIONS:\n- Set 80-day checkpoint for deal health review\n- Require 3+ contacts engaged before Propose stage\n- Schedule on-site visits for deals > $100K\n```\n\n### Example 2: Compare Top Rep vs Team Average\n\n**User says:** \"What does Sarah do differently to win more deals?\"\n\n**Actions:**\n1. Filter Sarah's closed deals vs team average\n2. Compare activity types, timing, stakeholder engagement\n3. Identify behavioral differences\n\n**Result:**\n```\nSARAH'S WINNING PATTERNS:\n\n1. SPEED TO FIRST MEETING\n Sarah: 2.1 days | Team avg: 5.3 days\n \n2. MULTI-THREADING\n Sarah: Always adds 2nd contact by day 7\n Team avg: Single contact for first 21 days\n \n3. ACTIVITY MIX\n Sarah: 60% calls, 30% meetings, 10% email\n Team: 20% calls, 10% meetings, 70% email\n\nPLAYBOOK RECOMMENDATION:\nAdopt Sarah's \"24-48-7\" rule: First call within 24 hours, \nfirst meeting within 48 hours, second contact by day 7.\n```\n\n### Example 3: Competitive Loss Analysis\n\n**User says:** \"Why are we losing to Acme Corp?\"\n\n**Actions:**\n1. Find lost deals with Acme mentioned (description, notes, opportunityclose)\n2. Analyze deal characteristics and loss patterns\n3. Generate competitive positioning recommendations\n\n**Result:**\n```\nCOMPETITIVE ANALYSIS: vs Acme Corp\nDeals Lost to Acme: 8 | Total Competitive: 15 | Loss Rate: 53%\n\nLOSS PATTERNS:\n- 75% lost on price (Acme undercuts by avg 20%)\n- 25% lost on feature (Acme's mobile app cited)\n\nWHERE WE WIN vs ACME:\n- Enterprise segment (62% win rate)\n- When economic buyer engaged early\n- When implementation timeline is priority\n\nBATTLECARD TALKING POINTS:\n1. Emphasize TCO, not initial price\n2. Lead with enterprise security\u002Fcompliance\n3. Engage economic buyer before Acme can anchor on price\n```\n\n## Troubleshooting\n\n### Error: Insufficient data for analysis\n**Cause:** Too few closed deals matching criteria\n**Solution:**\n- Expand date range\n- Broaden filters (combine industries, expand size range)\n- Note limited sample size in results\n\n### Error: No clear patterns found\n**Cause:** High variance in data or too many confounding variables\n**Solution:**\n- Narrow analysis to more homogeneous segment\n- Focus on extreme cases (fastest wins, longest losses)\n- Supplement with qualitative analysis of notes\n\n### Error: Activity data incomplete\n**Cause:** Activities not consistently linked to opportunities\n**Solution:**\n- Query activities for related accounts as backup\n- Use date overlap method (activities during deal lifecycle)\n- Advise on data hygiene improvements\n",{"data":37,"body":41},{"name":4,"description":6,"metadata":38},{"author":24,"version":39,"category":40},"1.0.0","sales-analytics",{"type":42,"children":43},"root",[44,53,59,66,73,78,89,124,132,142,155,160,168,177,184,192,201,209,218,226,235,241,249,258,263,271,280,288,297,303,311,320,328,337,345,354,362,371,377,385,406,415,428,436,445,453,462,468,476,485,493,502,508,516,525,533,542,548,558,567,575,584,590,598,607,613,776,782,790,967,975,1011,1017,1081,1087,1093,1103,1111,1134,1142,1151,1157,1166,1173,1191,1198,1207,1213,1222,1229,1247,1254,1263,1269,1275,1290,1308,1314,1327,1345,1351,1364],{"type":45,"tag":46,"props":47,"children":49},"element","h1",{"id":48},"winloss-pattern-analyzer",[50],{"type":51,"value":52},"text","Win\u002FLoss Pattern Analyzer",{"type":45,"tag":54,"props":55,"children":56},"p",{},[57],{"type":51,"value":58},"Sales teams need to understand why they win and lose deals. This skill analyzes historical closed opportunities to identify patterns, highlight what winners do differently, recognize common loss signals, and provide data-driven playbook recommendations.",{"type":45,"tag":60,"props":61,"children":63},"h2",{"id":62},"instructions",[64],{"type":51,"value":65},"Instructions",{"type":45,"tag":67,"props":68,"children":70},"h3",{"id":69},"step-1-define-analysis-scope",[71],{"type":51,"value":72},"Step 1: Define Analysis Scope",{"type":45,"tag":54,"props":74,"children":75},{},[76],{"type":51,"value":77},"When user asks \"Why are we losing enterprise deals in manufacturing vertical?\":",{"type":45,"tag":54,"props":79,"children":80},{},[81,87],{"type":45,"tag":82,"props":83,"children":84},"strong",{},[85],{"type":51,"value":86},"1.1 Parse Analysis Criteria:",{"type":51,"value":88},"\nExtract filters from user query:",{"type":45,"tag":90,"props":91,"children":92},"ul",{},[93,99,104,109,114,119],{"type":45,"tag":94,"props":95,"children":96},"li",{},[97],{"type":51,"value":98},"Deal size segment (enterprise, mid-market, SMB)",{"type":45,"tag":94,"props":100,"children":101},{},[102],{"type":51,"value":103},"Industry\u002Fvertical (manufacturing, financial services, etc.)",{"type":45,"tag":94,"props":105,"children":106},{},[107],{"type":51,"value":108},"Time period (last 6 months, last year, etc.)",{"type":45,"tag":94,"props":110,"children":111},{},[112],{"type":51,"value":113},"Sales stage of loss (if applicable)",{"type":45,"tag":94,"props":115,"children":116},{},[117],{"type":51,"value":118},"Competitor (if mentioned)",{"type":45,"tag":94,"props":120,"children":121},{},[122],{"type":51,"value":123},"Owner\u002Fteam (if specified)",{"type":45,"tag":54,"props":125,"children":126},{},[127],{"type":45,"tag":82,"props":128,"children":129},{},[130],{"type":51,"value":131},"1.2 Build Analysis Query:",{"type":45,"tag":54,"props":133,"children":134},{},[135,140],{"type":45,"tag":82,"props":136,"children":137},{},[138],{"type":51,"value":139},"Important: Dataverse SQL Limitations",{"type":51,"value":141},"\nDataverse SQL does NOT support: DATEADD(), GETUTCDATE(), subqueries, HAVING, DISTINCT, UNION, CASE, DATEDIFF.\nCalculate date filters and durations programmatically (e.g., use '2025-03-01' for last year).",{"type":45,"tag":143,"props":144,"children":148},"pre",{"className":145,"code":147,"language":51},[146],"language-text","SELECT opportunityid, name, accountid, customerid, estimatedvalue, actualvalue,\n createdon, actualclosedate, statecode, statuscode,\n salesstage, closeprobability, budgetstatus, need, \n purchasetimeframe, purchaseprocess, decisionmaker,\n description, qualificationcomments, msdyn_forecastcategory,\n ownerid\nFROM opportunity\nWHERE actualclosedate > '2025-03-01'\n",[149],{"type":45,"tag":150,"props":151,"children":153},"code",{"__ignoreMap":152},"",[154],{"type":51,"value":147},{"type":45,"tag":54,"props":156,"children":157},{},[158],{"type":51,"value":159},"Then filter programmatically for statecode = 1 (Won) or statecode = 2 (Lost).",{"type":45,"tag":54,"props":161,"children":162},{},[163],{"type":45,"tag":82,"props":164,"children":165},{},[166],{"type":51,"value":167},"Add Segment Filters:",{"type":45,"tag":143,"props":169,"children":172},{"className":170,"code":171,"language":51},[146],"-- Enterprise deals (example threshold)\nSELECT opportunityid, name, accountid, estimatedvalue, actualvalue,\n createdon, actualclosedate, statecode, statuscode\nFROM opportunity\nWHERE actualclosedate > '2025-03-01'\nAND estimatedvalue >= 100000\n\n-- Industry filter (via account join)\nSELECT o.opportunityid, o.name, o.estimatedvalue, a.industrycode\nFROM opportunity o\nJOIN account a ON o.accountid = a.accountid\nWHERE o.actualclosedate > '2025-03-01'\nAND a.industrycode = 12\n",[173],{"type":45,"tag":150,"props":174,"children":175},{"__ignoreMap":152},[176],{"type":51,"value":171},{"type":45,"tag":178,"props":179,"children":181},"h4",{"id":180},"step-2-segment-won-vs-lost-deals",[182],{"type":51,"value":183},"Step 2: Segment Won vs Lost Deals",{"type":45,"tag":54,"props":185,"children":186},{},[187],{"type":45,"tag":82,"props":188,"children":189},{},[190],{"type":51,"value":191},"2.1 Basic Segmentation:",{"type":45,"tag":143,"props":193,"children":196},{"className":194,"code":195,"language":51},[146],"WON DEALS:\n- Count: [N]\n- Total Value: $[X]\n- Average Value: $[Y]\n- Win Rate: [Z%]\n\nLOST DEALS:\n- Count: [N]\n- Total Value: $[X]\n- Average Value: $[Y]\n- Common Loss Reasons (statuscode):\n - Out-Sold (5): [N]\n - Canceled (4): [N]\n",[197],{"type":45,"tag":150,"props":198,"children":199},{"__ignoreMap":152},[200],{"type":51,"value":195},{"type":45,"tag":54,"props":202,"children":203},{},[204],{"type":45,"tag":82,"props":205,"children":206},{},[207],{"type":51,"value":208},"2.2 