[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-datadog-labs-dd-audit-ai-activity":3,"mdc-pswlx-key":39,"related-org-datadog-labs-dd-audit-ai-activity":1332,"related-repo-datadog-labs-dd-audit-ai-activity":1510},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":28,"repoUrl":29,"updatedAt":30,"license":31,"forks":32,"topics":33,"repo":34,"sourceUrl":37,"mdContent":38},"dd-audit-ai-activity","audit Datadog AI activity","Audit what the Bits AI assistant (MCP server) has done in your Datadog org — tool calls by user, resources accessed, and anomaly flags for AI governance.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"datadog-labs","Datadog Labs","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fdatadog-labs.png",[12,16,19,22,25],{"name":13,"slug":14,"type":15},"Security","security","tag",{"name":17,"slug":18,"type":15},"Governance","governance",{"name":20,"slug":21,"type":15},"Datadog","datadog",{"name":23,"slug":24,"type":15},"Audit","audit",{"name":26,"slug":27,"type":15},"Agents","agents",145,"https:\u002F\u002Fgithub.com\u002Fdatadog-labs\u002Fagent-skills","2026-05-08T05:05:15.770513",null,19,[],{"repoUrl":29,"stars":28,"forks":32,"topics":35,"description":36},[],"Public repository for Datadog Agent Skills","https:\u002F\u002Fgithub.com\u002Fdatadog-labs\u002Fagent-skills\u002Ftree\u002FHEAD\u002Fdd-audit\u002Fai-activity-audit","---\nname: dd-audit-ai-activity\ndescription: Audit what the Bits AI assistant (MCP server) has done in your Datadog org — tool calls by user, resources accessed, and anomaly flags for AI governance.\nmetadata:\n  version: \"0.1.0\"\n  author: datadog-labs\n  repository: https:\u002F\u002Fgithub.com\u002Fdatadog-labs\u002Fagent-skills\n  tags: datadog,audit,ai,mcp,bits-ai,governance,dd-audit\n  alwaysApply: \"false\"\n---\n\n# Audit Trail: AI Activity Audit\n\nEvery Datadog MCP tool call is recorded in Audit Trail under the `Bits AI SRE` category. This skill surfaces what the AI assistant has done in your org — which users invoked it, which tools were called, and which resources were affected.\n\n## Prerequisites\n\n```bash\npup auth login   # OAuth2 (recommended)\n# or set DD_API_KEY + DD_APP_KEY with audit_logs_read scope\n```\n\n## Queries\n\n### All MCP tool activity in a time window\n\n```bash\npup audit-logs search --query \"@evt.name:\\\"MCP Server\\\"\" --from 7d --limit 500 -o json \\\n  | jq '[.data[] | {\n      timestamp: .attributes.timestamp,\n      user: .attributes.attributes.usr.email,\n      actor_type: .attributes.attributes.evt.actor.type,\n      action: .attributes.attributes.action,\n      resource_type: .attributes.attributes.asset.type,\n      resource_id: .attributes.attributes.asset.id,\n      ip: .attributes.attributes.network.client.ip,\n      country: .attributes.attributes.network.client.geoip.country.name\n    }]'\n```\n\n### Activity by user (who is using the AI assistant most?)\n\n```bash\npup audit-logs search --query \"@evt.name:\\\"MCP Server\\\"\" --from 30d --limit 1000 -o json \\\n  | jq '[.data[] | .attributes.attributes.usr.email]\n    | group_by(.)\n    | map({user: .