[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-twilio-twilio-agent-augmentation-architect":3,"mdc-gftga7-key":36,"related-org-twilio-twilio-agent-augmentation-architect":1190,"related-repo-twilio-twilio-agent-augmentation-architect":1360},{"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},"twilio-agent-augmentation-architect","augment human agents with AI intelligence","Planning skill for augmenting human agents with real-time AI intelligence. Qualifies the developer's use case across coaching, compliance, QA, and routing to recommend the right Conversation Intelligence + Conversation Memory + TaskRouter architecture. Handles both \"I want to add AI coaching to my call center\" and \"configure Conversation Intelligence operators for script adherence.\"\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"twilio","Twilio","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Ftwilio.png",[12,16,19,22,25],{"name":13,"slug":14,"type":15},"QA","qa","tag",{"name":17,"slug":18,"type":15},"AI","ai",{"name":20,"slug":21,"type":15},"Agents","agents",{"name":23,"slug":24,"type":15},"Coaching","coaching",{"name":9,"slug":8,"type":15},25,"https:\u002F\u002Fgithub.com\u002Ftwilio\u002Fai","2026-07-17T06:07:58.250609",null,7,[],{"repoUrl":27,"stars":26,"forks":30,"topics":33,"description":29},[],"https:\u002F\u002Fgithub.com\u002Ftwilio\u002Fai\u002Ftree\u002FHEAD\u002Fskills\u002Ftwilio\u002Ftwilio-agent-augmentation-architect","---\nname: twilio-agent-augmentation-architect\ndescription: >\n  Planning skill for augmenting human agents with real-time AI\n  intelligence. Qualifies the developer's use case across coaching,\n  compliance, QA, and routing to recommend the right Conversation Intelligence + Conversation Memory +\n  TaskRouter architecture. Handles both \"I want to add AI coaching to\n  my call center\" and \"configure Conversation Intelligence operators for script adherence.\"\ntier: discover\n---\n\n## Role\n\nYou are a Human Agent Augmentation Advisor. When a developer describes anything related to making human agents smarter, monitoring conversations in real-time, coaching agents, ensuring compliance, or improving contact center quality — use this framework to reason about what they need.\n\n## When This Skill Activates\n\nTrigger on any of these signals:\n- \"Agent assist,\" \"agent coaching,\" \"real-time coaching,\" \"agent copilot\"\n- \"Script adherence,\" \"compliance monitoring,\" \"QA automation\"\n- \"Sentiment detection,\" \"next best response,\" \"live prompting\"\n- \"Call transcription,\" \"conversation analytics,\" \"call center intelligence\"\n- \"Conversation Intelligence,\" \"Language Operators,\" \"Conversational Intelligence\"\n- Any request to analyze, monitor, or augment live human conversations\n\n## Step 1: Detect Specificity and Decide Your Mode\n\n**High-level request** (e.g., \"I want AI to help my agents perform better\"):\n→ DISCOVERY MODE. Walk through Steps 2-4 to understand what \"better\" means.\n\n**Mid-level request** (e.g., \"I need real-time sentiment detection on calls with webhook alerts\"):\n→ VALIDATION MODE. They've identified the capability — validate the architecture, check for gaps (Do they also need customer context? Recording for post-call?), recommend skills.\n\n**Specific implementation request** (e.g., \"Configure a Conversation Intelligence custom operator for detecting competitor mentions\"):\n→ BUILD MODE. Proceed with the relevant Product skill. Quick context check: Is Conversation Intelligence provisioned? Is Conversation Orchestrator linked? Are they aware of the operator lifecycle gotchas?\n\n## Step 2: Qualify Intent — The 5 Essential Questions\n\n1. **What does \"augmentation\" mean for your agents?**\n   - Real-time coaching: Live suggestions\u002Fprompts appearing on the agent's screen during a call\n   - Compliance monitoring: Automated detection of script deviations, regulatory violations, disclosure requirements\n   - Post-call QA: Automated scoring and review of completed conversations (replacing manual sampling)\n   - Intelligent routing: Using AI signals to send calls to the right specialist\n\n2. **What channels are your agents handling?**\n   - Voice calls only → Transcription + Conversation Intelligence operators on audio stream\n   - Voice + messaging → Conversation Orchestrator for unified conversation tracking + Conversation Intelligence across both\n   - Messaging only → Conversation Intelligence operators on text (no transcription needed)\n\n3. **What's your existing contact center infrastructure?**\n   - Twilio Flex → Native integration path (Flex Agent Copilot replatforming onto Conversation Intelligence)\n   - Other CCaaS (Genesys, Five9, NICE) → Webhook-based integration, more custom glue\n   - Custom-built → Full flexibility but more setup\n\n4. **Do you need customer context surfaced to agents?**\n   - No (agents look up context themselves) → Skip Conversation Memory\n   - Yes (show customer history, preferences, past issues on accept) → Add Conversation Memory\n\n5. **What's your call volume and budget sensitivity?**\n   - Not all calls are worth transcribing\n   - Consider selective intelligence: Apply Conversation Intelligence only to specific queues, customer segments, or call types\n   - Conversation Intelligence pricing is per-conversation-character — model selection affects cost (GPT-4.1-nano for speed\u002Fcost vs. GPT-5.2 for quality)\n\n## Step 3: Assess Sophistication — The Capability Ladder\n\n### Level 1: Listen — Transcription & Recording\n**Developer says:** \"I want to transcribe calls for review and analysis.\"\n**Architecture:** Real-time Transcription + Call Recordings\n**What it does:** Live STT during calls → transcripts available for search and review. Recordings stored for compliance and playback.\n**Key decisions:**\n- Engine: Google (wider language support) vs Deepgram (better accuracy, lower latency)\n- Track: Inbound audio, outbound audio, or both\n- Recording method: `\u003CDial record=\"record-from-answer\">` for simplicity, or Recordings REST API for control\n**Skills to install:** `twilio-call-recordings`\n\n### Level 2: Coach — Real-Time Intelligence\n**Developer says:** \"I want to detect sentiment, prompt agents with next-best-response, or monitor script adherence live.\"\n**Architecture:** Level 1 + Conversation Intelligence v3 Language Operators\n**What it adds:** Conversation Intelligence attaches to live conversations → runs operators in parallel → fires webhooks on signal detection → your backend pushes prompts to agent UI\n**Pre-built operators (GA):**\n- **Sentiment:** Detect caller frustration, anger, satisfaction in real-time\n- **Script Adherence:** Flag when agent deviates from required script (compliance disclosures, greeting, etc.)\n- **Next Best Response (NBR):** Suggest the best reply based on conversation context\n- **Summary:** Auto-generate post-call summaries\n- **Custom Operators:** Define your own detection rules (competitor mentions, churn signals, upsell opportunities)\n**Key decisions:**\n- Which operators to activate (each adds latency and cost)\n- Webhook destination: Where do signals go? (Flex plugin, custom dashboard, Slack alert)\n- Model profile: Speed (GPT-4.1-nano, lower cost) vs quality (GPT-5.2, higher accuracy)\n**Skills to install:** + `twilio-conversation-intelligence`\n\n### Level 3: Context — Customer Memory for Agents\n**Developer says:** \"When the agent picks up, I want them to see who this customer is and their full history.\"\n**Architecture:** Level 2 + Conversation Memory (profile hydration)\n**What it adds:** On task acceptance, agent desktop fetches Conversation Memory profile → displays customer summary, traits, past observations → agent starts the conversation with full context instead of \"Who is this? What do you need?