Query Won Deals:",{"type":45,"tag":143,"props":210,"children":213},{"className":211,"code":212,"language":51},[146],"SELECT opportunityid, name, accountid, actualvalue, actualclosedate,\n createdon, salesstage, closeprobability,\n budgetstatus, need, purchasetimeframe, decisionmaker, ownerid\nFROM opportunity\nWHERE statecode = 1\nAND actualclosedate > '2025-03-01'\n",[214],{"type":45,"tag":150,"props":215,"children":216},{"__ignoreMap":152},[217],{"type":51,"value":212},{"type":45,"tag":54,"props":219,"children":220},{},[221],{"type":45,"tag":82,"props":222,"children":223},{},[224],{"type":51,"value":225},"2.3 Query Lost Deals:",{"type":45,"tag":143,"props":227,"children":230},{"className":228,"code":229,"language":51},[146],"SELECT opportunityid, name, accountid, estimatedvalue, actualclosedate,\n createdon, statuscode, salesstage,\n budgetstatus, need, purchasetimeframe, decisionmaker, ownerid\nFROM opportunity\nWHERE statecode = 2\nAND actualclosedate > '2025-03-01'\n",[231],{"type":45,"tag":150,"props":232,"children":233},{"__ignoreMap":152},[234],{"type":51,"value":229},{"type":45,"tag":178,"props":236,"children":238},{"id":237},"step-3-analyze-sales-cycle-patterns",[239],{"type":51,"value":240},"Step 3: Analyze Sales Cycle Patterns",{"type":45,"tag":54,"props":242,"children":243},{},[244],{"type":45,"tag":82,"props":245,"children":246},{},[247],{"type":51,"value":248},"3.1 Calculate Sales Cycle Length:",{"type":45,"tag":143,"props":250,"children":253},{"className":251,"code":252,"language":51},[146],"For each opportunity (calculate programmatically):\nsales_cycle_days = actualclosedate - createdon (in days)\n",[254],{"type":45,"tag":150,"props":255,"children":256},{"__ignoreMap":152},[257],{"type":51,"value":252},{"type":45,"tag":54,"props":259,"children":260},{},[261],{"type":51,"value":262},"Note: DATEDIFF is not supported in Dataverse SQL. Calculate durations in your application logic.",{"type":45,"tag":54,"props":264,"children":265},{},[266],{"type":45,"tag":82,"props":267,"children":268},{},[269],{"type":51,"value":270},"3.2 Compare Won vs Lost Cycles:",{"type":45,"tag":143,"props":272,"children":275},{"className":273,"code":274,"language":51},[146],"WON DEALS:\n- Average Sales Cycle: [X] days\n- Median Sales Cycle: [Y] days\n- Shortest: [Z] days\n- Longest: [W] days\n\nLOST DEALS:\n- Average Sales Cycle: [X] days\n- Median Sales Cycle: [Y] days\n- Shortest: [Z] days\n- Longest: [W] days\n\nINSIGHT:\n- Deals that drag [X]+ days are [Y]x more likely to lose\n- Sweet spot for wins: [A] - [B] days\n",[276],{"type":45,"tag":150,"props":277,"children":278},{"__ignoreMap":152},[279],{"type":51,"value":274},{"type":45,"tag":54,"props":281,"children":282},{},[283],{"type":45,"tag":82,"props":284,"children":285},{},[286],{"type":51,"value":287},"3.3 Analyze Stage Duration:",{"type":45,"tag":143,"props":289,"children":292},{"className":290,"code":291,"language":51},[146],"For each deal, calculate time in each stage:\n- Time in Qualify\n- Time in Develop\n- Time in Propose\n- Time in Close\n\nCompare averages between won and lost:\n| Stage | Won Avg Days | Lost Avg Days | Difference |\n|-------|--------------|---------------|------------|\n| Qualify | [X] | [Y] | [+\u002F-Z] |\n| Develop | [X] | [Y] | [+\u002F-Z] |\n| Propose | [X] | [Y] | [+\u002F-Z] |\n| Close | [X] | [Y] | [+\u002F-Z] |\n",[293],{"type":45,"tag":150,"props":294,"children":295},{"__ignoreMap":152},[296],{"type":51,"value":291},{"type":45,"tag":178,"props":298,"children":300},{"id":299},"step-4-analyze-activity-patterns",[301],{"type":51,"value":302},"Step 4: Analyze Activity Patterns",{"type":45,"tag":54,"props":304,"children":305},{},[306],{"type":45,"tag":82,"props":307,"children":308},{},[309],{"type":51,"value":310},"4.1 Query Activities for Won Deals:",{"type":45,"tag":143,"props":312,"children":315},{"className":313,"code":314,"language":51},[146],"SELECT o.opportunityid, a.activitytypecode, COUNT(*) as count\nFROM opportunity o\nJOIN activitypointer a ON o.opportunityid = a.regardingobjectid\nWHERE o.statecode = 1\nAND [segment filters]\nGROUP BY o.opportunityid, a.activitytypecode\n",[316],{"type":45,"tag":150,"props":317,"children":318},{"__ignoreMap":152},[319],{"type":51,"value":314},{"type":45,"tag":54,"props":321,"children":322},{},[323],{"type":45,"tag":82,"props":324,"children":325},{},[326],{"type":51,"value":327},"4.2 Query Activities for Lost Deals:",{"type":45,"tag":143,"props":329,"children":332},{"className":330,"code":331,"language":51},[146],"SELECT o.opportunityid, a.activitytypecode, COUNT(*) as count\nFROM opportunity o\nJOIN activitypointer a ON o.opportunityid = a.regardingobjectid\nWHERE o.statecode = 2\nAND [segment filters]\nGROUP BY o.opportunityid, a.activitytypecode\n",[333],{"type":45,"tag":150,"props":334,"children":335},{"__ignoreMap":152},[336],{"type":51,"value":331},{"type":45,"tag":54,"props":338,"children":339},{},[340],{"type":45,"tag":82,"props":341,"children":342},{},[343],{"type":51,"value":344},"4.3 Compare Activity Metrics:",{"type":45,"tag":143,"props":346,"children":349},{"className":347,"code":348,"language":51},[146],"| Metric | Won Avg | Lost Avg | Delta | Insight |\n|--------|---------|----------|-------|---------|\n| Total Activities | [X] | [Y] | [+\u002F-Z] | Winners have more touchpoints |\n| Phone Calls | [X] | [Y] | [+\u002F-Z] | Calls correlate with wins |\n| Meetings | [X] | [Y] | [+\u002F-Z] | Face time matters |\n| Emails | [X] | [Y] | [+\u002F-Z] | Similar email volume |\n| Tasks Completed | [X] | [Y] | [+\u002F-Z] | Execution discipline |\n\nACTIVITY PATTERNS:\n- Won deals average [X] activities, lost deals average [Y]\n- [Z]% more phone calls in won deals\n- Won deals have [W]x more in-person meetings\n",[350],{"type":45,"tag":150,"props":351,"children":352},{"__ignoreMap":152},[353],{"type":51,"value":348},{"type":45,"tag":54,"props":355,"children":356},{},[357],{"type":45,"tag":82,"props":358,"children":359},{},[360],{"type":51,"value":361},"4.4 Activity Frequency Analysis:",{"type":45,"tag":143,"props":363,"children":366},{"className":364,"code":365,"language":51},[146],"Calculate activities per week throughout sales cycle:\n\nWon Deals Activity Curve:\nWeek 1: [avg activities]\nWeek 2: [avg activities]\nWeek 3: [avg activities]\n...\n\nLost Deals Activity Curve:\nWeek 1: [avg activities]\nWeek 2: [avg activities]\nWeek 3: [avg activities]\n...\n\nINSIGHT:\n- Winners maintain consistent engagement\n- Losers often show activity gaps in weeks [X-Y]\n- Key difference at [stage]: winners have [X] more activities\n",[367],{"type":45,"tag":150,"props":368,"children":369},{"__ignoreMap":152},[370],{"type":51,"value":365},{"type":45,"tag":178,"props":372,"children":374},{"id":373},"step-5-analyze-stakeholder-engagement",[375],{"type":51,"value":376},"Step 5: Analyze Stakeholder Engagement",{"type":45,"tag":54,"props":378,"children":379},{},[380],{"type":45,"tag":82,"props":381,"children":382},{},[383],{"type":51,"value":384},"5.1 Count Contacts Engaged:",{"type":45,"tag":54,"props":386,"children":387},{},[388,390,396,398,404],{"type":51,"value":389},"Contacts involved in activities are stored in ",{"type":45,"tag":150,"props":391,"children":393},{"className":392},[],[394],{"type":51,"value":395},"activityparty",{"type":51,"value":397},", not ",{"type":45,"tag":150,"props":399,"children":401},{"className":400},[],[402],{"type":51,"value":403},"activitypointer",{"type":51,"value":405},". Run per opportunity:",{"type":45,"tag":143,"props":407,"children":410},{"className":408,"code":409,"language":51},[146],"SELECT ap.partyid, ap.participationtypemask\nFROM activityparty ap\nJOIN activitypointer a ON ap.activityid = a.activityid\nWHERE a.regardingobjectid = '[opportunityid]'\nAND a.statecode = 1\n",[411],{"type":45,"tag":150,"props":412,"children":413},{"__ignoreMap":152},[414],{"type":51,"value":409},{"type":45,"tag":54,"props":416,"children":417},{},[418,420,426],{"type":51,"value":419},"Deduplicate ",{"type":45,"tag":150,"props":421,"children":423},{"className":422},[],[424],{"type":51,"value":425},"partyid",{"type":51,"value":427}," values programmatically per opportunity to count unique contacts