[0], tool_calls: length})\n    | sort_by(-.tool_calls)'\n```\n\n### Resources modified by AI tool calls\n\n```bash\npup audit-logs search \\\n  --query \"@evt.name:\\\"MCP Server\\\" @action:(created OR modified OR deleted)\" \\\n  --from 7d --limit 500 -o json \\\n  | jq '[.data[] | {\n      timestamp: .attributes.timestamp,\n      user: .attributes.attributes.usr.email,\n      action: .attributes.attributes.action,\n      resource_type: .attributes.attributes.asset.type,\n      resource_id: .attributes.attributes.asset.id\n    }]'\n```\n\n### AI activity for a specific user\n\n```bash\npup audit-logs search \\\n  --query \"@evt.name:\\\"MCP Server\\\" @usr.email:user@example.com\" \\\n  --from 30d --limit 500 -o json \\\n  | jq '[.data[] | {\n      timestamp: .attributes.timestamp,\n      action: .attributes.attributes.action,\n      resource_type: .attributes.attributes.asset.type,\n      resource_id: .attributes.attributes.asset.id\n    }]'\n```\n\n### Weekly summary report\n\n```bash\npup audit-logs search --query \"@evt.name:\\\"MCP Server\\\"\" --from 7d --limit 1000 -o json \\\n  | jq '{\n      total_tool_calls: (.data | length),\n      unique_users: ([.data[] | .attributes.attributes.usr.email] | unique | length),\n      top_users: (\n        [.data[] | .attributes.attributes.usr.email]\n        | group_by(.)\n        | map({user: .[0], calls: length})\n        | sort_by(-.calls)\n        | .[:5]\n      ),\n      actions_breakdown: (\n        [.data[] | .attributes.attributes.action]\n        | group_by(.)\n        | map({action: .[0], count: length})\n        | sort_by(-.count)\n      ),\n      resource_types: (\n        [.data[] | .attributes.attributes.asset.type]\n        | group_by(.)\n        | map({type: .[0], count: length})\n        | sort_by(-.count)\n      )\n    }'\n```\n\n## Anomaly Flags\n\n| Signal | Governance concern |\n|--------|--------------------|\n| AI performing `deleted` actions on monitors or dashboards | Review whether destructive AI operations are expected |\n| AI acting as `SUPPORT_USER` | Datadog support using AI on behalf of org |\n| First-time user invoking AI tools | New user accessing AI assistant |\n| High volume of tool calls in short window | Automated\u002Fbatch AI usage |\n| AI accessing resources outside user's normal scope | Potential over-permissioned AI session |\n\n## Output Format\n\n```\nAI Activity Audit — [Org] — [Date Range]\n\nTotal MCP tool calls: [N]\nUnique users: [N]\n\nTop users:\n  [user@example.com]: [N] calls\n\nActions breakdown:\n  accessed: [N]\n  modified: [N]\n  created: [N]\n  deleted: [N]\n\nResource types affected:\n  dashboard: [N]\n  monitor: [N]\n\nAnomalies:\n  [List any flagged events with timestamp, user, action, resource]\n```\n\n## Context\n\nThis skill is most useful for:\n- **Security reviews:** Verifying AI actions were authorized and within expected scope\n- **Compliance audits:** Demonstrating AI activity is logged and attributable to specific users\n- **Governance reports:** Understanding adoption and risk surface of the AI assistant across the org\n\nNo other observability vendor audits their AI assistant's actions at this level of detail.\n\n## References\n\n- [Bits AI SRE documentation](https:\u002F\u002Fdocs.datadoghq.com\u002Fbits_ai\u002F)\n- [Audit Trail events — Bits AI SRE category](https:\u002F\u002Fdocs.datadoghq.com\u002Faccount_management\u002Faudit_trail\u002Fevents\u002F)\n- [MCP Server setup](https:\u002F\u002Fdocs.datadoghq.com\u002Fbits_ai\u002Fmcp_server\u002F)\n",{"data":40,"body":45},{"name":4,"description":6,"metadata":41},{"version":42,"author":8,"repository":29,"tags":43,"alwaysApply":44},"0.1.0","datadog,audit,ai,mcp,bits-ai,governance,dd-audit","false",{"type":46,"children":47},"root",[48,57,72,79,128,134,141,346,352,480,486,651,657,812,818,1104,1110,1217,1223,1233,1239,1244,1280,1285,1291,1326],{"type":49,"tag":50,"props":51,"children":53},"element","h1",{"id":52},"audit-trail-ai-activity-audit",[54],{"type":55,"value":56},"text","Audit Trail: AI Activity Audit",{"type":49,"tag":58,"props":59,"children":60},"p",{},[61,63,70],{"type":55,"value":62},"Every Datadog MCP tool call is recorded in Audit Trail under the ",{"type":49,"tag":64,"props":65,"children":67},"code",{"className":66},[],[68],{"type":55,"value":69},"Bits AI SRE",{"type":55,"value":71}," category. This skill surfaces what the AI assistant has done in your org — which users invoked it, which tools were called, and which resources were affected.",{"type":49,"tag":73,"props":74,"children":76},"h2",{"id":75},"prerequisites",[77],{"type":55,"value":78},"Prerequisites",{"type":49,"tag":80,"props":81,"children":86},"pre",{"className":82,"code":83,"language":84,"meta":85,"style":85},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","pup auth login   # OAuth2 (recommended)\n# or set DD_API_KEY + DD_APP_KEY with audit_logs_read scope\n","bash","",[87],{"type":49,"tag":64,"props":88,"children":89},{"__ignoreMap":85},[90,119],{"type":49,"tag":91,"props":92,"children":95},"span",{"class":93,"line":94},"line",1,[96,102,108,113],{"type":49,"tag":91,"props":97,"children":99},{"style":98},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[100],{"type":55,"value":101},"pup",{"type":49,"tag":91,"props":103,"children":105},{"style":104},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[106],{"type":55,"value":107}," auth",{"type":49,"tag":91,"props":109,"children":110},{"style":104},[111],{"type":55,"value":112}," login",{"type":49,"tag":91,"props":114,"children":116},{"style":115},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[117],{"type":55,"value":118},"   # OAuth2 (recommended)\n",{"type":49,"tag":91,"props":120,"children":122},{"class":93,"line":121},2,[123],{"type":49,"tag":91,"props":124,"children":125},{"style":115},[126],{"type":55,"value":127},"# or set DD_API_KEY + DD_APP_KEY with audit_logs_read scope\n",{"type":49,"tag":73,"props":129,"children":131},{"id":130},"queries",[132],{"type":55,"value":133},"Queries",{"type":49,"tag":135,"props":136,"children":138},"h3",{"id":137},"all-mcp-tool-activity-in-a-time-window",[139],{"type":55,"value":140},"All MCP tool activity in a time window",{"type":49,"tag":80,"props":142,"children":144},{"className":82,"code":143,"language":84,"meta":85,"style":85},"pup audit-logs search --query \"@evt.name:\\\"MCP Server\\\"\" --from 7d --limit 500 -o json \\\n  | jq '[.data[] | {\n      timestamp: .attributes.timestamp,\n      user: .attributes.attributes.usr.email,\n      actor_type: .attributes.attributes.evt.actor.type,\n      action: .attributes.attributes.action,\n      resource_type: .attributes.attributes.asset.type,\n      resource_id: .attributes.attributes.asset.id,\n      ip: .attributes.attributes.network.client.ip,\n      country: .attributes.attributes.network.client.geoip.country.name\n    }]'\n",[145],{"type":49,"tag":64,"props":146,"children":147},{"__ignoreMap":85},[148,237,260,269,278,287,296,305,314,323,332],{"type":49,"tag":91,"props":149,"children":150},{"class":93,"line":94},[151,155,160,165,170,176,181,187,192,196,201,206,211,216,222,227,232],{"type":49,"tag":91,"props":152,"children":153},{"style":98},[154],{"type":55,"value":101},{"type":49,"tag":91,"props":156,"children":157},{"style":104},[158],{"type":55,"value":159}," audit-logs",{"type":49,"tag":91,"props":161,"children":162},{"style":104},[163],{"type":55,"value":164}," search",{"type":49,"tag":91,"props":166,"children":167},{"style":104},[168],{"type":55,"value":169}," --query",{"type":49,"tag":91,"props":171,"children":173},{"style":172},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[174],{"type":55,"value":175}," \"",{"type":49,"tag":91,"props":177,"children":178},{"style":104},[179],{"type":55,"value":180},"@evt.name:",{"type":49,"tag":91,"props":182,"children":184},{"style":183},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[185],{"type":55,"value":186},"\\\"",{"type":49,"tag":91,"props":188,"children":189},{"style":104},[190],{"type":55,"value":191},"MCP