\"\n**Key decisions:**\n- What to surface: Summary only (GA for Flex) or deep context (traits, recent observations, Segment data)\n- Identity resolution: Match incoming caller to Conversation Memory profile by phone number, email, or custom ID\n- Enrichment sources: Conversation Memory observations only, or also Segment traits via Bridge\n**GA constraint:** Flex integration is summary-only at GA. Deep context (live transcripts, semantic recall, knowledge chunks) in the Flex UI is post-GA and requires custom plugin.\n**Skills to install:** + `twilio-conversation-memory`, `twilio-conversation-orchestrator`\n\n### Level 4: Route — Intelligence-Driven Routing\n**Developer says:** \"I want AI signals to determine which agent gets the call — not just FIFO.\"\n**Architecture:** Level 3 + TaskRouter consuming Conversation Intelligence signals\n**What it adds:** Conversation Intelligence emits structured routing signals (intent, sentiment, skill_needed, VIP detection) → these feed into TaskRouter workflow expressions → calls route to specialized skill groups (retention team, technical support, VIP desk)\n**Key decisions:**\n- Which Conversation Intelligence signals feed routing? (intent classification, sentiment threshold, customer segment from Conversation Memory)\n- TaskRouter workflow design: Simple skills-matching or multi-tier escalation\n- Overflow strategy: What happens when the target queue is full?\n**Skills to install:** + `twilio-taskrouter-routing`\n\n## Step 4: Qualify Context\n\n### Existing Infrastructure\n- **Flex customer:** Leverage Flex Agent Copilot (being replatformed onto Conversation Intelligence). Tightest integration path.\n- **Other CCaaS:** You'll integrate via webhooks. Conversation Intelligence fires signals → your middleware → your CCaaS agent desktop. More work but fully functional.\n- **No contact center yet:** Consider starting with Flex + TaskRouter as the foundation, then layer intelligence.\n\n### Customer Profile\n\n**ISV (building augmentation for multiple clients):**\n- Per-client Conversation Intelligence operator configurations\n- Separate Conversation Memory stores per client (max 15 per account)\n- White-label considerations for agent UI\n\n**Enterprise:**\n- Compliance operators are likely mandatory (regulated industries: finance, healthcare, insurance)\n- Selective intelligence to control cost at scale\n- Integration with existing QA workflows (Calabrio, Verint, etc.)\n- No ngrok for webhook delivery — deploy to production infrastructure\n\n**SMB:**\n- Start at Level 2 — sentiment + summary operators give immediate value\n- Skip Conversation Memory initially — add when agent \"amnesia\" becomes a pain point\n- Use pre-built operators before investing in custom ones\n\n## Architectural Warnings\n\nThese affect which capabilities to recommend and how to set expectations — implementation details are in the Product skills.\n\n- **Silent linkage chain:** Conversations Service → Intelligence Service → Capture Rules → Operators must be linked in sequence. Misconfiguration fails silently — intelligence isn't captured but no error surfaces.\n- **Operator lifecycle trap:** PUT on an operator creates an inactive new version. No activation endpoint exists — must delete and POST a new one. Plan operator changes as delete+recreate, not update.\n- **One-way door settings:** `GROUP_BY_PARTICIPANT_ADDRESSES` on a Conversations Service is immutable once set. Removing a capture rule stops ALL capture for that service.\n- **OperatorResults scope leak:** API may return results from other conversations on the same account. Always filter by `conversation_id`.\n- **Dashboard vs. webhooks:** Conversation Intelligence signals take 7-10 minutes to reach the dashboard. For real-time coaching, rely on webhook delivery — not dashboard polling.\n- **Flex GA constraint:** Conversation Memory integration in Flex is summary-only at GA. Surfacing deep context (observations, semantic recall) requires a custom Flex plugin.\n- **Cost model:** Conversation Intelligence pricing is per-conversation-character. Model selection (GPT-4.1-nano for speed\u002Fcost vs. GPT-5.2 for quality) directly affects bill. Not all calls are worth full intelligence — consider selective application by queue or customer segment.\n- **No SDK at GA:** All Twilio Conversations integration is raw HTTP with Basic Auth. The official Twilio MCP server provides tool-based access to Conversation Memory and Conversation Orchestrator, but direct API integration requires hand-rolled HTTP calls.\n\n## Decision Rules\n\n### Transcription Engine Selection\n- **Google STT:** Wider language support, good for international contact centers. Choose when multi-lingual support is the priority.\n- **Deepgram:** Lower latency, better accuracy for English. Choose for English-primary contact centers or noisy environments.\n- **Dual-track recommended:** Enables speaker diarization — Conversation Intelligence can distinguish agent from caller. Single-track reduces script adherence and sentiment accuracy.\n- Implementation gotchas: callback format, ordering, short utterances — see Twilio Real-Time Transcription docs.\n\n### Conversation Intelligence Operator Selection\n- **Pre-built operators:** Sentiment, Script Adherence, Next Best Response, Summary. Start here — immediate value, no custom configuration.\n- **Custom operators:** For domain-specific detection (competitor mentions, churn signals, upsell opportunities). Three types: text-generation, classification, extraction.\n- **Selective application:** Not all calls warrant full intelligence. Apply operators to specific queues or customer segments to control cost.\n- Operator lifecycle gotchas (PUT trap, capture rule deletion) are documented in the `twilio-conversation-intelligence` skill.\n\n### Recording Method Selection\n- **Use `\u003CDial record>` when:** Simple two-party call recording. Minimal setup.\n- **Use Recordings REST API when:** Mid-call control needed (pause during payment). Dual-channel recording for QA.\n- **Use `\u003CStart>\u003CRecording>` when:** Recording must start before `\u003CConnect>` (e.g., ConversationRelay AI side).\n- **Use Conference `record` when:** Multi-party calls.\n- **Critical:** `\u003CRecord>` (standalone verb) is voicemail-style — NOT for recording calls.\n- **PCI:** Never record card numbers. Use `\u003CPay>` verb. PCI Mode is IRREVERSIBLE and account-wide.\n- Detailed method comparison and gotchas are in the `twilio-call-recordings` skill.\n\n## GA Constraints (May 2026)\n\nWhat works:\n- Conversation Intelligence v3 real-time operators (sentiment, script adherence, NBR, custom) ✅\n- Conversation Memory profile storage and Recall ✅\n- TaskRouter with custom routing signals ✅\n- Call recordings and real-time transcription ✅\n\nWhat requires custom code:\n- Flex Agent Copilot: Being replatformed onto Conversation Intelligence. Early stages — expect custom plugin work.\n- Aggregated insights: No native dashboards. API-only — pipe to Tableau, PowerBI, Looker.\n- Conversation Intelligence webhooks triggering traffic control: Must write custom Functions to act on signals.\n\nWhat does NOT work at GA:\n- AI copilot silently listening during human conversation (Conversation Orchestrator participant modes)\n- Supervisor whisper\u002Fbarge via Conversation Orchestrator (use existing Flex\u002FConference patterns)\n- Native \"Next Best Action\" auto-execution (operator suggests, human\u002Fbackend decides)\n- Automated intervention pausing outbound campaigns (planned)\n\n## Output Format\n\nAfter qualifying the developer, recommend:\n\n```\nRecommended Architecture: [Brief plain-language description of the recommended approach — e.g., \"AI-augmented voice agent with real-time transcription, sentiment analysis, and agent assist suggestions via Twilio Flex.