engaged.",{"type":45,"tag":54,"props":429,"children":430},{},[431],{"type":45,"tag":82,"props":432,"children":433},{},[434],{"type":51,"value":435},"5.2 Analyze Contact Roles:",{"type":45,"tag":143,"props":437,"children":440},{"className":438,"code":439,"language":51},[146],"Identify roles of engaged contacts:\n- Economic Buyers (C-level, VP)\n- Technical Evaluators (Directors, Managers)\n- End Users (Individual Contributors)\n- Procurement\u002FLegal\n",[441],{"type":45,"tag":150,"props":442,"children":443},{"__ignoreMap":152},[444],{"type":51,"value":439},{"type":45,"tag":54,"props":446,"children":447},{},[448],{"type":45,"tag":82,"props":449,"children":450},{},[451],{"type":51,"value":452},"5.3 Compare Stakeholder Engagement:",{"type":45,"tag":143,"props":454,"children":457},{"className":455,"code":456,"language":51},[146],"| Metric | Won Deals | Lost Deals | Insight |\n|--------|-----------|------------|---------|\n| Avg Contacts Engaged | [X] | [Y] | Wider engagement wins |\n| Economic Buyer Engaged | [X%] | [Y%] | Must engage decision maker |\n| Multi-threaded (3+ contacts) | [X%] | [Y%] | Don't single-thread |\n| Champion Identified | [X%] | [Y%] | Internal advocates matter |\n\nKEY FINDING:\n- Won deals engaged [X] contacts on average vs [Y] for lost\n- [Z%] of won deals had economic buyer engagement vs [W%] for lost\n- Single-threaded deals ([1 contact]) have [X%] lower win rate\n",[458],{"type":45,"tag":150,"props":459,"children":460},{"__ignoreMap":152},[461],{"type":51,"value":456},{"type":45,"tag":178,"props":463,"children":465},{"id":464},"step-6-analyze-qualification-patterns",[466],{"type":51,"value":467},"Step 6: Analyze Qualification Patterns",{"type":45,"tag":54,"props":469,"children":470},{},[471],{"type":45,"tag":82,"props":472,"children":473},{},[474],{"type":51,"value":475},"6.1 Compare BANT Completion:",{"type":45,"tag":143,"props":477,"children":480},{"className":478,"code":479,"language":51},[146],"| Qualification Factor | Won % Complete | Lost % Complete | Gap |\n|---------------------|----------------|-----------------|-----|\n| Budget Confirmed | [X%] | [Y%] | [Z%] |\n| Decision Maker ID'd | [X%] | [Y%] | [Z%] |\n| Need Validated | [X%] | [Y%] | [Z%] |\n| Timeline Defined | [X%] | [Y%] | [Z%] |\n| Process Understood | [X%] | [Y%] | [Z%] |\n\nINSIGHT:\n- Biggest qualification gap: [Factor] ([X%] difference)\n- Deals without confirmed budget are [X]x more likely to lose\n- Decision maker engagement is strongest predictor of win\n",[481],{"type":45,"tag":150,"props":482,"children":483},{"__ignoreMap":152},[484],{"type":51,"value":479},{"type":45,"tag":54,"props":486,"children":487},{},[488],{"type":45,"tag":82,"props":489,"children":490},{},[491],{"type":51,"value":492},"6.2 Analyze by Sales Stage at Loss:",{"type":45,"tag":143,"props":494,"children":497},{"className":495,"code":496,"language":51},[146],"For lost deals, at which stage did they lose?\n\n| Stage at Loss | Count | % of Losses | Value Lost |\n|---------------|-------|-------------|------------|\n| Qualify | [N] | [X%] | $[Y] |\n| Develop | [N] | [X%] | $[Y] |\n| Propose | [N] | [X%] | $[Y] |\n| Close | [N] | [X%] | $[Y] |\n\nINSIGHT:\n- [X%] of losses happen at [Stage]\n- Late-stage losses (Propose\u002FClose) indicate [specific issue]\n- Early losses (Qualify) may indicate poor lead quality\n",[498],{"type":45,"tag":150,"props":499,"children":500},{"__ignoreMap":152},[501],{"type":51,"value":496},{"type":45,"tag":178,"props":503,"children":505},{"id":504},"step-7-analyze-deal-characteristics",[506],{"type":51,"value":507},"Step 7: Analyze Deal Characteristics",{"type":45,"tag":54,"props":509,"children":510},{},[511],{"type":45,"tag":82,"props":512,"children":513},{},[514],{"type":51,"value":515},"7.1 Compare Deal Attributes:",{"type":45,"tag":143,"props":517,"children":520},{"className":518,"code":519,"language":51},[146],"| Attribute | Won Avg\u002FMode | Lost Avg\u002FMode | Pattern |\n|-----------|--------------|---------------|---------|\n| Deal Size | $[X] | $[Y] | [Larger\u002Fsmaller lose more?] |\n| Company Size | [X] employees | [Y] employees | [Sweet spot?] |\n| Industry Mix | [breakdown] | [breakdown] | [Industry patterns] |\n| Source | [top sources] | [top sources] | [Source quality] |\n\nDEAL SIZE ANALYSIS:\n- Win rate by deal size:\n $0-25K: [X%]\n $25K-100K: [Y%]\n $100K-500K: [Z%]\n $500K+: [W%]\n \nINSIGHT: Win rate drops significantly above $[threshold]\n",[521],{"type":45,"tag":150,"props":522,"children":523},{"__ignoreMap":152},[524],{"type":51,"value":519},{"type":45,"tag":54,"props":526,"children":527},{},[528],{"type":45,"tag":82,"props":529,"children":530},{},[531],{"type":51,"value":532},"7.2 Competitive Analysis:",{"type":45,"tag":143,"props":534,"children":537},{"className":535,"code":536,"language":51},[146],"Analyze mentions of competitors in descriptions and notes:\n\n| Competitor | Times Faced | We Won | We Lost | Win Rate vs Them |\n|------------|-------------|--------|---------|------------------|\n| Competitor A | [N] | [W] | [L] | [X%] |\n| Competitor B | [N] | [W] | [L] | [X%] |\n| Competitor C | [N] | [W] | [L] | [X%] |\n| No Competitor | [N] | [W] | [L] | [X%] |\n\nINSIGHT:\n- We struggle against [Competitor] (only [X%] win rate)\n- We dominate against [Competitor] ([Y%] win rate)\n- Deals with no competition have [Z%] win rate\n",[538],{"type":45,"tag":150,"props":539,"children":540},{"__ignoreMap":152},[541],{"type":51,"value":536},{"type":45,"tag":178,"props":543,"children":545},{"id":544},"step-8-identify-differentiating-factors",[546],{"type":51,"value":547},"Step 8: Identify Differentiating Factors",{"type":45,"tag":54,"props":549,"children":550},{},[551,556],{"type":45,"tag":82,"props":552,"children":553},{},[554],{"type":51,"value":555},"8.1 Statistical Analysis:",{"type":51,"value":557},"\nCalculate correlation between each factor and win probability:",{"type":45,"tag":143,"props":559,"children":562},{"className":560,"code":561,"language":51},[146],"FACTORS MOST CORRELATED WITH WINNING:\n1. Economic buyer engagement (r = 0.72)\n2. Number of meetings (r = 0.65)\n3. Multi-threading (3+ contacts) (r = 0.61)\n4. Budget confirmation (r = 0.58)\n5. Response time to inquiries (r = 0.54)\n\nFACTORS MOST CORRELATED WITH LOSING:\n1. Single-threaded relationship (r = -0.68)\n2. Extended time in Propose stage (r = -0.55)\n3. Competitor [X] involvement (r = -0.52)\n4. Activity gaps > 10 days (r = -0.48)\n5. Missing decision maker engagement (r = -0.45)\n",[563],{"type":45,"tag":150,"props":564,"children":565},{"__ignoreMap":152},[566],{"type":51,"value":561},{"type":45,"tag":54,"props":568,"children":569},{},[570],{"type":45,"tag":82,"props":571,"children":572},{},[573],{"type":51,"value":574},"8.2 What Winners Did Differently:",{"type":45,"tag":143,"props":576,"children":579},{"className":577,"code":578,"language":51},[146],"WINNING BEHAVIORS:\n✓ Engaged economic buyer by [X] stage in [Y%] of won deals\n✓ Averaged [X] in-person\u002Fvideo meetings\n✓ Multi-threaded with [X]+ stakeholders\n✓ Confirmed budget before Propose stage\n✓ Maintained [X] activities per week minimum\n✓ Closed within [X] days of proposal submission\n✓ Had internal champion identified\n\nLOSING BEHAVIORS:\n✗ Single-threaded with only one contact\n✗ Skipped discovery, went straight to proposal\n✗ Long gaps between activities (10+ days)\n✗ Never engaged economic buyer\n✗ Let proposal sit for [X]+ days without follow-up\n✗ Didn't qualify budget until late stage\n",[580],{"type":45,"tag":150,"props":581,"children":582},{"__ignoreMap":152},[583],{"type":51,"value":578},{"type":45,"tag":178,"props":585,"children":587},{"id":586},"step-9-generate-playbook-insights",[588],{"type":51,"value":589},"Step 9: Generate Playbook Insights",{"type":45,"tag":54,"props":591,"children":592},{},[593],{"type":45,"tag":82,"props":594,"children":595},{},[596],{"type":51,"value":597},"Output Format:",{"type":45,"tag":143,"props":599,"children":602},{"className":600,"code":601,"language":51},[146],"════════════════════════════════════════════════════════════════\nWIN\u002FLOSS PATTERN ANALYSIS\n════════════════════════════════════════════════════════════════\n\nAnalysis Criteria:\n• Segment: Enterprise deals (>$100K)\n• Industry: Manufacturing\n• Time Period: Last 12 months\n• Total Deals Analyzed: [N] (Won: [W], Lost: [L])\n\n════════════════════════════════════════════════════════════════\nEXECUTIVE SUMMARY\n════════════════════════════════════════════════════════════════\n\nOverall Win Rate: [X%]\nAverage Deal Size - Won: $[X] | Lost: $[Y]\nAverage Sales Cycle - Won: [X] days | Lost: [Y] days\n\nTOP 3 REASONS WE'RE LOSING:\n1. Single-threaded relationships (72% of losses)\n2. Late-stage competitor entry (48% of losses)\n3. Extended time in Propose stage (43% of losses)\n\nTOP 3 THINGS WINNERS DO DIFFERENTLY:\n1. Engage economic buyer before Propose stage\n2. Multi-thread with 4+ stakeholders\n3. Maintain weekly touchpoints throughout cycle\n\n════════════════════════════════════════════════════════════════\nDETAILED ANALYSIS\n════════════════════════════════════════════════════════════════\n\n📊 SALES CYCLE COMPARISON\n────────────────────────────────────────────────────────────────\n\n WON LOST INSIGHT\nAverage Cycle: 68 days 92 days Winners close 26% faster\nTime in Qualify: 12 days 18 days Faster qualification\nTime in Develop: 28 days 35 days Efficient discovery\nTime in Propose: 18 days 32 days ⚠️ Key difference\nTime in Close: 10 days 7 days Similar (losses give up)\n\nKEY INSIGHT: Deals in Propose stage >25 days have 67% lower win rate.\nACTION: If no progress after 20 days, escalate or re-qualify.\n\n📊 ACTIVITY PATTERN COMPARISON\n────────────────────────────────────────────────────────────────\n\n WON AVG LOST AVG DELTA\nTotal Activities: 24 16 +50%\nPhone Calls: 8 4 +100% ⬆️\nMeetings: 5 2 +150% ⬆️\nEmails: 10 9 Similar\nTasks: 6 3 +100%\n\nACTIVITY FREQUENCY:\n- Won deals: 3.2 activities\u002Fweek average\n- Lost deals: 1.8 activities\u002Fweek average\n- Gap widens in weeks 3-6 of sales cycle\n\nKEY INSIGHT: Winning deals have 2x the phone calls and meetings.\nACTION: Minimum 2 calls and 1 meeting per week during active pursuit.\n\n📊 STAKEHOLDER ENGAGEMENT\n────────────────────────────────────────────────────────────────\n\n WON LOST DELTA\nContacts Engaged: 4.2 1.8 +133% ⬆️\nEconomic Buyer Met: 78% 23% +55% ⬆️⬆️\nChampion Identified: 85% 34% +51% ⬆️⬆️\nMulti-threaded (3+): 72% 18% +54% ⬆️⬆️\n\nCONTACT ROLE ANALYSIS:\n- Won deals engage VP+ in 78% of cases\n- Lost deals often stuck at Manager level\n- Single-threaded deals win only 12% of the time\n\nKEY INSIGHT: Economic buyer engagement is the #1 predictor of winning.\nACTION: Do not move to Propose without executive meeting scheduled.\n\n📊 QUALIFICATION ANALYSIS\n────────────────────────────────────────────────────────────────\n\n WON LOST GAP\nBudget Confirmed: 82% 41% +41%\nDecision Maker ID: 91% 52% +39%\nNeed Validated: 88% 67% +21%\nTimeline Defined: 76% 48% +28%\nProcess Understood: 84% 35% +49% ⬆️\n\nKEY INSIGHT: Understanding the buying process is critical but often skipped.\nACTION: Always ask \"Walk me through your decision process\" in discovery.\n\n📊 COMPETITIVE ANALYSIS\n────────────────────────────────────────────────────────────────\n\nCOMPETITOR WIN RATES:\n• vs. Acme Corp: 35% (significant weakness)\n• vs. GlobalTech: 62% (slight advantage) \n• vs. No competitor: 78% (best scenario)\n• Multi-vendor evaluation: 42%\n\nACME CORP PATTERN:\n- They win on price (mentioned in 80% of losses to them)\n- We win on service\u002Fsupport (mentioned in wins against them)\n- They entered late-stage in 60% of their wins\n\nKEY INSIGHT: When Acme is involved, emphasize support\u002Fservice early.\nACTION: If Acme detected, proactively address price with ROI analysis.\n\n════════════════════════════════════════════════════════════════\nPLAYBOOK RECOMMENDATIONS\n════════════════════════════════════════════════════════════════\n\nSTAGE: QUALIFY\n────────────────────────────────────────────────────────────────\n□ Confirm budget status in first substantive call\n□ Identify and map all stakeholders by role\n□ Understand buying process and timeline\n□ Ask about other solutions being evaluated\n\nBenchmark: Complete Qualify in ≤14 days\nRed Flag: Can't identify economic buyer after 2 weeks\n\nSTAGE: DEVELOP\n────────────────────────────────────────────────────────────────\n□ Schedule meeting with economic buyer\n□ Engage minimum 3 stakeholders\n□ Identify and enable champion\n□ Complete technical validation\n□ Address competitive positioning proactively\n\nBenchmark: Minimum 3 activities per week\nRed Flag: Only one contact engaged; no exec access\n\nSTAGE: PROPOSE\n────────────────────────────────────────────────────────────────\n□ Proposal walk-through meeting (don't just email)\n□ Economic buyer reviews proposal directly\n□ Address objections within 48 hours\n□ Negotiate with decision-maker present\n\nBenchmark: Decision within 21 days of proposal\nRed Flag: >25 days in Propose without progress\n\nSTAGE: CLOSE\n────────────────────────────────────────────────────────────────\n□ Verbal commitment from economic buyer\n□ Legal\u002Fprocurement engaged early\n□ Implementation timeline discussed\n□ Success criteria defined\n\nBenchmark: Contract signed within 14 days of verbal\nRed Flag: Legal delays without clear timeline\n\n════════════════════════════════════════════════════════════════\nEARLY WARNING SIGNALS\n════════════════════════════════════════════════════════════════\n\nWatch for these loss indicators:\n⚠️ Single contact engagement after 3 weeks\n⚠️ Can't schedule economic buyer meeting\n⚠️ Activity gap >10 days in active stage\n⚠️ Competitor mentioned in late stage\n⚠️ Budget discussion deferred repeatedly\n⚠️ Proposal sitting without response >14 days\n⚠️ \"We need more time\" without specific next step\n\n════════════════════════════════════════════════════════════════\n",[603],{"type":45,"tag":150,"props":604,"children":605},{"__ignoreMap":152},[606],{"type":51,"value":601},{"type":45,"tag":67,"props":608,"children":610},{"id":609},"dataverse-tables-used",[611],{"type":51,"value":612},"Dataverse Tables Used",{"type":45,"tag":614,"props":615,"children":616},"table",{},[617,636],{"type":45,"tag":618,"props":619,"children":620},"thead",{},[621],{"type":45,"tag":622,"props":623,"children":624},"tr",{},[625,631],{"type":45,"tag":626,"props":627,"children":628},"th",{},[629],{"type":51,"value":630},"Table",{"type":45,"tag":626,"props":632,"children":633},{},[634],{"type":51,"value":635},"Purpose",{"type":45,"tag":637,"props":638,"children":639},"tbody",{},[640,658,675,692,708,725,742,759],{"type":45,"tag":622,"props":641,"children":642},{},[643,653],{"type":45,"tag":644,"props":645,"children":646},"td",{},[647],{"type":45,"tag":150,"props":648,"children":650},{"className":649},[],[651],{"type":51,"value":652},"opportunity",{"type":45,"tag":644,"props":654,"children":655},{},[656],{"type":51,"value":657},"Primary entity for win\u002Floss data",{"type":45,"tag":622,"props":659,"children":660},{},[661,670],{"type":45,"tag":644,"props":662,"children":663},{},[664],{"type":45,"tag":150,"props":665,"children":667},{"className":666},[],[668],{"type":51,"value":669},"account",{"type":45,"tag":644,"props":671,"children":672},{},[673],{"type":51,"value":674},"Industry and firmographic filters",{"type":45,"tag":622,"props":676,"children":677},{},[678,687],{"type":45,"tag":644,"props":679,"children":680},{},[681],{"type":45,"tag":150,"props":682,"children":684},{"className":683},[],[685],{"type":51,"value":686},"contact",{"type":45,"tag":644,"props":688,"children":689},{},[690],{"type":51,"value":691},"Stakeholder engagement analysis",{"type":45,"tag":622,"props":693,"children":694},{},[695,703],{"type":45,"tag":644,"props":696,"children":697},{},[698],{"type":45,"tag":150,"props":699,"children":701},{"className":700},[],[702],{"type":51,"value":403},{"type":45,"tag":644,"props":704,"children":705},{},[706],{"type":51,"value":707},"Activity pattern analysis",{"type":45,"tag":622,"props":709,"children":710},{},[711,720],{"type":45,"tag":644,"props":712,"children":713},{},[714],{"type":45,"tag":150,"props":715,"children":717},{"className":716},[],[718],{"type":51,"value":719},"phonecall",{"type":45,"tag":644,"props":721,"children":722},{},[723],{"type":51,"value":724},"Call frequency