Server",{"type":49,"tag":91,"props":193,"children":194},{"style":183},[195],{"type":55,"value":186},{"type":49,"tag":91,"props":197,"children":198},{"style":172},[199],{"type":55,"value":200},"\"",{"type":49,"tag":91,"props":202,"children":203},{"style":104},[204],{"type":55,"value":205}," --from",{"type":49,"tag":91,"props":207,"children":208},{"style":104},[209],{"type":55,"value":210}," 7d",{"type":49,"tag":91,"props":212,"children":213},{"style":104},[214],{"type":55,"value":215}," --limit",{"type":49,"tag":91,"props":217,"children":219},{"style":218},"--shiki-light:#F76D47;--shiki-default:#F78C6C;--shiki-dark:#F78C6C",[220],{"type":55,"value":221}," 500",{"type":49,"tag":91,"props":223,"children":224},{"style":104},[225],{"type":55,"value":226}," -o",{"type":49,"tag":91,"props":228,"children":229},{"style":104},[230],{"type":55,"value":231}," json",{"type":49,"tag":91,"props":233,"children":234},{"style":183},[235],{"type":55,"value":236}," \\\n",{"type":49,"tag":91,"props":238,"children":239},{"class":93,"line":121},[240,245,250,255],{"type":49,"tag":91,"props":241,"children":242},{"style":172},[243],{"type":55,"value":244},"  |",{"type":49,"tag":91,"props":246,"children":247},{"style":98},[248],{"type":55,"value":249}," jq",{"type":49,"tag":91,"props":251,"children":252},{"style":172},[253],{"type":55,"value":254}," '",{"type":49,"tag":91,"props":256,"children":257},{"style":104},[258],{"type":55,"value":259},"[.data[] | {\n",{"type":49,"tag":91,"props":261,"children":263},{"class":93,"line":262},3,[264],{"type":49,"tag":91,"props":265,"children":266},{"style":104},[267],{"type":55,"value":268},"      timestamp: .attributes.timestamp,\n",{"type":49,"tag":91,"props":270,"children":272},{"class":93,"line":271},4,[273],{"type":49,"tag":91,"props":274,"children":275},{"style":104},[276],{"type":55,"value":277},"      user: .attributes.attributes.usr.email,\n",{"type":49,"tag":91,"props":279,"children":281},{"class":93,"line":280},5,[282],{"type":49,"tag":91,"props":283,"children":284},{"style":104},[285],{"type":55,"value":286},"      actor_type: .attributes.attributes.evt.actor.type,\n",{"type":49,"tag":91,"props":288,"children":290},{"class":93,"line":289},6,[291],{"type":49,"tag":91,"props":292,"children":293},{"style":104},[294],{"type":55,"value":295},"      action: .attributes.attributes.action,\n",{"type":49,"tag":91,"props":297,"children":299},{"class":93,"line":298},7,[300],{"type":49,"tag":91,"props":301,"children":302},{"style":104},[303],{"type":55,"value":304},"      resource_type: .attributes.attributes.asset.type,\n",{"type":49,"tag":91,"props":306,"children":308},{"class":93,"line":307},8,[309],{"type":49,"tag":91,"props":310,"children":311},{"style":104},[312],{"type":55,"value":313},"      resource_id: .attributes.attributes.asset.id,\n",{"type":49,"tag":91,"props":315,"children":317},{"class":93,"line":316},9,[318],{"type":49,"tag":91,"props":319,"children":320},{"style":104},[321],{"type":55,"value":322},"      ip: .attributes.attributes.network.client.ip,\n",{"type":49,"tag":91,"props":324,"children":326},{"class":93,"line":325},10,[327],{"type":49,"tag":91,"props":328,"children":329},{"style":104},[330],{"type":55,"value":331},"      