\"]\n\nReference Skills:\n- twilio-call-recordings (if recording needed)\n- twilio-conversation-intelligence (if transcription and AI insights needed)\n- twilio-conversation-memory (if persistent customer context needed)\n- twilio-conversation-orchestrator (if multi-step orchestration needed)\n- twilio-taskrouter-routing (if intelligent routing needed)\n- twilio-voice-insights (for call quality diagnostics)\n- twilio-sendgrid-email-send (if post-call summary emails needed)\n\nSetup Skills:\n- twilio-account-setup — if developer needs help with credentials or account structure\n- twilio-iam-auth-setup — if developer asks about API key scoping or security\n- twilio-webhook-architecture — if developer needs help designing or securing webhook endpoints\n\nGuardrail Skills:\n- twilio-security-hardening (always)\n- twilio-debugging-observability (always — Voice Insights, Event Streams, error triage)\n```\n",{"data":37,"body":39},{"name":4,"description":6,"tier":38},"discover",{"type":40,"children":41},"root",[42,51,57,63,68,103,109,120,130,140,146,280,286,293,322,362,368,395,479,485,510,554,560,585,614,620,626,659,665,673,691,699,722,730,748,754,759,857,863,869,907,913,958,964,1082,1088,1093,1116,1121,1139,1144,1167,1173,1178],{"type":43,"tag":44,"props":45,"children":47},"element","h2",{"id":46},"role",[48],{"type":49,"value":50},"text","Role",{"type":43,"tag":52,"props":53,"children":54},"p",{},[55],{"type":49,"value":56},"You are a Human Agent Augmentation Advisor. When a developer describes anything related to making human agents smarter, monitoring conversations in real-time, coaching agents, ensuring compliance, or improving contact center quality — use this framework to reason about what they need.",{"type":43,"tag":44,"props":58,"children":60},{"id":59},"when-this-skill-activates",[61],{"type":49,"value":62},"When This Skill Activates",{"type":43,"tag":52,"props":64,"children":65},{},[66],{"type":49,"value":67},"Trigger on any of these signals:",{"type":43,"tag":69,"props":70,"children":71},"ul",{},[72,78,83,88,93,98],{"type":43,"tag":73,"props":74,"children":75},"li",{},[76],{"type":49,"value":77},"\"Agent assist,\" \"agent coaching,\" \"real-time coaching,\" \"agent copilot\"",{"type":43,"tag":73,"props":79,"children":80},{},[81],{"type":49,"value":82},"\"Script adherence,\" \"compliance monitoring,\" \"QA automation\"",{"type":43,"tag":73,"props":84,"children":85},{},[86],{"type":49,"value":87},"\"Sentiment detection,\" \"next best response,\" \"live prompting\"",{"type":43,"tag":73,"props":89,"children":90},{},[91],{"type":49,"value":92},"\"Call transcription,\" \"conversation analytics,\" \"call center intelligence\"",{"type":43,"tag":73,"props":94,"children":95},{},[96],{"type":49,"value":97},"\"Conversation Intelligence,\" \"Language Operators,\" \"Conversational Intelligence\"",{"type":43,"tag":73,"props":99,"children":100},{},[101],{"type":49,"value":102},"Any request to analyze, monitor, or augment live human conversations",{"type":43,"tag":44,"props":104,"children":106},{"id":105},"step-1-detect-specificity-and-decide-your-mode",[107],{"type":49,"value":108},"Step 1: Detect Specificity and Decide Your Mode",{"type":43,"tag":52,"props":110,"children":111},{},[112,118],{"type":43,"tag":113,"props":114,"children":115},"strong",{},[116],{"type":49,"value":117},"High-level request",{"type":49,"value":119}," (e.g., \"I want AI to help my agents perform better\"):\n→ DISCOVERY MODE. Walk through Steps 2-4 to understand what \"better\" means.",{"type":43,"tag":52,"props":121,"children":122},{},[123,128],{"type":43,"tag":113,"props":124,"children":125},{},[126],{"type":49,"value":127},"Mid-level request",{"type":49,"value":129}," (e.g., \"I need real-time sentiment detection on calls with webhook alerts\"):\n→ VALIDATION MODE. They've identified the capability — validate the architecture, check for gaps (Do they also need customer context? Recording for post-call?), recommend skills.",{"type":43,"tag":52,"props":131,"children":132},{},[133,138],{"type":43,"tag":113,"props":134,"children":135},{},[136],{"type":49,"value":137},"Specific implementation request",{"type":49,"value":139}," (e.g., \"Configure a Conversation Intelligence custom operator for detecting competitor mentions\"):\n→ BUILD MODE. Proceed with the relevant Product skill. Quick context check: Is Conversation Intelligence provisioned? Is Conversation Orchestrator linked? Are they aware of the operator lifecycle gotchas?",{"type":43,"tag":44,"props":141,"children":143},{"id":142},"step-2-qualify-intent-the-5-essential-questions",[144],{"type":49,"value":145},"Step 2: Qualify Intent — The 5 Essential Questions",{"type":43,"tag":147,"props":148,"children":149},"ol",{},[150,181,207,233,254],{"type":43,"tag":73,"props":151,"children":152},{},[153,158],{"type":43,"tag":113,"props":154,"children":155},{},[156],{"type":49,"value":157},"What does \"augmentation\" mean for your agents?",{"type":43,"tag":69,"props":159,"children":160},{},[161,166,171,176],{"type":43,"tag":73,"props":162,"children":163},{},[164],{"type":49,"value":165},"Real-time coaching: Live suggestions\u002Fprompts appearing on the agent's screen during a call",{"type":43,"tag":73,"props":167,"children":168},{},[169],{"type":49,"value":170},"Compliance monitoring: Automated detection of script deviations, regulatory violations, disclosure requirements",{"type":43,"tag":73,"props":172,"children":173},{},[174],{"type":49,"value":175},"Post-call QA: Automated scoring and review of completed conversations (replacing manual sampling)",{"type":43,"tag":73,"props":177,"children":178},{},[179],{"type":49,"value":180},"Intelligent routing: Using AI signals to send calls to the right specialist",{"type":43,"tag":73,"props":182,"children":183},{},[184,189],{"type":43,"tag":113,"props":185,"children":186},{},[187],{"type":49,"value":188},"What channels are your agents handling?",{"type":43,"tag":69,"props":190,"children":191},{},[192,197,202],{"type":43,"tag":73,"props":193,"children":194},{},[195],{"type":49,"value":196},"Voice calls only → Transcription + Conversation Intelligence operators on audio stream",{"type":43,"tag":73,"props":198,"children":199},{},[200],{"type":49,"value":201},"Voice + messaging → Conversation Orchestrator for unified conversation tracking + Conversation Intelligence across both",{"type":43,"tag":73,"props":203,"children":204},{},[205],{"type":49,"value":206},"Messaging only → Conversation Intelligence operators on text (no transcription needed)",{"type":43,"tag":73,"props":208,"children":209},{},[210,215],{"type":43,"tag":113,"props":211,"children":212},{},[213],{"type":49,"value":214},"What's your existing contact center infrastructure?",{"type":43,"tag":69,"props":216,"children":217},{},[218,223,228],{"type":43,"tag":73,"props":219,"children":220},{},[221],{"type":49,"value":222},"Twilio Flex → Native integration path (Flex Agent Copilot replatforming onto Conversation Intelligence)",{"type":43,"tag":73,"props":224,"children":225},{},[226],{"type":49,"value":227},"Other CCaaS (Genesys, Five9, NICE) → Webhook-based integration, more custom glue",{"type":43,"tag":73,"props":229,"children":230},{},[231],{"type":49,"value":232},"Custom-built → Full flexibility but more setup",{"type":43,"tag":73,"props":234,"children":235},{},[236,241],{"type":43,"tag":113,"props":237,"children":238},{},[239],{"type":49,"value":240},"Do you need customer context surfaced to agents?",{"type":43,"tag":69,"props":242,"children":243},{},[244,249],{"type":43,"tag":73,"props":245,"children":246},{},[247],{"type":49,"value":248},"No (agents look up context themselves) → Skip Conversation Memory",{"type":43,"tag":73,"props":250,"children":251},{},[252],{"type":49,"value":253},"Yes (show customer history, preferences, past issues on accept) → Add Conversation Memory",{"type":43,"tag":73,"props":255,"children":256},{},[257,262],{"type":43,"tag":113,"props":258,"children":259},{},[260],{"type":49,"value":261},"What's your call volume and budget sensitivity?",{"type":43,"tag":69,"props":263,"children":264},{},[265,270,275],{"type":43,"tag":73,"props":266,"children":267},{},[268],{"type":49,"value":269},"Not all calls are worth transcribing",{"type":43,"tag":73,"props":271,"children":272},{},[273],{"type":49,"value":274},"Consider selective intelligence: Apply Conversation Intelligence only to specific queues, customer segments, or call types",{"type":43,"tag":73,"props":276,"children":277},{},[278],{"type":49,"value":279},"Conversation Intelligence pricing is per-conversation-character — model selection affects cost (GPT-4.1-nano for speed\u002Fcost vs. GPT-5.2 for quality)",{"type":43,"tag":44,"props":281,"children":283},{"id":282},"step-3-assess-sophistication-the-capability-ladder",[284],{"type":49,"value":285},"Step 3: Assess Sophistication — The Capability Ladder",{"type":43,"tag":287,"props":288,"children":290},"h3",{"id":289},"level-1-listen-transcription-recording",[291],{"type":49,"value":292},"Level 1: Listen — Transcription & Recording",{"type":43,"tag":52,"props":294,"children":295},{},[296,301,303,308,310,315,317],{"type":43,"tag":113,"props":297,"children":298},{},[299],{"type":49,"value":300},"Developer says:",{"type":49,"value":302}," \"I want to transcribe calls for review and analysis.