analysis",{"type":45,"tag":622,"props":726,"children":727},{},[728,737],{"type":45,"tag":644,"props":729,"children":730},{},[731],{"type":45,"tag":150,"props":732,"children":734},{"className":733},[],[735],{"type":51,"value":736},"appointment",{"type":45,"tag":644,"props":738,"children":739},{},[740],{"type":51,"value":741},"Meeting frequency analysis",{"type":45,"tag":622,"props":743,"children":744},{},[745,754],{"type":45,"tag":644,"props":746,"children":747},{},[748],{"type":45,"tag":150,"props":749,"children":751},{"className":750},[],[752],{"type":51,"value":753},"email",{"type":45,"tag":644,"props":755,"children":756},{},[757],{"type":51,"value":758},"Email engagement",{"type":45,"tag":622,"props":760,"children":761},{},[762,771],{"type":45,"tag":644,"props":763,"children":764},{},[765],{"type":45,"tag":150,"props":766,"children":768},{"className":767},[],[769],{"type":51,"value":770},"annotation",{"type":45,"tag":644,"props":772,"children":773},{},[774],{"type":51,"value":775},"Notes for competitive intelligence",{"type":45,"tag":67,"props":777,"children":779},{"id":778},"key-fields-reference",[780],{"type":51,"value":781},"Key Fields Reference",{"type":45,"tag":54,"props":783,"children":784},{},[785],{"type":45,"tag":82,"props":786,"children":787},{},[788],{"type":51,"value":789},"opportunity:",{"type":45,"tag":90,"props":791,"children":792},{},[793,804,835,846,857,868,879,890,901,912,923,934,945,956],{"type":45,"tag":94,"props":794,"children":795},{},[796,802],{"type":45,"tag":150,"props":797,"children":799},{"className":798},[],[800],{"type":51,"value":801},"statecode",{"type":51,"value":803}," (STATE) - Open(0), Won(1), Lost(2)",{"type":45,"tag":94,"props":805,"children":806},{},[807,813,815,821,823,828,830],{"type":45,"tag":150,"props":808,"children":810},{"className":809},[],[811],{"type":51,"value":812},"statuscode",{"type":51,"value":814}," (STATUS) - In Progress(1), On Hold(2) ",{"type":45,"tag":816,"props":817,"children":818},"span",{},[819],{"type":51,"value":820},"Open",{"type":51,"value":822},"; Won(3) ",{"type":45,"tag":816,"props":824,"children":825},{},[826],{"type":51,"value":827},"Won",{"type":51,"value":829},"; Canceled(4), Out-Sold(5) ",{"type":45,"tag":816,"props":831,"children":832},{},[833],{"type":51,"value":834},"Lost",{"type":45,"tag":94,"props":836,"children":837},{},[838,844],{"type":45,"tag":150,"props":839,"children":841},{"className":840},[],[842],{"type":51,"value":843},"createdon",{"type":51,"value":845}," (DATETIME) - Start of sales cycle",{"type":45,"tag":94,"props":847,"children":848},{},[849,855],{"type":45,"tag":150,"props":850,"children":852},{"className":851},[],[853],{"type":51,"value":854},"actualclosedate",{"type":51,"value":856}," (DATE) - End of sales cycle (when closed)",{"type":45,"tag":94,"props":858,"children":859},{},[860,866],{"type":45,"tag":150,"props":861,"children":863},{"className":862},[],[864],{"type":51,"value":865},"estimatedvalue",{"type":51,"value":867}," (MONEY) - Expected deal size",{"type":45,"tag":94,"props":869,"children":870},{},[871,877],{"type":45,"tag":150,"props":872,"children":874},{"className":873},[],[875],{"type":51,"value":876},"actualvalue",{"type":51,"value":878}," (MONEY) - Actual won value",{"type":45,"tag":94,"props":880,"children":881},{},[882,888],{"type":45,"tag":150,"props":883,"children":885},{"className":884},[],[886],{"type":51,"value":887},"salesstage",{"type":51,"value":889}," (CHOICE) - Stage at close: Qualify(0), Develop(1), Propose(2), Close(3)",{"type":45,"tag":94,"props":891,"children":892},{},[893,899],{"type":45,"tag":150,"props":894,"children":896},{"className":895},[],[897],{"type":51,"value":898},"budgetstatus",{"type":51,"value":900}," (CHOICE) - No Budget(0), May Buy(1), Can Buy(2), Will Buy(3)",{"type":45,"tag":94,"props":902,"children":903},{},[904,910],{"type":45,"tag":150,"props":905,"children":907},{"className":906},[],[908],{"type":51,"value":909},"need",{"type":51,"value":911}," (CHOICE) - Must have(0), Should have(1), Good to have(2), No need(3)",{"type":45,"tag":94,"props":913,"children":914},{},[915,921],{"type":45,"tag":150,"props":916,"children":918},{"className":917},[],[919],{"type":51,"value":920},"purchasetimeframe",{"type":51,"value":922}," (CHOICE) - Immediate(0), This Quarter(1), Next Quarter(2), This Year(3), Unknown(4)",{"type":45,"tag":94,"props":924,"children":925},{},[926,932],{"type":45,"tag":150,"props":927,"children":929},{"className":928},[],[930],{"type":51,"value":931},"decisionmaker",{"type":51,"value":933}," (BIT) - Was decision maker engaged",{"type":45,"tag":94,"props":935,"children":936},{},[937,943],{"type":45,"tag":150,"props":938,"children":940},{"className":939},[],[941],{"type":51,"value":942},"closeprobability",{"type":51,"value":944}," (INT) - Final win probability (0-100)",{"type":45,"tag":94,"props":946,"children":947},{},[948,954],{"type":45,"tag":150,"props":949,"children":951},{"className":950},[],[952],{"type":51,"value":953},"msdyn_opportunityscore",{"type":51,"value":955}," (INT) - AI predictive score at close",{"type":45,"tag":94,"props":957,"children":958},{},[959,965],{"type":45,"tag":150,"props":960,"children":962},{"className":961},[],[963],{"type":51,"value":964},"msdyn_opportunitygrade",{"type":51,"value":966}," (CHOICE) - Grade A(0), B(1), C(2), D(3)",{"type":45,"tag":54,"props":968,"children":969},{},[970],{"type":45,"tag":82,"props":971,"children":972},{},[973],{"type":51,"value":974},"account:",{"type":45,"tag":90,"props":976,"children":977},{},[978,989,1000],{"type":45,"tag":94,"props":979,"children":980},{},[981,987],{"type":45,"tag":150,"props":982,"children":984},{"className":983},[],[985],{"type":51,"value":986},"industrycode",{"type":51,"value":988}," (CHOICE) - Industry classification (Accounting(1), Agriculture(2), etc.)",{"type":45,"tag":94,"props":990,"children":991},{},[992,998],{"type":45,"tag":150,"props":993,"children":995},{"className":994},[],[996],{"type":51,"value":997},"numberofemployees",{"type":51,"value":999}," (INT) - Company size",{"type":45,"tag":94,"props":1001,"children":1002},{},[1003,1009],{"type":45,"tag":150,"props":1004,"children":1006},{"className":1005},[],[1007],{"type":51,"value":1008},"revenue",{"type":51,"value":1010}," (MONEY) - Annual revenue",{"type":45,"tag":67,"props":1012,"children":1014},{"id":1013},"analysis-best-practices",[1015],{"type":51,"value":1016},"Analysis Best Practices",{"type":45,"tag":1018,"props":1019,"children":1020},"ol",{},[1021,1031,1041,1051,1061,1071],{"type":45,"tag":94,"props":1022,"children":1023},{},[1024,1029],{"type":45,"tag":82,"props":1025,"children":1026},{},[1027],{"type":51,"value":1028},"Sufficient sample size:",{"type":51,"value":1030}," Need minimum 20-30 deals for meaningful patterns",{"type":45,"tag":94,"props":1032,"children":1033},{},[1034,1039],{"type":45,"tag":82,"props":1035,"children":1036},{},[1037],{"type":51,"value":1038},"Control variables:",{"type":51,"value":1040}," Compare similar deal sizes and industries",{"type":45,"tag":94,"props":1042,"children":1043},{},[1044,1049],{"type":45,"tag":82,"props":1045,"children":1046},{},[1047],{"type":51,"value":1048},"Time relevance:",{"type":51,"value":1050}," Focus on recent data (last 12-18 months)",{"type":45,"tag":94,"props":1052,"children":1053},{},[1054,1059],{"type":45,"tag":82,"props":1055,"children":1056},{},[1057],{"type":51,"value":1058},"Qualitative context:",{"type":51,"value":1060}," Numbers show what, notes show why",{"type":45,"tag":94,"props":1062,"children":1063},{},[1064,1069],{"type":45,"tag":82,"props":1065,"children":1066},{},[1067],{"type":51,"value":1068},"Action-oriented:",{"type":51,"value":1070}," Every insight should drive specific behavior change",{"type":45,"tag":94,"props":1072,"children":1073},{},[1074,1079],{"type":45,"tag":82,"props":1075,"children":1076},{},[1077],{"type":51,"value":1078},"Regular refresh:",{"type":51,"value":1080}," Re-run analysis quarterly to update playbook",{"type":45,"tag":60,"props":1082,"children":1084},{"id":1083},"examples",[1085],{"type":51,"value":1086},"Examples",{"type":45,"tag":67,"props":1088,"children":1090},{"id":1089},"example-1-why-are-we-losing-enterprise-deals",[1091],{"type":51,"value":1092},"Example 1: Why Are We Losing Enterprise Deals?",{"type":45,"tag":54,"props":1094,"children":1095},{},[1096,1101],{"type":45,"tag":82,"props":1097,"children":1098},{},[1099],{"type":51,"value":1100},"User says:",{"type":51,"value":1102}," \"Why are we losing enterprise deals in manufacturing?