country: .attributes.attributes.network.client.geoip.country.name\n",{"type":49,"tag":91,"props":333,"children":335},{"class":93,"line":334},11,[336,341],{"type":49,"tag":91,"props":337,"children":338},{"style":104},[339],{"type":55,"value":340},"    }]",{"type":49,"tag":91,"props":342,"children":343},{"style":172},[344],{"type":55,"value":345},"'\n",{"type":49,"tag":135,"props":347,"children":349},{"id":348},"activity-by-user-who-is-using-the-ai-assistant-most",[350],{"type":55,"value":351},"Activity by user (who is using the AI assistant most?)",{"type":49,"tag":80,"props":353,"children":355},{"className":82,"code":354,"language":84,"meta":85,"style":85},"pup audit-logs search --query \"@evt.name:\\\"MCP Server\\\"\" --from 30d --limit 1000 -o json \\\n  | jq '[.data[] | .attributes.attributes.usr.email]\n    | group_by(.)\n    | map({user: .[0], tool_calls: length})\n    | sort_by(-.tool_calls)'\n",[356],{"type":49,"tag":64,"props":357,"children":358},{"__ignoreMap":85},[359,432,452,460,468],{"type":49,"tag":91,"props":360,"children":361},{"class":93,"line":94},[362,366,370,374,378,382,386,390,394,398,402,406,411,415,420,424,428],{"type":49,"tag":91,"props":363,"children":364},{"style":98},[365],{"type":55,"value":101},{"type":49,"tag":91,"props":367,"children":368},{"style":104},[369],{"type":55,"value":159},{"type":49,"tag":91,"props":371,"children":372},{"style":104},[373],{"type":55,"value":164},{"type":49,"tag":91,"props":375,"children":376},{"style":104},[377],{"type":55,"value":169},{"type":49,"tag":91,"props":379,"children":380},{"style":172},[381],{"type":55,"value":175},{"type":49,"tag":91,"props":383,"children":384},{"style":104},[385],{"type":55,"value":180},{"type":49,"tag":91,"props":387,"children":388},{"style":183},[389],{"type":55,"value":186},{"type":49,"tag":91,"props":391,"children":392},{"style":104},[393],{"type":55,"value":191},{"type":49,"tag":91,"props":395,"children":396},{"style":183},[397],{"type":55,"value":186},{"type":49,"tag":91,"props":399,"children":400},{"style":172},[401],{"type":55,"value":200},{"type":49,"tag":91,"props":403,"children":404},{"style":104},[405],{"type":55,"value":205},{"type":49,"tag":91,"props":407,"children":408},{"style":104},[409],{"type":55,"value":410}," 30d",{"type":49,"tag":91,"props":412,"children":413},{"style":104},[414],{"type":55,"value":215},{"type":49,"tag":91,"props":416,"children":417},{"style":218},[418],{"type":55,"value":419}," 1000",{"type":49,"tag":91,"props":421,"children":422},{"style":104},[423],{"type":55,"value":226},{"type":49,"tag":91,"props":425,"children":426},{"style":104},[427],{"type":55,"value":231},{"type":49,"tag":91,"props":429,"children":430},{"style":183},[431],{"type":55,"value":236},{"type":49,"tag":91,"props":433,"children":434},{"class":93,"line":121},[435,439,443,447],{"type":49,"tag":91,"props":436,"children":437},{"style":172},[438],{"type":55,"value":244},{"type":49,"tag":91,"props":440,"children":441},{"style":98},[442],{"type":55,"value":249},{"type":49,"tag":91,"props":444,"children":445},{"style":172},[446],{"type":55,"value":254},{"type":49,"tag":91,"props":448,"children":449},{"style":104},[450],{"type":55,"value":451},"[.data[] | .attributes.attributes.usr.email]\n",{"type":49,"tag":91,"props":453,"children":454},{"class":93,"line":262},[455],{"type":49,"tag":91,"props":456,"children":457},{"style":104},[458],{"type":55,"value":459},"    | group_by(.)