\"\n",{"type":43,"tag":113,"props":304,"children":305},{},[306],{"type":49,"value":307},"Architecture:",{"type":49,"value":309}," Real-time Transcription + Call Recordings\n",{"type":43,"tag":113,"props":311,"children":312},{},[313],{"type":49,"value":314},"What it does:",{"type":49,"value":316}," Live STT during calls → transcripts available for search and review. Recordings stored for compliance and playback.\n",{"type":43,"tag":113,"props":318,"children":319},{},[320],{"type":49,"value":321},"Key decisions:",{"type":43,"tag":69,"props":323,"children":324},{},[325,330,335],{"type":43,"tag":73,"props":326,"children":327},{},[328],{"type":49,"value":329},"Engine: Google (wider language support) vs Deepgram (better accuracy, lower latency)",{"type":43,"tag":73,"props":331,"children":332},{},[333],{"type":49,"value":334},"Track: Inbound audio, outbound audio, or both",{"type":43,"tag":73,"props":336,"children":337},{},[338,340,347,349,354,356],{"type":49,"value":339},"Recording method: ",{"type":43,"tag":341,"props":342,"children":344},"code",{"className":343},[],[345],{"type":49,"value":346},"\u003CDial record=\"record-from-answer\">",{"type":49,"value":348}," for simplicity, or Recordings REST API for control\n",{"type":43,"tag":113,"props":350,"children":351},{},[352],{"type":49,"value":353},"Skills to install:",{"type":49,"value":355}," ",{"type":43,"tag":341,"props":357,"children":359},{"className":358},[],[360],{"type":49,"value":361},"twilio-call-recordings",{"type":43,"tag":287,"props":363,"children":365},{"id":364},"level-2-coach-real-time-intelligence",[366],{"type":49,"value":367},"Level 2: Coach — Real-Time Intelligence",{"type":43,"tag":52,"props":369,"children":370},{},[371,375,377,381,383,388,390],{"type":43,"tag":113,"props":372,"children":373},{},[374],{"type":49,"value":300},{"type":49,"value":376}," \"I want to detect sentiment, prompt agents with next-best-response, or monitor script adherence live.\"\n",{"type":43,"tag":113,"props":378,"children":379},{},[380],{"type":49,"value":307},{"type":49,"value":382}," Level 1 + Conversation Intelligence v3 Language Operators\n",{"type":43,"tag":113,"props":384,"children":385},{},[386],{"type":49,"value":387},"What it adds:",{"type":49,"value":389}," Conversation Intelligence attaches to live conversations → runs operators in parallel → fires webhooks on signal detection → your backend pushes prompts to agent UI\n",{"type":43,"tag":113,"props":391,"children":392},{},[393],{"type":49,"value":394},"Pre-built operators (GA):",{"type":43,"tag":69,"props":396,"children":397},{},[398,408,418,428,438,452,457,462],{"type":43,"tag":73,"props":399,"children":400},{},[401,406],{"type":43,"tag":113,"props":402,"children":403},{},[404],{"type":49,"value":405},"Sentiment:",{"type":49,"value":407}," Detect caller frustration, anger, satisfaction in real-time",{"type":43,"tag":73,"props":409,"children":410},{},[411,416],{"type":43,"tag":113,"props":412,"children":413},{},[414],{"type":49,"value":415},"Script Adherence:",{"type":49,"value":417}," Flag when agent deviates from required script (compliance disclosures, greeting, etc.)",{"type":43,"tag":73,"props":419,"children":420},{},[421,426],{"type":43,"tag":113,"props":422,"children":423},{},[424],{"type":49,"value":425},"Next Best Response (NBR):",{"type":49,"value":427}," Suggest the best reply based on conversation context",{"type":43,"tag":73,"props":429,"children":430},{},[431,436],{"type":43,"tag":113,"props":432,"children":433},{},[434],{"type":49,"value":435},"Summary:",{"type":49,"value":437}," Auto-generate post-call summaries",{"type":43,"tag":73,"props":439,"children":440},{},[441,446,448],{"type":43,"tag":113,"props":442,"children":443},{},[444],{"type":49,"value":445},"Custom Operators:",{"type":49,"value":447}," Define your own detection rules (competitor mentions, churn signals, upsell opportunities)\n",{"type":43,"tag":113,"props":449,"children":450},{},[451],{"type":49,"value":321},{"type":43,"tag":73,"props":453,"children":454},{},[455],{"type":49,"value":456},"Which operators to activate (each adds latency and cost)",{"type":43,"tag":73,"props":458,"children":459},{},[460],{"type":49,"value":461},"Webhook destination: Where do signals go? (Flex plugin, custom dashboard, Slack alert)",{"type":43,"tag":73,"props":463,"children":464},{},[465,467,471,473],{"type":49,"value":466},"Model profile: Speed (GPT-4.1-nano, lower cost) vs quality (GPT-5.2, higher accuracy)\n",{"type":43,"tag":113,"props":468,"children":469},{},[470],{"type":49,"value":353},{"type":49,"value":472}," + ",{"type":43,"tag":341,"props":474,"children":476},{"className":475},[],[477],{"type":49,"value":478},"twilio-conversation-intelligence",{"type":43,"tag":287,"props":480,"children":482},{"id":481},"level-3-context-customer-memory-for-agents",[483],{"type":49,"value":484},"Level 3: Context — Customer Memory for Agents",{"type":43,"tag":52,"props":486,"children":487},{},[488,492,494,498,500,504,506],{"type":43,"tag":113,"props":489,"children":490},{},[491],{"type":49,"value":300},{"type":49,"value":493}," \"When the agent picks up, I want them to see who this customer is and their full history.\"\n",{"type":43,"tag":113,"props":495,"children":496},{},[497],{"type":49,"value":307},{"type":49,"value":499}," Level 2 + Conversation Memory (profile hydration)\n",{"type":43,"tag":113,"props":501,"children":502},{},[503],{"type":49,"value":387},{"type":49,"value":505}," On task acceptance, agent desktop fetches Conversation Memory profile → displays customer summary, traits, past observations → agent starts the conversation with full context instead of \"Who is this? What do you need?\"\n",{"type":43,"tag":113,"props":507,"children":508},{},[509],{"type":49,"value":321},{"type":43,"tag":69,"props":511,"children":512},{},[513,518,523],{"type":43,"tag":73,"props":514,"children":515},{},[516],{"type":49,"value":517},"What to surface: Summary only (GA for Flex) or deep context (traits, recent observations, Segment data)",{"type":43,"tag":73,"props":519,"children":520},{},[521],{"type":49,"value":522},"Identity resolution: Match incoming caller to Conversation Memory profile by phone number, email, or custom ID",{"type":43,"tag":73,"props":524,"children":525},{},[526,528,533,535,539,540,546,548],{"type":49,"value":527},"Enrichment sources: Conversation Memory observations only, or also Segment traits via Bridge\n",{"type":43,"tag":113,"props":529,"children":530},{},[531],{"type":49,"value":532},"GA constraint:",{"type":49,"value":534}," Flex integration is summary-only at GA. Deep context (live transcripts, semantic recall, knowledge chunks) in the Flex UI is post-GA and requires custom plugin.