\"",{"type":45,"tag":54,"props":1104,"children":1105},{},[1106],{"type":45,"tag":82,"props":1107,"children":1108},{},[1109],{"type":51,"value":1110},"Actions:",{"type":45,"tag":1018,"props":1112,"children":1113},{},[1114,1119,1124,1129],{"type":45,"tag":94,"props":1115,"children":1116},{},[1117],{"type":51,"value":1118},"Filter opportunities: estimatedvalue > $100K, industry = manufacturing",{"type":45,"tag":94,"props":1120,"children":1121},{},[1122],{"type":51,"value":1123},"Segment into won (statecode=1) vs lost (statecode=2)",{"type":45,"tag":94,"props":1125,"children":1126},{},[1127],{"type":51,"value":1128},"Compare sales cycles, activity patterns, stakeholder engagement",{"type":45,"tag":94,"props":1130,"children":1131},{},[1132],{"type":51,"value":1133},"Identify statistically significant differentiators",{"type":45,"tag":54,"props":1135,"children":1136},{},[1137],{"type":45,"tag":82,"props":1138,"children":1139},{},[1140],{"type":51,"value":1141},"Result:",{"type":45,"tag":143,"props":1143,"children":1146},{"className":1144,"code":1145,"language":51},[146],"WIN\u002FLOSS ANALYSIS: Enterprise Manufacturing\nPeriod: Last 12 months | Won: 12 | Lost: 18 | Win Rate: 40%\n\nKEY DIFFERENTIATORS:\n\n1. SALES CYCLE\n Won: 65 days avg | Lost: 98 days avg\n Insight: Deals dragging past 80 days are 3x more likely to lose\n\n2. STAKEHOLDER ENGAGEMENT\n Won: 3.2 contacts engaged avg | Lost: 1.4 contacts\n Insight: Multi-threading increases win rate by 45%\n\n3. ACTIVITY PATTERNS\n Won: 2.1 meetings per deal | Lost: 0.8 meetings\n Insight: Face-to-face engagement critical in manufacturing\n\nRECOMMENDATIONS:\n- Set 80-day checkpoint for deal health review\n- Require 3+ contacts engaged before Propose stage\n- Schedule on-site visits for deals > $100K\n",[1147],{"type":45,"tag":150,"props":1148,"children":1149},{"__ignoreMap":152},[1150],{"type":51,"value":1145},{"type":45,"tag":67,"props":1152,"children":1154},{"id":1153},"example-2-compare-top-rep-vs-team-average",[1155],{"type":51,"value":1156},"Example 2: Compare Top Rep vs Team Average",{"type":45,"tag":54,"props":1158,"children":1159},{},[1160,1164],{"type":45,"tag":82,"props":1161,"children":1162},{},[1163],{"type":51,"value":1100},{"type":51,"value":1165}," \"What does Sarah do differently to win more deals?\"",{"type":45,"tag":54,"props":1167,"children":1168},{},[1169],{"type":45,"tag":82,"props":1170,"children":1171},{},[1172],{"type":51,"value":1110},{"type":45,"tag":1018,"props":1174,"children":1175},{},[1176,1181,1186],{"type":45,"tag":94,"props":1177,"children":1178},{},[1179],{"type":51,"value":1180},"Filter Sarah's closed deals vs team average",{"type":45,"tag":94,"props":1182,"children":1183},{},[1184],{"type":51,"value":1185},"Compare activity types, timing, stakeholder engagement",{"type":45,"tag":94,"props":1187,"children":1188},{},[1189],{"type":51,"value":1190},"Identify behavioral differences",{"type":45,"tag":54,"props":1192,"children":1193},{},[1194],{"type":45,"tag":82,"props":1195,"children":1196},{},[1197],{"type":51,"value":1141},{"type":45,"tag":143,"props":1199,"children":1202},{"className":1200,"code":1201,"language":51},[146],"SARAH'S WINNING PATTERNS:\n\n1. SPEED TO FIRST MEETING\n Sarah: 2.1 days | Team avg: 5.3 days\n \n2. MULTI-THREADING\n Sarah: Always adds 2nd contact by day 7\n Team avg: Single contact for first 21 days\n \n3. ACTIVITY MIX\n Sarah: 60% calls, 30% meetings, 10% email\n Team: 20% calls, 10% meetings, 70% email\n\nPLAYBOOK RECOMMENDATION:\nAdopt Sarah's \"24-48-7\" rule: First call within 24 hours, \nfirst meeting within 48 hours, second contact by day 7.\n",[1203],{"type":45,"tag":150,"props":1204,"children":1205},{"__ignoreMap":152},[1206],{"type":51,"value":1201},{"type":45,"tag":67,"props":1208,"children":1210},{"id":1209},"example-3-competitive-loss-analysis",[1211],{"type":51,"value":1212},"Example 3: Competitive Loss Analysis",{"type":45,"tag":54,"props":1214,"children":1215},{},[1216,1220],{"type":45,"tag":82,"props":1217,"children":1218},{},[1219],{"type":51,"value":1100},{"type":51,"value":1221}," \"Why are we losing to Acme Corp?\"",{"type":45,"tag":54,"props":1223,"children":1224},{},[1225],{"type":45,"tag":82,"props":1226,"children":1227},{},[1228],{"type":51,"value":1110},{"type":45,"tag":1018,"props":1230,"children":1231},{},[1232,1237,1242],{"type":45,"tag":94,"props":1233,"children":1234},{},[1235],{"type":51,"value":1236},"Find lost deals with Acme mentioned (description, notes, opportunityclose)",{"type":45,"tag":94,"props":1238,"children":1239},{},[1240],{"type":51,"value":1241},"Analyze deal characteristics and loss patterns",{"type":45,"tag":94,"props":1243,"children":1244},{},[1245],{"type":51,"value":1246},"Generate competitive positioning recommendations",{"type":45,"tag":54,"props":1248,"children":1249},{},[1250],{"type":45,"tag":82,"props":1251,"children":1252},{},[1253],{"type":51,"value":1141},{"type":45,"tag":143,"props":1255,"children":1258},{"className":1256,"code":1257,"language":51},[146],"COMPETITIVE ANALYSIS: vs Acme Corp\nDeals Lost to Acme: 8 | Total Competitive: 15 | Loss Rate: 53%\n\nLOSS PATTERNS:\n- 75% lost on price (Acme undercuts by avg 20%)\n- 25% lost on feature (Acme's mobile app cited)\n\nWHERE WE WIN vs ACME:\n- Enterprise segment (62% win rate)\n- When economic buyer engaged early\n- When implementation timeline is priority\n\nBATTLECARD TALKING POINTS:\n1. Emphasize TCO, not initial price\n2. Lead with enterprise security\u002Fcompliance\n3. Engage economic buyer before Acme can anchor on price\n",[1259],{"type":45,"tag":150,"props":1260,"children":1261},{"__ignoreMap":152},[1262],{"type":51,"value":1257},{"type":45,"tag":60,"props":1264,"children":1266},{"id":1265},"troubleshooting",[1267],{"type":51,"value":1268},"Troubleshooting",{"type":45,"tag":67,"props":1270,"children":1272},{"id":1271},"error-insufficient-data-for-analysis",[1273],{"type":51,"value":1274},"Error: Insufficient data for analysis",{"type":45,"tag":54,"props":1276,"children":1277},{},[1278,1283,1285],{"type":45,"tag":82,"props":1279,"children":1280},{},[1281],{"type":51,"value":1282},"Cause:",{"type":51,"value":1284}," Too few closed deals matching criteria\n",{"type":45,"tag":82,"props":1286,"children":1287},{},[1288],{"type":51,"value":1289},"Solution:",{"type":45,"tag":90,"props":1291,"children":1292},{},[1293,1298,1303],{"type":45,"tag":94,"props":1294,"children":1295},{},[1296],{"type":51,"value":1297},"Expand date range",{"type":45,"tag":94,"props":1299,"children":1300},{},[1301],{"type":51,"value":1302},"Broaden filters (combine industries, expand size range)",{"type":45,"tag":94,"props":1304,"children":1305},{},[1306],{"type":51,"value":1307},"Note limited sample size in results",{"type":45,"tag":67,"props":1309,"children":1311},{"id":1310},"error-no-clear-patterns-found",[1312],{"type":51,"value":1313},"Error: No clear patterns found",{"type":45,"tag":54,"props":1315,"children":1316},{},[1317,1321,1323],{"type":45,"tag":82,"props":1318,"children":1319},{},[1320],{"type":51,"value":1282},{"type":51,"value":1322}," High variance in data or too many confounding variables\n",{"type":45,"tag":82,"props":1324,"children":1325},{},[1326],{"type":51,"value":1289},{"type":45,"tag":90,"props":1328,"children":1329},{},[1330,1335,1340],{"type":45,"tag":94,"props":1331,"children":1332},{},[1333],{"type":51,"value":1334},"Narrow analysis to more homogeneous segment",{"type":45,"tag":94,"props":1336,"children":1337},{},[1338],{"type":51,"value":1339},"Focus on extreme cases (fastest wins, longest losses)",{"type":45,"tag":94,"props":1341,"children":1342},{},[1343],{"type":51,"value":1344},"Supplement with qualitative analysis of notes",{"type":45,"tag":67,"props":1346,"children":1348},{"id":1347},"error-activity-data-incomplete",[1349],{"type":51,"value":1350},"Error: Activity data incomplete",{"type":45,"tag":54,"props":1352,"children":1353},{},[1354,1358,1360],{"type":45,"tag":82,"props":1355,"children":1356},{},[1357],{"type":51,"value":1282},{"type":51,"value":1359}," Activities