\n",{"type":49,"tag":91,"props":461,"children":462},{"class":93,"line":271},[463],{"type":49,"tag":91,"props":464,"children":465},{"style":104},[466],{"type":55,"value":467},"    | map({user: .[0], tool_calls: length})\n",{"type":49,"tag":91,"props":469,"children":470},{"class":93,"line":280},[471,476],{"type":49,"tag":91,"props":472,"children":473},{"style":104},[474],{"type":55,"value":475},"    | sort_by(-.tool_calls)",{"type":49,"tag":91,"props":477,"children":478},{"style":172},[479],{"type":55,"value":345},{"type":49,"tag":135,"props":481,"children":483},{"id":482},"resources-modified-by-ai-tool-calls",[484],{"type":55,"value":485},"Resources modified by AI tool calls",{"type":49,"tag":80,"props":487,"children":489},{"className":82,"code":488,"language":84,"meta":85,"style":85},"pup audit-logs search \\\n  --query \"@evt.name:\\\"MCP Server\\\" @action:(created OR modified OR deleted)\" \\\n  --from 7d --limit 500 -o json \\\n  | jq '[.data[] | {\n      timestamp: .attributes.timestamp,\n      user: .attributes.attributes.usr.email,\n      action: .attributes.attributes.action,\n      resource_type: .attributes.attributes.asset.type,\n      resource_id: .attributes.attributes.asset.id\n    }]'\n",[490],{"type":49,"tag":64,"props":491,"children":492},{"__ignoreMap":85},[493,512,553,585,604,611,618,625,632,640],{"type":49,"tag":91,"props":494,"children":495},{"class":93,"line":94},[496,500,504,508],{"type":49,"tag":91,"props":497,"children":498},{"style":98},[499],{"type":55,"value":101},{"type":49,"tag":91,"props":501,"children":502},{"style":104},[503],{"type":55,"value":159},{"type":49,"tag":91,"props":505,"children":506},{"style":104},[507],{"type":55,"value":164},{"type":49,"tag":91,"props":509,"children":510},{"style":183},[511],{"type":55,"value":236},{"type":49,"tag":91,"props":513,"children":514},{"class":93,"line":121},[515,520,524,528,532,536,540,545,549],{"type":49,"tag":91,"props":516,"children":517},{"style":104},[518],{"type":55,"value":519},"  --query",{"type":49,"tag":91,"props":521,"children":522},{"style":172},[523],{"type":55,"value":175},{"type":49,"tag":91,"props":525,"children":526},{"style":104},[527],{"type":55,"value":180},{"type":49,"tag":91,"props":529,"children":530},{"style":183},[531],{"type":55,"value":186},{"type":49,"tag":91,"props":533,"children":534},{"style":104},[535],{"type":55,"value":191},{"type":49,"tag":91,"props":537,"children":538},{"style":183},[539],{"type":55,"value":186},{"type":49,"tag":91,"props":541,"children":542},{"style":104},[543],{"type":55,"value":544}," @action:(created OR modified OR deleted)",{"type":49,"tag":91,"props":546,"children":547},{"style":172},[548],{"type":55,"value":200},{"type":49,"tag":91,"props":550,"children":551},{"style":183},[552],{"type":55,"value":236},{"type":49,"tag":91,"props":554,"children":555},{"class":93,"line":262},[556,561,565,569,573,577,581],{"type":49,"tag":91,"props":557,"children":558},{"style":104},[559],{"type":55,"value":560},"  --from",{"type":49,"tag":91,"props":562,"children":563},{"style":104},[564],{"type":55,"value":210},{"type":49,"tag":91,"props":566,"children":567},{"style":104},[568],{"type":55,"value":215},{"type":49,"tag":91,"props":570,"children":571},{"style":218},[572],{"type":55,"value":221},{"type":49,"tag":91,"props":574,"children":575},{"style":104},[576],{"type":55,"value":226},{"type":49,"tag":91,"props":578,"children":579},{"style":104},[580],{"type":55,"value":231},{"type":49,"tag":91,"props":582,"children":583},{"style":183},[584],{"type":55,"value":236},{"type":49,"tag":91,"props":586,"children":587},{"class":93,"line":271},[588,592,596,600],{"type":49,"tag":91,"props