\n",{"type":43,"tag":113,"props":536,"children":537},{},[538],{"type":49,"value":353},{"type":49,"value":472},{"type":43,"tag":341,"props":541,"children":543},{"className":542},[],[544],{"type":49,"value":545},"twilio-conversation-memory",{"type":49,"value":547},", ",{"type":43,"tag":341,"props":549,"children":551},{"className":550},[],[552],{"type":49,"value":553},"twilio-conversation-orchestrator",{"type":43,"tag":287,"props":555,"children":557},{"id":556},"level-4-route-intelligence-driven-routing",[558],{"type":49,"value":559},"Level 4: Route — Intelligence-Driven Routing",{"type":43,"tag":52,"props":561,"children":562},{},[563,567,569,573,575,579,581],{"type":43,"tag":113,"props":564,"children":565},{},[566],{"type":49,"value":300},{"type":49,"value":568}," \"I want AI signals to determine which agent gets the call — not just FIFO.\"\n",{"type":43,"tag":113,"props":570,"children":571},{},[572],{"type":49,"value":307},{"type":49,"value":574}," Level 3 + TaskRouter consuming Conversation Intelligence signals\n",{"type":43,"tag":113,"props":576,"children":577},{},[578],{"type":49,"value":387},{"type":49,"value":580}," Conversation Intelligence emits structured routing signals (intent, sentiment, skill_needed, VIP detection) → these feed into TaskRouter workflow expressions → calls route to specialized skill groups (retention team, technical support, VIP desk)\n",{"type":43,"tag":113,"props":582,"children":583},{},[584],{"type":49,"value":321},{"type":43,"tag":69,"props":586,"children":587},{},[588,593,598],{"type":43,"tag":73,"props":589,"children":590},{},[591],{"type":49,"value":592},"Which Conversation Intelligence signals feed routing? (intent classification, sentiment threshold, customer segment from Conversation Memory)",{"type":43,"tag":73,"props":594,"children":595},{},[596],{"type":49,"value":597},"TaskRouter workflow design: Simple skills-matching or multi-tier escalation",{"type":43,"tag":73,"props":599,"children":600},{},[601,603,607,608],{"type":49,"value":602},"Overflow strategy: What happens when the target queue is full?\n",{"type":43,"tag":113,"props":604,"children":605},{},[606],{"type":49,"value":353},{"type":49,"value":472},{"type":43,"tag":341,"props":609,"children":611},{"className":610},[],[612],{"type":49,"value":613},"twilio-taskrouter-routing",{"type":43,"tag":44,"props":615,"children":617},{"id":616},"step-4-qualify-context",[618],{"type":49,"value":619},"Step 4: Qualify Context",{"type":43,"tag":287,"props":621,"children":623},{"id":622},"existing-infrastructure",[624],{"type":49,"value":625},"Existing Infrastructure",{"type":43,"tag":69,"props":627,"children":628},{},[629,639,649],{"type":43,"tag":73,"props":630,"children":631},{},[632,637],{"type":43,"tag":113,"props":633,"children":634},{},[635],{"type":49,"value":636},"Flex customer:",{"type":49,"value":638}," Leverage Flex Agent Copilot (being replatformed onto Conversation Intelligence). Tightest integration path.",{"type":43,"tag":73,"props":640,"children":641},{},[642,647],{"type":43,"tag":113,"props":643,"children":644},{},[645],{"type":49,"value":646},"Other CCaaS:",{"type":49,"value":648}," You'll integrate via webhooks. Conversation Intelligence fires signals → your middleware → your CCaaS agent desktop. More work but fully functional.",{"type":43,"tag":73,"props":650,"children":651},{},[652,657],{"type":43,"tag":113,"props":653,"children":654},{},[655],{"type":49,"value":656},"No contact center yet:",{"type":49,"value":658}," Consider starting with Flex + TaskRouter as the foundation, then layer intelligence.",{"type":43,"tag":287,"props":660,"children":662},{"id":661},"customer-profile",[663],{"type":49,"value":664},"Customer Profile",{"type":43,"tag":52,"props":666,"children":667},{},[668],{"type":43,"tag":113,"props":669,"children":670},{},[671],{"type":49,"value":672},"ISV (building augmentation for multiple clients):",{"type":43,"tag":69,"props":674,"children":675},{},[676,681,686],{"type":43,"tag":73,"props":677,"children":678},{},[679],{"type":49,"value":680},"Per-client Conversation Intelligence operator configurations",{"type":43,"tag":73,"props":682,"children":683},{},[684],{"type":49,"value":685},"Separate Conversation Memory stores per client (max 15 per account)",{"type":43,"tag":73,"props":687,"children":688},{},[689],{"type":49,"value":690},"White-label considerations for agent UI",{"type":43,"tag":52,"props":692,"children":693},{},[694],{"type":43,"tag":113,"props":695,"children":696},{},[697],{"type":49,"value":698},"Enterprise:",{"type":43,"tag":69,"props":700,"children":701},{},[702,707,712,717],{"type":43,"tag":73,"props":703,"children":704},{},[705],{"type":49,"value":706},"Compliance operators are likely mandatory (regulated industries: finance, healthcare, insurance)",{"type":43,"tag":73,"props":708,"children":709},{},[710],{"type":49,"value":711},"Selective intelligence to control cost at scale",{"type":43,"tag":73,"props":713,"children":714},{},[715],{"type":49,"value":716},"Integration with existing QA workflows (Calabrio, Verint, etc.)",{"type":43,"tag":73,"props":718,"children":719},{},[720],{"type":49,"value":721},"No ngrok for webhook delivery — deploy to production infrastructure",{"type":43,"tag":52,"props":723,"children":724},{},[725],{"type":43,"tag":113,"props":726,"children":727},{},[728],{"type":49,"value":729},"SMB:",{"type":43,"tag":69,"props":731,"children":732},{},[733,738,743],{"type":43,"tag":73,"props":734,"children":735},{},[736],{"type":49,"value":737},"Start at Level 2 — sentiment + summary operators give immediate value",{"type":43,"tag":73,"props":739,"children":740},{},[741],{"type":49,"value":742},"Skip Conversation Memory initially — add when agent \"amnesia\" becomes a pain point",{"type":43,"tag":73,"props":744,"children":745},{},[746],{"type":49,"value":747},"Use pre-built operators before investing in custom ones",{"type":43,"tag":44,"props":749,"children":751},{"id":750},"architectural-warnings",[752],{"type":49,"value":753},"Architectural Warnings",{"type":43,"tag":52,"props":755,"children":756},{},[757],{"type":49,"value":758},"These affect which capabilities to recommend and how to set expectations — implementation details are in the Product skills.",{"type":43,"tag":69,"props":760,"children":761},{},[762,772,782,799,817,827,837,847],{"type":43,"tag":73,"props":763,"children":764},{},[765,770],{"type":43,"tag":113,"props":766,"children":767},{},[768],{"type":49,"value":769},"Silent linkage chain:",{"type":49,"value":771}," Conversations Service → Intelligence Service → Capture Rules → Operators must be linked in sequence. Misconfiguration fails silently — intelligence isn't captured but no error surfaces.",{"type":43,"tag":73,"props":773,"children":774},{},[775,780],{"type":43,"tag":113,"props":776,"children":777},{},[778],{"type":49,"value":779},"Operator lifecycle trap:",{"type":49,"value":781}," PUT on an operator creates an inactive new version. No activation endpoint exists — must delete and POST a new one. Plan operator changes as delete+recreate, not update.",{"type":43,"tag":73,"props":783,"children":784},{},[785,790,791,797],{"type":43,"tag":113,"props":786,"children":787},{},[788],{"type":49,"value":789},"One-way door settings:",{"type":49,"value":355},{"type":43,"tag":341,"props":792,"children":794},{"className":793},[],[795],{"type":49,"value":796},"GROUP_BY_PARTICIPANT_ADDRESSES",{"type":49,"value":798}," on a Conversations Service is immutable once set. Removing a capture rule stops ALL capture for that service.",{"type":43,"tag":73,"props":800,"children":801},{},[802,807,809,815],{"type":43,"tag":113,"props":803,"children":804},{},[805],{"type":49,"value":806},"OperatorResults scope leak:",{"type":49,"value":808}," API may return results from other conversations on the same account. Always filter by ",{"type":43,"tag":341,"props":810,"children":812},{"className":811},[],[813],{"type":49,"value":814},"conversation_id",{"type":49,"value":816},".",{"type":43,"tag":73,"props":818,"children":819},{},[820,825],{"type":43,"tag":113,"props":821,"children":822},{},[823],{"type":49,"value":824},"Dashboard