not consistently linked to opportunities\n",{"type":45,"tag":82,"props":1361,"children":1362},{},[1363],{"type":51,"value":1289},{"type":45,"tag":90,"props":1365,"children":1366},{},[1367,1372,1377],{"type":45,"tag":94,"props":1368,"children":1369},{},[1370],{"type":51,"value":1371},"Query activities for related accounts as backup",{"type":45,"tag":94,"props":1373,"children":1374},{},[1375],{"type":51,"value":1376},"Use date overlap method (activities during deal lifecycle)",{"type":45,"tag":94,"props":1378,"children":1379},{},[1380],{"type":51,"value":1381},"Advise on data hygiene improvements",{"items":1383,"total":1484},[1384,1401,1415,1428,1444,1456,1468],{"slug":1385,"name":1385,"fn":1386,"description":1387,"org":1388,"tags":1389,"stars":26,"repoUrl":27,"updatedAt":1400},"account-briefing-generator","generate account briefings for sales meetings","Generates meeting briefings by aggregating account info, contacts, opportunities, cases, and activity history into structured prep documents with talking points and discovery questions. Use when user says \"prep me for my call\", \"brief me on this account\", \"meeting prep\", \"I have a meeting with [company]\", \"account briefing\", \"customer briefing\", or \"prepare for customer meeting\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1390,1391,1392,1395,1396,1397],{"name":15,"slug":16,"type":13},{"name":24,"slug":25,"type":13},{"name":1393,"slug":1394,"type":13},"Meetings","meetings",{"name":9,"slug":8,"type":13},{"name":18,"slug":19,"type":13},{"name":1398,"slug":1399,"type":13},"Summarization","summarization","2026-04-06T18:36:32.277939",{"slug":1402,"name":1402,"fn":1403,"description":1404,"org":1405,"tags":1406,"stars":26,"repoUrl":27,"updatedAt":1414},"account-risk-early-warning","identify account churn risks from engagement signals","Identifies accounts showing warning signs of churn by analyzing activity trends, support cases, and engagement signals. Scores risk and prioritizes intervention targets. Use when user asks \"which accounts are at risk\", \"churn risk analysis\", \"find accounts that might leave\", \"customer health check\", \"at-risk customers\", \"retention warning signs\", or \"account health score\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1407,1408,1409,1410,1413],{"name":15,"slug":16,"type":13},{"name":24,"slug":25,"type":13},{"name":9,"slug":8,"type":13},{"name":1411,"slug":1412,"type":13},"Risk Assessment","risk-assessment",{"name":18,"slug":19,"type":13},"2026-04-06T18:36:28.462732",{"slug":1416,"name":1416,"fn":1417,"description":1418,"org":1419,"tags":1420,"stars":26,"repoUrl":27,"updatedAt":1427},"competitive-intelligence","generate competitive intelligence from sales data","Analyzes opportunity data and activity notes to generate competitive intelligence including win\u002Floss rates by competitor, patterns, and rep-ready battlecard talking points. Use when user asks \"how are we doing against [competitor]\", \"competitive analysis\", \"competitor win rate\", \"battlecard for [competitor]\", \"competitive landscape\", \"why are we losing to [competitor]\", or \"competitor intelligence\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1421,1423,1424,1425,1426],{"name":1422,"slug":1416,"type":13},"Competitive Intelligence",{"name":15,"slug":16,"type":13},{"name":24,"slug":25,"type":13},{"name":9,"slug":8,"type":13},{"name":18,"slug":19,"type":13},"2026-04-06T18:36:23.280253",{"slug":1429,"name":1429,"fn":1430,"description":1431,"org":1432,"tags":1433,"stars":26,"repoUrl":27,"updatedAt":1443},"create-an-asset","generate customized sales assets from Dataverse","Generates customized sales assets including one-pagers, proposals, executive summaries, ROI summaries, and mutual action plans from Dataverse context. Use when user says \"create a one-pager\", \"draft a proposal\", \"generate executive summary\", \"build ROI summary\", \"create mutual action plan\", \"sales asset for [account]\", \"proposal outline\", or \"customer-facing document\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1434,1437,1438,1441,1442],{"name":1435,"slug":1436,"type":13},"Content Creation","content-creation",{"name":24,"slug":25,"type":13},{"name":1439,"slug":1440,"type":13},"Marketing","marketing",{"name":9,"slug":8,"type":13},{"name":18,"slug":19,"type":13},"2026-04-06T18:36:24.562421",{"slug":1445,"name":1445,"fn":1446,"description":1447,"org":1448,"tags":1449,"stars":26,"repoUrl":27,"updatedAt":1455},"cross-sell-target-identifier","identify cross-sell targets from customer patterns","Analyzes successful product customers to identify patterns, then finds similar accounts that are good cross-sell candidates with fit scores and reasoning. Use when user asks \"who should I pitch this product to\", \"find cross-sell opportunities\", \"which customers should buy Product X\", \"identify upsell targets\", \"product expansion candidates\", or \"who else would buy this\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1450,1451,1452,1453,1454],{"name":21,"slug":22,"type":13},{"name":15,"slug":16,"type":13},{"name":24,"slug":25,"type":13},{"name":9,"slug":8,"type":13},{"name":18,"slug":19,"type":13},"2026-04-06T18:36:37.380929",{"slug":1457,"name":1457,"fn":1458,"description":1459,"org":1460,"tags":1461,"stars":26,"repoUrl":27,"updatedAt":1467},"daily-briefing","prepare daily business briefings from Dataverse","Delivers a prioritized morning summary covering today's meetings, overdue tasks, pipeline alerts, and recommended actions from Dataverse. Use when user says \"what's on my plate today\", \"daily briefing\", \"morning summary\", \"what do I need to focus on today\", \"start my day\", \"daily digest\", \"today's priorities\", or \"what's happening today\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1462,1463,1464,1465,1466],{"name":15,"slug":16,"type":13},{"name":24,"slug":25,"type":13},{"name":9,"slug":8,"type":13},{"name":18,"slug":19,"type":13},{"name":1398,"slug":1399,"type":13},"2026-04-06T18:36:31.028078",{"slug":1469,"name":1469,"fn":1470,"description":1471,"org":1472,"tags":1473,"stars":26,"repoUrl":27,"updatedAt":1483},"draft-outreach","draft personalized sales outreach from Dataverse","Generates personalized outreach messages by pulling context from Dataverse records. Creates tailored emails for new prospects, re-engagement, follow-ups, or cross-sell. Use when user says \"draft an email to [contact]\", \"write outreach for\", \"help me reach out to\", \"compose email\", \"re-engage this contact\", \"follow-up email\", \"prospecting email\", or \"outreach message for\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1474,1475,1476,1478,1479,1482],{"name":15,"slug":16,"type":13},{"name":24,"slug":25,"type":13},{"name":1477,"slug":753,"type":13},"Email",{"name":9,"slug":8,"type":13},{"name":1480,"slug":1481,"type":13},"Outreach","outreach",{"name":18,"slug":19,"type":13},"2026-04-06T18:36:36.103544",16,{"items":1486,"total":1679},[1487,1509,1530,1549,1564,1581,1592,1605,1620,1635,1654,1667],{"slug":1488,"name":1488,"fn":1489,"description":1490,"org":1491,"tags":1492,"stars":1506,"repoUrl":1507,"updatedAt":1508},"rushstack-best-practices","manage Rush monorepos with best practices","Provides best practices and guidance for working with Rush monorepos. Use when the user is working in a Rush-based repository, asks about Rush commands (install, update, build, rebuild), needs help with project selection, dependency management, build caching, subspace configuration, or troubleshooting Rush-specific issues.