":589,"children":590},{"style":172},[591],{"type":55,"value":244},{"type":49,"tag":91,"props":593,"children":594},{"style":98},[595],{"type":55,"value":249},{"type":49,"tag":91,"props":597,"children":598},{"style":172},[599],{"type":55,"value":254},{"type":49,"tag":91,"props":601,"children":602},{"style":104},[603],{"type":55,"value":259},{"type":49,"tag":91,"props":605,"children":606},{"class":93,"line":280},[607],{"type":49,"tag":91,"props":608,"children":609},{"style":104},[610],{"type":55,"value":268},{"type":49,"tag":91,"props":612,"children":613},{"class":93,"line":289},[614],{"type":49,"tag":91,"props":615,"children":616},{"style":104},[617],{"type":55,"value":277},{"type":49,"tag":91,"props":619,"children":620},{"class":93,"line":298},[621],{"type":49,"tag":91,"props":622,"children":623},{"style":104},[624],{"type":55,"value":295},{"type":49,"tag":91,"props":626,"children":627},{"class":93,"line":307},[628],{"type":49,"tag":91,"props":629,"children":630},{"style":104},[631],{"type":55,"value":304},{"type":49,"tag":91,"props":633,"children":634},{"class":93,"line":316},[635],{"type":49,"tag":91,"props":636,"children":637},{"style":104},[638],{"type":55,"value":639},"      resource_id: .attributes.attributes.asset.id\n",{"type":49,"tag":91,"props":641,"children":642},{"class":93,"line":325},[643,647],{"type":49,"tag":91,"props":644,"children":645},{"style":104},[646],{"type":55,"value":340},{"type":49,"tag":91,"props":648,"children":649},{"style":172},[650],{"type":55,"value":345},{"type":49,"tag":135,"props":652,"children":654},{"id":653},"ai-activity-for-a-specific-user",[655],{"type":55,"value":656},"AI activity for a specific user",{"type":49,"tag":80,"props":658,"children":660},{"className":82,"code":659,"language":84,"meta":85,"style":85},"pup audit-logs search \\\n  --query \"@evt.name:\\\"MCP Server\\\" @usr.email:user@example.com\" \\\n  --from 30d --limit 500 -o json \\\n  | jq '[.data[] | {\n      timestamp: .attributes.timestamp,\n      action: .attributes.attributes.action,\n      resource_type: .attributes.attributes.asset.type,\n      resource_id: .attributes.attributes.asset.id\n    }]'\n",[661],{"type":49,"tag":64,"props":662,"children":663},{"__ignoreMap":85},[664,683,723,754,773,780,787,794,801],{"type":49,"tag":91,"props":665,"children":666},{"class":93,"line":94},[667,671,675,679],{"type":49,"tag":91,"props":668,"children":669},{"style":98},[670],{"type":55,"value":101},{"type":49,"tag":91,"props":672,"children":673},{"style":104},[674],{"type":55,"value":159},{"type":49,"tag":91,"props":676,"children":677},{"style":104},[678],{"type":55,"value":164},{"type":49,"tag":91,"props":680,"children":681},{"style":183},[682],{"type":55,"value":236},{"type":49,"tag":91,"props":684,"children":685},{"class":93,"line":121},[686,690,694,698,702,706,710,715,719],{"type":49,"tag":91,"props":687,"children":688},{"style":104},[689],{"type":55,"value":519},{"type":49,"tag":91,"props":691,"children":692},{"style":172},[693],{"type":55,"value":175},{"type":49,"tag":91,"props":695,"children":696},{"style":104},[697],{"type":55,"value":180},{"type":49,"tag":91,"props":699,"children":700},{"style":183},[701],{"type":55,"value":186},{"type":49,"tag":91,"props":703,"children":704},{"style":104},[705],{"type":55,"value":191},{"type":49,"tag":91,"props":707,"children":708},{"style":183},[709],{"type":55,"value":186},{"type":49,"tag":91,"props":711,"children":712},{"style":104},[713],{"type":55,"value":714}," @usr.email:user@example.com",{"type":49,"tag":91,"props":716,"children":717},{"style":172},[718],{"type