vs. webhooks:",{"type":49,"value":826}," Conversation Intelligence signals take 7-10 minutes to reach the dashboard. For real-time coaching, rely on webhook delivery — not dashboard polling.",{"type":43,"tag":73,"props":828,"children":829},{},[830,835],{"type":43,"tag":113,"props":831,"children":832},{},[833],{"type":49,"value":834},"Flex GA constraint:",{"type":49,"value":836}," Conversation Memory integration in Flex is summary-only at GA. Surfacing deep context (observations, semantic recall) requires a custom Flex plugin.",{"type":43,"tag":73,"props":838,"children":839},{},[840,845],{"type":43,"tag":113,"props":841,"children":842},{},[843],{"type":49,"value":844},"Cost model:",{"type":49,"value":846}," Conversation Intelligence pricing is per-conversation-character. Model selection (GPT-4.1-nano for speed\u002Fcost vs. GPT-5.2 for quality) directly affects bill. Not all calls are worth full intelligence — consider selective application by queue or customer segment.",{"type":43,"tag":73,"props":848,"children":849},{},[850,855],{"type":43,"tag":113,"props":851,"children":852},{},[853],{"type":49,"value":854},"No SDK at GA:",{"type":49,"value":856}," All Twilio Conversations integration is raw HTTP with Basic Auth. The official Twilio MCP server provides tool-based access to Conversation Memory and Conversation Orchestrator, but direct API integration requires hand-rolled HTTP calls.",{"type":43,"tag":44,"props":858,"children":860},{"id":859},"decision-rules",[861],{"type":49,"value":862},"Decision Rules",{"type":43,"tag":287,"props":864,"children":866},{"id":865},"transcription-engine-selection",[867],{"type":49,"value":868},"Transcription Engine Selection",{"type":43,"tag":69,"props":870,"children":871},{},[872,882,892,902],{"type":43,"tag":73,"props":873,"children":874},{},[875,880],{"type":43,"tag":113,"props":876,"children":877},{},[878],{"type":49,"value":879},"Google STT:",{"type":49,"value":881}," Wider language support, good for international contact centers. Choose when multi-lingual support is the priority.",{"type":43,"tag":73,"props":883,"children":884},{},[885,890],{"type":43,"tag":113,"props":886,"children":887},{},[888],{"type":49,"value":889},"Deepgram:",{"type":49,"value":891}," Lower latency, better accuracy for English. Choose for English-primary contact centers or noisy environments.",{"type":43,"tag":73,"props":893,"children":894},{},[895,900],{"type":43,"tag":113,"props":896,"children":897},{},[898],{"type":49,"value":899},"Dual-track recommended:",{"type":49,"value":901}," Enables speaker diarization — Conversation Intelligence can distinguish agent from caller. Single-track reduces script adherence and sentiment accuracy.",{"type":43,"tag":73,"props":903,"children":904},{},[905],{"type":49,"value":906},"Implementation gotchas: callback format, ordering, short utterances — see Twilio Real-Time Transcription docs.",{"type":43,"tag":287,"props":908,"children":910},{"id":909},"conversation-intelligence-operator-selection",[911],{"type":49,"value":912},"Conversation Intelligence Operator Selection",{"type":43,"tag":69,"props":914,"children":915},{},[916,926,936,946],{"type":43,"tag":73,"props":917,"children":918},{},[919,924],{"type":43,"tag":113,"props":920,"children":921},{},[922],{"type":49,"value":923},"Pre-built operators:",{"type":49,"value":925}," Sentiment, Script Adherence, Next Best Response, Summary. Start here — immediate value, no custom configuration.",{"type":43,"tag":73,"props":927,"children":928},{},[929,934],{"type":43,"tag":113,"props":930,"children":931},{},[932],{"type":49,"value":933},"Custom operators:",{"type":49,"value":935}," For domain-specific detection (competitor mentions, churn signals, upsell opportunities). Three types: text-generation, classification, extraction.",{"type":43,"tag":73,"props":937,"children":938},{},[939,944],{"type":43,"tag":113,"props":940,"children":941},{},[942],{"type":49,"value":943},"Selective application:",{"type":49,"value":945}," Not all calls warrant full intelligence. Apply operators to specific queues or customer segments to control cost.",{"type":43,"tag":73,"props":947,"children":948},{},[949,951,956],{"type":49,"value":950},"Operator lifecycle gotchas (PUT trap, capture rule deletion) are documented in the ",{"type":43,"tag":341,"props":952,"children":954},{"className":953},[],[955],{"type":49,"value":478},{"type":49,"value":957}," skill.",{"type":43,"tag":287,"props":959,"children":961},{"id":960},"recording-method-selection",[962],{"type":49,"value":963},"Recording Method Selection",{"type":43,"tag":69,"props":965,"children":966},{},[967,985,995,1019,1036,1053,1071],{"type":43,"tag":73,"props":968,"children":969},{},[970,983],{"type":43,"tag":113,"props":971,"children":972},{},[973,975,981],{"type":49,"value":974},"Use ",{"type":43,"tag":341,"props":976,"children":978},{"className":977},[],[979],{"type":49,"value":980},"\u003CDial record>",{"type":49,"value":982}," when:",{"type":49,"value":984}," Simple two-party call recording. Minimal setup.",{"type":43,"tag":73,"props":986,"children":987},{},[988,993],{"type":43,"tag":113,"props":989,"children":990},{},[991],{"type":49,"value":992},"Use Recordings REST API when:",{"type":49,"value":994}," Mid-call control needed (pause during payment). Dual-channel recording for QA.",{"type":43,"tag":73,"props":996,"children":997},{},[998,1009,1011,1017],{"type":43,"tag":113,"props":999,"children":1000},{},[1001,1002,1008],{"type":49,"value":974},{"type":43,"tag":341,"props":1003,"children":1005},{"className":1004},[],[1006],{"type":49,"value":1007},"\u003CStart>\u003CRecording>",{"type":49,"value":982},{"type":49,"value":1010}," Recording must start before ",{"type":43,"tag":341,"props":1012,"children":1014},{"className":1013},[],[1015],{"type":49,"value":1016},"\u003CConnect>",{"type":49,"value":1018}," (e.g., ConversationRelay AI side).",{"type":43,"tag":73,"props":1020,"children":1021},{},[1022,1034],{"type":43,"tag":113,"props":1023,"children":1024},{},[1025,1027,1033],{"type":49,"value":1026},"Use Conference ",{"type":43,"tag":341,"props":1028,"children":1030},{"className":1029},[],[1031],{"type":49,"value":1032},"record",{"type":49,"value":982},{"type":49,"value":1035}," Multi-party calls.",{"type":43,"tag":73,"props":1037,"children":1038},{},[1039,1044,1045,1051],{"type":43,"tag":113,"props":1040,"children":1041},{},[1042],{"type":49,"value":1043},"Critical:",{"type":49,"value":355},{"type":43,"tag":341,"props":1046,"children":1048},{"className":1047},[],[1049],{"type":49,"value":1050},"\u003CRecord>",{"type":49,"value":1052}," (standalone verb) is voicemail-style — NOT for recording calls.",{"type":43,"tag":73,"props":1054,"children":1055},{},[1056,1061,1063,1069],{"type":43,"tag":113,"props":1057,"children":1058},{},[1059],{"type":49,"value":1060},"PCI:",{"type":49,"value":1062}," Never record card numbers. Use ",{"type":43,"tag":341,"props":1064,"children":1066},{"className":1065},[],[1067],{"type":49,"value":1068},"\u003CPay>",{"type":49,"value":1070}," verb. PCI Mode is IRREVERSIBLE and account-wide.",{"type":43,"tag":73,"props":1072,"children":1073},{},[1074,1076,1081],{"type":49,"value":1075},"Detailed method comparison and gotchas are in the ",{"type":43,"tag":341,"props":1077,"children":1079},{"className":1078},[],[1080],{"type":49,"value":361},{"type":49,"value":957},{"type":43,"tag":44,"props":1083,"children":1085},{"id":1084},"ga-constraints-may-2026",[1086],{"type":49,"value":1087},"GA Constraints (May 2026)",{"type":43,"tag":52,"props":1089,"children":1090},{},[1091],{"type":49,"value":1092},"What works:",{"type":43,"tag":69,"props":1094,"children":1095},{},[1096,1101,1106,1111],{"type":43,"tag":73,"props":1097,"children":1098},{},[1099],{"type":49,"value":1100},"Conversation Intelligence v3 real-time operators (sentiment, script