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1493,1496,1499,1500,1503],{"name":1494,"slug":1495,"type":13},"Engineering","engineering",{"name":1497,"slug":1498,"type":13},"Local Development","local-development",{"name":9,"slug":8,"type":13},{"name":1501,"slug":1502,"type":13},"Project Management","project-management",{"name":1504,"slug":1505,"type":13},"Rush","rush",6484,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Frushstack","2026-04-06T18:34:44.965032",{"slug":1510,"name":1510,"fn":1511,"description":1512,"org":1513,"tags":1514,"stars":1527,"repoUrl":1528,"updatedAt":1529},"azure-ai-agents-persistent-dotnet","build AI agents with Azure .NET SDK","Azure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools. Use for agent CRUD, conversation threads, streaming responses, function calling, file search, and code interpreter. Triggers: \"PersistentAgentsClient\", \"persistent agents\", \"agent threads\", \"agent runs\", \"streaming agents\", \"function calling agents .NET\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1515,1518,1521,1524],{"name":1516,"slug":1517,"type":13},".NET","net",{"name":1519,"slug":1520,"type":13},"Agents","agents",{"name":1522,"slug":1523,"type":13},"Azure","azure",{"name":1525,"slug":1526,"type":13},"LLM","llm",2804,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills","2026-07-03T16:32:10.297433",{"slug":1531,"name":1531,"fn":1532,"description":1533,"org":1534,"tags":1535,"stars":1527,"repoUrl":1528,"updatedAt":1548},"azure-ai-anomalydetector-java","build anomaly detection applications with Java","Build anomaly detection applications with Azure AI Anomaly Detector SDK for Java. Use when implementing univariate\u002Fmultivariate anomaly detection, time-series analysis, or AI-powered monitoring.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1536,1537,1538,1541,1544,1545],{"name":21,"slug":22,"type":13},{"name":1522,"slug":1523,"type":13},{"name":1539,"slug":1540,"type":13},"Data Analysis","data-analysis",{"name":1542,"slug":1543,"type":13},"Java","java",{"name":9,"slug":8,"type":13},{"name":1546,"slug":1547,"type":13},"Monitoring","monitoring","2026-05-13T06:14:16.261754",{"slug":1550,"name":1550,"fn":1551,"description":1552,"org":1553,"tags":1554,"stars":1527,"repoUrl":1528,"updatedAt":1563},"azure-ai-contentsafety-java","build content moderation applications with Azure AI","Build content moderation applications with Azure AI Content Safety SDK for Java. Use when implementing text\u002Fimage analysis, blocklist management, or harm detection for hate, violence, sexual content, and self-harm.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1555,1558,1559,1560],{"name":1556,"slug":1557,"type":13},"AI Infrastructure","ai-infrastructure",{"name":1522,"slug":1523,"type":13},{"name":1542,"slug":1543,"type":13},{"name":1561,"slug":1562,"type":13},"Security","security","2026-07-07T06:53:31.293235",{"slug":1565,"name":1565,"fn":1566,"description":1567,"org":1568,"tags":1569,"stars":1527,"repoUrl":1528,"updatedAt":1580},"azure-ai-contentsafety-py","detect harmful content with Azure AI Content Safety","Azure AI Content Safety SDK for Python. Use for detecting harmful content in text and images with multi-severity classification.\nTriggers: \"azure-ai-contentsafety\", \"ContentSafetyClient\", \"content moderation\", \"harmful content\", \"text analysis\", \"image analysis\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1570,1571,1574,1575,1576,1579],{"name":1522,"slug":1523,"type":13},{"name":1572,"slug":1573,"type":13},"Compliance","compliance",{"name":1525,"slug":1526,"type":13},{"name":9,"slug":8,"type":13},{"name":1577,"slug":1578,"type":13},"Python","python",{"name":1561,"slug":1562,"type":13},"2026-07-18T05:14:23.017504",{"slug":1582,"name":1582,"fn":1583,"description":1584,"org":1585,"tags":1586,"stars":1527,"repoUrl":1528,"updatedAt":1591},"azure-ai-language-conversations-py","implement conversational language understanding with Python","Implement Conversational Language Understanding (CLU) using the azure-ai-language-conversations Python SDK. Use when working with ConversationAnalysisClient to analyze conversation intent and entities, building NLP features, or integrating language understanding into applications.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1587,1588,1589,1590],{"name":21,"slug":22,"type":13},{"name":1522,"slug":1523,"type":13},{"name":1525,"slug":1526,"type":13},{"name":1577,"slug":1578,"type":13},"2026-07-31T05:54:29.068751",{"slug":1593,"name":1593,"fn":1594,"description":1595,"org":1596,"tags":1597,"stars":1527,"repoUrl":1528,"updatedAt":1604},"azure-ai-translation-text-py","translate text using Azure AI services","Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications.\nTriggers: \"text translation\", \"translator\", \"translate text\", \"transliterate\", \"TextTranslationClient\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1598,1601,1602,1603],{"name":1599,"slug":1600,"type":13},"API Development","api-development",{"name":1522,"slug":1523,"type":13},{"name":9,"slug":8,"type":13},{"name":1577,"slug":1578,"type":13},"2026-07-18T05:14:16.988376",{"slug":1606,"name":1606,"fn":1607,"description":1608,"org":1609,"tags":1610,"stars":1527,"repoUrl":1528,"updatedAt":1619},"azure-ai-vision-imageanalysis-py","analyze images with Azure AI Vision","Azure AI Vision Image Analysis SDK for captions, tags, objects, OCR, people detection, and smart cropping. Use for computer vision and image understanding tasks.\nTriggers: \"image analysis\", \"computer vision\", \"OCR\", \"object detection\", \"ImageAnalysisClient\", \"image caption\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1611,1612,1615,1618],{"name":1522,"slug":1523,"type":13},{"name":1613,"slug":1614,"type":13},"Computer Vision","computer-vision",{"name":1616,"slug":1617,"type":13},"Images","images",{"name":1577,"slug":1578,"type":13},"2026-07-18T05:14:18.007737",{"slug":1621,"name":1621,"fn":1622,"description":1623,"org":1624,"tags":1625,"stars":1527,"repoUrl":1528,"updatedAt":1634},"azure-appconfiguration-java","manage configuration with Azure App Configuration","Azure App Configuration SDK for Java. Centralized application configuration management with key-value settings, feature flags, and snapshots.\nTriggers: \"ConfigurationClient java\", \"app configuration java\", \"feature flag java\", \"configuration setting java\", \"azure config java\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1626,1627,1630,1633],{"name":1522,"slug":1523,"type":13},{"name":1628,"slug":1629,"type":13},"Configuration","configuration",{"name":1631,"slug":1632,"type":13},"Feature Flags","feature-flags",{"name":1542,"slug":1543,"type":13},"2026-07-03T16:32:01.278468",{"slug":1636,"name":1636,"fn":1637,"description":1638,"org":1639,"tags":1640,"stars":1527,"repoUrl":1528,"updatedAt":1653},"azure-cosmos-rust","build applications with Azure Cosmos DB","Azure Cosmos DB library for Rust (NoSQL API). Document CRUD, containers, and globally distributed data.\nTriggers: \"cosmos db rust\", \"CosmosClient rust\", \"document crud rust\", \"NoSQL rust\", \"partition key rust\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1641,1644,1647,1650],{"name":1642,"slug":1643,"type":13},"Cosmos DB","cosmos-db",{"name":1645,"slug":1646,"type":13},"Database","database",{"name":1648,"slug":1649,"type":13},"NoSQL","nosql",{"name":1651,"slug":1652,"type":13},"Rust","rust","2026-07-31T05:54:27.021432",{"slug":1655,"name":1655,"fn":1637,"description":1656,"org":1657,"tags":1658,"stars":1527,"repoUrl":1528,"updatedAt":1666},"azure-cosmos-ts","Azure Cosmos DB JavaScript\u002FTypeScript SDK (@azure\u002Fcosmos) for data plane operations. Use for CRUD operations on documents, queries, bulk operations, and container management. Triggers: \"Cosmos DB\", \"@azure\u002Fcosmos\", \"CosmosClient\", \"document CRUD\", \"NoSQL queries\", \"bulk operations\", \"partition key\", \"container.items\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1659,1660,1661,1662,1663],{"name":1642,"slug":1643,"type":13},{"name":1645,"slug":1646,"type":13},{"name":9,"slug":8,"type":13},{"name":1648,"slug":1649,"type":13},{"name":1664,"slug":1665,"type":13},"TypeScript","typescript","2026-07-03T16:31:19.368382",{"slug":1668,"name":1668,"fn":1669,"description":1670,"org":1671,"tags":1672,"stars":1527,"repoUrl":1528,"updatedAt":1678},"azure-data-tables-java","build table storage applications with Java","Build table storage applications with Azure Tables SDK for Java. Use when working with Azure Table Storage or Cosmos DB Table API for NoSQL key-value data, schemaless storage, or structured data at scale.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1673,1674,1675,1676,1677],{"name":1522,"slug":1523,"type":13},{"name":1642,"slug":1643,"type":13},{"name":1645,"slug":1646,"type":13},{"name":1542,"slug":1543,"type":13},{"name":1648,"slug":1649,"type":13},"2026-05-13T06:14:17.582229",267]