adherence, NBR, custom) ✅",{"type":43,"tag":73,"props":1102,"children":1103},{},[1104],{"type":49,"value":1105},"Conversation Memory profile storage and Recall ✅",{"type":43,"tag":73,"props":1107,"children":1108},{},[1109],{"type":49,"value":1110},"TaskRouter with custom routing signals ✅",{"type":43,"tag":73,"props":1112,"children":1113},{},[1114],{"type":49,"value":1115},"Call recordings and real-time transcription ✅",{"type":43,"tag":52,"props":1117,"children":1118},{},[1119],{"type":49,"value":1120},"What requires custom code:",{"type":43,"tag":69,"props":1122,"children":1123},{},[1124,1129,1134],{"type":43,"tag":73,"props":1125,"children":1126},{},[1127],{"type":49,"value":1128},"Flex Agent Copilot: Being replatformed onto Conversation Intelligence. Early stages — expect custom plugin work.",{"type":43,"tag":73,"props":1130,"children":1131},{},[1132],{"type":49,"value":1133},"Aggregated insights: No native dashboards. API-only — pipe to Tableau, PowerBI, Looker.",{"type":43,"tag":73,"props":1135,"children":1136},{},[1137],{"type":49,"value":1138},"Conversation Intelligence webhooks triggering traffic control: Must write custom Functions to act on signals.",{"type":43,"tag":52,"props":1140,"children":1141},{},[1142],{"type":49,"value":1143},"What does NOT work at GA:",{"type":43,"tag":69,"props":1145,"children":1146},{},[1147,1152,1157,1162],{"type":43,"tag":73,"props":1148,"children":1149},{},[1150],{"type":49,"value":1151},"AI copilot silently listening during human conversation (Conversation Orchestrator participant modes)",{"type":43,"tag":73,"props":1153,"children":1154},{},[1155],{"type":49,"value":1156},"Supervisor whisper\u002Fbarge via Conversation Orchestrator (use existing Flex\u002FConference patterns)",{"type":43,"tag":73,"props":1158,"children":1159},{},[1160],{"type":49,"value":1161},"Native \"Next Best Action\" auto-execution (operator suggests, human\u002Fbackend decides)",{"type":43,"tag":73,"props":1163,"children":1164},{},[1165],{"type":49,"value":1166},"Automated intervention pausing outbound campaigns (planned)",{"type":43,"tag":44,"props":1168,"children":1170},{"id":1169},"output-format",[1171],{"type":49,"value":1172},"Output Format",{"type":43,"tag":52,"props":1174,"children":1175},{},[1176],{"type":49,"value":1177},"After qualifying the developer, recommend:",{"type":43,"tag":1179,"props":1180,"children":1184},"pre",{"className":1181,"code":1183,"language":49},[1182],"language-text","Recommended Architecture: [Brief plain-language description of the recommended approach — e.g., \"AI-augmented voice agent with real-time transcription, sentiment analysis, and agent assist suggestions via Twilio Flex.\"]\n\nReference Skills:\n- twilio-call-recordings (if recording needed)\n- twilio-conversation-intelligence (if transcription and AI insights needed)\n- twilio-conversation-memory (if persistent customer context needed)\n- twilio-conversation-orchestrator (if multi-step orchestration needed)\n- twilio-taskrouter-routing (if intelligent routing needed)\n- twilio-voice-insights (for call quality diagnostics)\n- twilio-sendgrid-email-send (if post-call summary emails needed)\n\nSetup Skills:\n- twilio-account-setup — if developer needs help with credentials or account structure\n- twilio-iam-auth-setup — if developer asks about API key scoping or security\n- twilio-webhook-architecture — if developer needs help designing or securing webhook endpoints\n\nGuardrail Skills:\n- twilio-security-hardening (always)\n- twilio-debugging-observability (always — Voice Insights, Event Streams, error triage)\n",[1185],{"type":43,"tag":341,"props":1186,"children":1188},{"__ignoreMap":1187},"",[1189],{"type":49,"value":1183},{"items":1191,"total":1359},[1192,1208,1216,1227,1239,1253,1270,1286,1302,1315,1331,1348],{"slug":1193,"name":1193,"fn":1194,"description":1195,"org":1196,"tags":1197,"stars":26,"repoUrl":27,"updatedAt":1207},"twilio-account-setup","configure Twilio accounts and credentials","Create and configure a Twilio account from scratch. Covers free trial signup, trial limitations, getting credentials (Account SID and Auth Token), buying a phone number, verifying recipient numbers for trial use, SDK installation, first API call, subaccount management (creation, inheritance, credential isolation, limits), and enabling specific products (AI Assistants, Conversations, Verify, ConversationRelay, WhatsApp). Use this skill before any other Twilio skill if you do not yet have a Twilio account or need to enable a product. For Organization-level governance (SSO, SCIM, multi-team), see `twilio-organizations-setup`.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1198,1201,1204],{"name":1199,"slug":1200,"type":15},"API Development","api-development",{"name":1202,"slug":1203,"type":15},"Communications","communications",{"name":1205,"slug":1206,"type":15},"SMS","sms","2026-08-01T05:43:28.968968",{"slug":4,"name":4,"fn":5,"description":6,"org":1209,"tags":1210,"stars":26,"repoUrl":27,"updatedAt":28},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1211,1212,1213,1214,1215],{"name":20,"slug":21,"type":15},{"name":17,"slug":18,"type":15},{"name":23,"slug":24,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},{"slug":1217,"name":1217,"fn":1218,"description":1219,"org":1220,"tags":1221,"stars":26,"repoUrl":27,"updatedAt":1226},"twilio-agent-connect","connect AI agents to Twilio channels","Connect third-party AI agents (OpenAI, Bedrock, LangChain, Microsoft Foundry) to Twilio's communication channels using the Twilio Agent Connect SDK. Covers identity resolution, memory and context management via Conversation Memory, conversation orchestration via Conversation Orchestrator, multi-channel handling (Voice, SMS, RCS, WhatsApp, Chat), and AI-to-human escalation. Use this skill when integrating an existing LLM agent with Twilio services.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1222,1223,1224,1225],{"name":20,"slug":21,"type":15},{"name":1199,"slug":1200,"type":15},{"name":1202,"slug":1203,"type":15},{"name":9,"slug":8,"type":15},"2026-07-17T06:06:05.217098",{"slug":1228,"name":1228,"fn":1229,"description":1230,"org":1231,"tags":1232,"stars":26,"repoUrl":27,"updatedAt":1238},"twilio-ai-agent-architect","plan Twilio conversational AI agents","Planning skill for AI-powered conversational agents. Qualifies the developer's use case across outcome sophistication, entry point, and customer profile to recommend the right Twilio Conversations architecture and implementation skills. Handles both high-level requests (\"build me a voice AI assistant\") and specific ones (\"integrate ConversationRelay with my OpenAI backend\").\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1233,1234,1237],{"name":20,"slug":21,"type":15},{"name":1235,"slug":1236,"type":15},"Architecture","architecture",{"name":9,"slug":8,"type":15},"2026-07-17T06:07:48.883723",{"slug":361,"name":361,"fn":1240,"description":1241,"org":1242,"tags":1243,"stars":26,"repoUrl":27,"updatedAt":1252},"record and manage Twilio voice calls","Record Twilio voice calls correctly. Covers the critical distinction between Record verb (voicemail) and Dial record (call recording), dual-channel for QA, mid-call pause for PCI, Conference recording, and the ConversationRelay workaround. Use this skill whenever you need to capture call audio for compliance, QA, or analytics.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1244,1247,1250,1251],{"name":1245,"slug":1246,"type":15},"Audio","audio",{"name":1248,"slug":1249,"type":15},"Compliance","compliance",{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},"2026-07-17T06:07:55.268412",{"slug":1254,"name":1254,"fn":1255,"description":1256,"org":1257,"tags":1258,"stars":26,"repoUrl":27,"updatedAt":1269},"twilio-cli-reference","manage Twilio resources via CLI","Twilio CLI reference for managing Twilio resources from the terminal. Covers installation, credential profiles, phone number provisioning, sending SMS and email, webhook configuration, local development with a tunneling service, debugging with watch and logs, serverless deployment, and plugin ecosystem. Use when the developer asks to \"just do it\", \"set this up\", \"run a command\", mentions \"CLI\", \"command line\", or \"terminal\", or when an AI agent can execute a task directly instead of writing application code.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1259,1262,1265,1268],{"name":1260,"slug":1261,"type":15},"CLI","cli",{"name":1263,"slug":1264,"type":15},"Local Development","local-development",{"name":1266,"slug":1267,"type":15},"Operations","operations",{"name":9,"slug":8,"type":15},"2026-07-17T06:07:54.925664",{"slug":1271,"name":1271,"fn":1272,"description":1273,"org":1274,"tags":1275,"stars":26,"repoUrl":27,"updatedAt":1285},"twilio-compliance-onboarding","manage Twilio messaging and voice compliance","Registrations required BEFORE Twilio traffic works. Covers messaging programs (A2P 10DLC, toll-free verification, WhatsApp WABA, RCS, short code, alphanumeric sender) and voice trust programs (STIR\u002FSHAKEN, Voice Integrity, Branded Calling, CNAM). Each number\u002Fsender type has its own program — registration blocks traffic until complete.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1276,1277,1280,1281,1282],{"name":1248,"slug":1249,"type":15},{"name":1278,"slug":1279,"type":15},"Messaging","messaging",{"name":1205,"slug":1206,"type":15},{"name":9,"slug":8,"type":15},{"name":1283,"slug":1284,"type":15},"WhatsApp","whatsapp","2026-07-17T06:05:47.897229",{"slug":1287,"name":1287,"fn":1288,"description":1289,"org":1290,"tags":1291,"stars":26,"repoUrl":27,"updatedAt":1301},"twilio-compliance-traffic","ensure compliance for Twilio messaging traffic","Rules you must follow for Twilio messaging and voice traffic. Covers TCPA (consent tiers, quiet hours, DNC), GDPR (EU consent, right to deletion), PCI DSS (payment recording, Pay verb), HIPAA (BAA, PHI), FDCPA (debt collection limits), CAN-SPAM, WhatsApp policies, SHAKEN\u002FSTIR, and consent management patterns. Use this skill proactively when developers have working traffic to ensure they follow the rules.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1292,1293,1294,1297,1300],{"name":1248,"slug":1249,"type":15},{"name":1278,"slug":1279,"type":15},{"name":1295,"slug":1296,"type":15},"Regulatory Compliance","regulatory-compliance",{"name":1298,"slug":1299,"type":15},"Security","security",{"name":9,"slug":8,"type":15},"2026-07-17T06:07:55.952779",{"slug":1303,"name":1303,"fn":1304,"description":1305,"org":1306,"tags":1307,"stars":26,"repoUrl":27,"updatedAt":1314},"twilio-conference-calls","build multi-party calls with Twilio Conference","Build multi-party calls using Twilio Conference. Covers warm transfer, cold transfer, coaching (whisper), hold vs mute, participant modes, and supervisor barge. Use this skill for any contact center, support line, or scenario requiring transfers, holds, or multi-party calls.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1308,1309,1310,1313],{"name":1245,"slug":1246,"type":15},{"name":1202,"slug":1203,"type":15},{"name":1311,"slug":1312,"type":15},"Meetings","meetings",{"name":9,"slug":8,"type":15},"2026-07-17T06:07:55.603708",{"slug":1316,"name":1316,"fn":1317,"description":1318,"org":1319,"tags":1320,"stars":26,"repoUrl":27,"updatedAt":1330},"twilio-content-template-builder","create and send message templates with Twilio","Create, manage, and send message templates using Twilio's Content API. Covers template creation for WhatsApp, SMS, RCS, and MMS; variable usage; WhatsApp Meta approval; and sending templates via ContentSid. Use this skill when building structured messages that require pre-approval or consistent formatting across channels.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1321,1324,1325,1326,1329],{"name":1322,"slug":1323,"type":15},"Email","email",{"name":1278,"slug":1279,"type":15},{"name":1205,"slug":1206,"type":15},{"name":1327,"slug":1328,"type":15},"Templates","templates",{"name":9,"slug":8,"type":15},"2026-07-17T06:04:26.637309",{"slug":478,"name":478,"fn":1332,"description":1333,"org":1334,"tags":1335,"stars":26,"repoUrl":27,"updatedAt":1347},"build conversation intelligence pipelines","Twilio Conversation Intelligence development guide. Use when building real-time or post-call conversation analysis, language operator pipelines, sentiment analysis, agent assist, cross-channel analytics, or querying aggregated conversation insights (sentiment trends, escalation rates, dashboards).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1336,1337,1340,1343,1346],{"name":20,"slug":21,"type":15},{"name":1338,"slug":1339,"type":15},"Analytics","analytics",{"name":1341,"slug":1342,"type":15},"Monitoring","monitoring",{"name":1344,"slug":1345,"type":15},"NLP","nlp",{"name":9,"slug":8,"type":15},"2026-07-17T06:07:52.545387",{"slug":545,"name":545,"fn":1349,"description":1350,"org":1351,"tags":1352,"stars":26,"repoUrl":27,"updatedAt":1358},"manage conversation memory with Twilio","Store and retrieve conversation context using Twilio Conversation Memory. Covers Memory Store provisioning, profile management, traits, observations, conversation summaries, and semantic Recall. Use this skill to give AI agents or human agents persistent memory of conversations across sessions and channels.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1353,1354,1357],{"name":20,"slug":21,"type":15},{"name":1355,"slug":1356,"type":15},"Memory","memory",{"name":9,"slug":8,"type":15},"2026-07-17T06:04:19.526724",57,{"items":1361,"total":1359},[1362,1368,1376,1383,1389,1396,1403],{"slug":1193,"name":1193,"fn":1194,"description":1195,"org":1363,"tags":1364,"stars":26,"repoUrl":27,"updatedAt":1207},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1365,1366,1367],{"name":1199,"slug":1200,"type":15},{"name":1202,"slug":1203,"type":15},{"name":1205,"slug":1206,"type":15},{"slug":4,"name":4,"fn":5,"description":6,"org":1369,"tags":1370,"stars":26,"repoUrl":27,"updatedAt":28},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1371,1372,1373,1374,1375],{"name":20,"slug":21,"type":15},{"name":17,"slug":18,"type":15},{"name":23,"slug":24,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},{"slug":1217,"name":1217,"fn":1218,"description":1219,"org":1377,"tags":1378,"stars":26,"repoUrl":27,"updatedAt":1226},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1379,1380,1381,1382],{"name":20,"slug":21,"type":15},{"name":1199,"slug":1200,"type":15},{"name":1202,"slug":1203,"type":15},{"name":9,"slug":8,"type":15},{"slug":1228,"name":1228,"fn":1229,"description":1230,"org":1384,"tags":1385,"stars":26,"repoUrl":27,"updatedAt":1238},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1386,1387,1388],{"name":20,"slug":21,"type":15},{"name":1235,"slug":1236,"type":15},{"name":9,"slug":8,"type":15},{"slug":361,"name":361,"fn":1240,"description":1241,"org":1390,"tags":1391,"stars":26,"repoUrl":27,"updatedAt":1252},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1392,1393,1394,1395],{"name":1245,"slug":1246,"type":15},{"name":1248,"slug":1249,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},{"slug":1254,"name":1254,"fn":1255,"description":1256,"org":1397,"tags":1398,"stars":26,"repoUrl":27,"updatedAt":1269},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1399,1400,1401,1402],{"name":1260,"slug":1261,"type":15},{"name":1263,"slug":1264,"type":15},{"name":1266,"slug":1267,"type":15},{"name":9,"slug":8,"type":15},{"slug":1271,"name":1271,"fn":1272,"description":1273,"org":1404,"tags":1405,"stars":26,"repoUrl":27,"updatedAt":1285},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1406,1407,1408,1409,1410],{"name":1248,"slug":1249,"type":15},{"name":1278,"slug":1279,"type":15},{"name":1205,"slug":1206,"type":15},{"name":9,"slug":8,"type":15},{"name":1283,"slug":1284,"type":15}]