":55,"value":200},{"type":49,"tag":91,"props":720,"children":721},{"style":183},[722],{"type":55,"value":236},{"type":49,"tag":91,"props":724,"children":725},{"class":93,"line":262},[726,730,734,738,742,746,750],{"type":49,"tag":91,"props":727,"children":728},{"style":104},[729],{"type":55,"value":560},{"type":49,"tag":91,"props":731,"children":732},{"style":104},[733],{"type":55,"value":410},{"type":49,"tag":91,"props":735,"children":736},{"style":104},[737],{"type":55,"value":215},{"type":49,"tag":91,"props":739,"children":740},{"style":218},[741],{"type":55,"value":221},{"type":49,"tag":91,"props":743,"children":744},{"style":104},[745],{"type":55,"value":226},{"type":49,"tag":91,"props":747,"children":748},{"style":104},[749],{"type":55,"value":231},{"type":49,"tag":91,"props":751,"children":752},{"style":183},[753],{"type":55,"value":236},{"type":49,"tag":91,"props":755,"children":756},{"class":93,"line":271},[757,761,765,769],{"type":49,"tag":91,"props":758,"children":759},{"style":172},[760],{"type":55,"value":244},{"type":49,"tag":91,"props":762,"children":763},{"style":98},[764],{"type":55,"value":249},{"type":49,"tag":91,"props":766,"children":767},{"style":172},[768],{"type":55,"value":254},{"type":49,"tag":91,"props":770,"children":771},{"style":104},[772],{"type":55,"value":259},{"type":49,"tag":91,"props":774,"children":775},{"class":93,"line":280},[776],{"type":49,"tag":91,"props":777,"children":778},{"style":104},[779],{"type":55,"value":268},{"type":49,"tag":91,"props":781,"children":782},{"class":93,"line":289},[783],{"type":49,"tag":91,"props":784,"children":785},{"style":104},[786],{"type":55,"value":295},{"type":49,"tag":91,"props":788,"children":789},{"class":93,"line":298},[790],{"type":49,"tag":91,"props":791,"children":792},{"style":104},[793],{"type":55,"value":304},{"type":49,"tag":91,"props":795,"children":796},{"class":93,"line":307},[797],{"type":49,"tag":91,"props":798,"children":799},{"style":104},[800],{"type":55,"value":639},{"type":49,"tag":91,"props":802,"children":803},{"class":93,"line":316},[804,808],{"type":49,"tag":91,"props":805,"children":806},{"style":104},[807],{"type":55,"value":340},{"type":49,"tag":91,"props":809,"children":810},{"style":172},[811],{"type":55,"value":345},{"type":49,"tag":135,"props":813,"children":815},{"id":814},"weekly-summary-report",[816],{"type":55,"value":817},"Weekly summary report",{"type":49,"tag":80,"props":819,"children":821},{"className":82,"code":820,"language":84,"meta":85,"style":85},"pup audit-logs search --query \"@evt.name:\\\"MCP Server\\\"\" --from 7d --limit 1000 -o json \\\n  | jq '{\n      total_tool_calls: (.data | length),\n      unique_users: ([.data[] | .attributes.attributes.usr.email] | unique | length),\n      top_users: (\n        [.data[] | .attributes.attributes.usr.email]\n        | group_by(.)\n        | map({user: .[0], calls: length})\n        | sort_by(-.calls)\n        | .[:5]\n      ),\n      actions_breakdown: (\n        [.data[] | .attributes.attributes.action]\n        | group_by(.)\n        | map({action: .[0], count: length})\n        | sort_by(-.count)\n      ),\n      resource_types: (\n        [.data[] | .attributes.attributes.asset.type]\n        | group_by(.)\n        | map({type: .[0], count: length})\n        | sort_by(-.count)\n      )\n    }'\n",[822],{"type":49,"tag":64,"props":823,"children":824},{"__ignoreMap":85},[825,896,916,924,932,940,948,956,964,972,980,988,997,1006,1014,1023,1032,1040,1049,1057,1065,1074,1082,1091],{"type":49,"tag":91,"props":826,"children":827},{"class":93,"line":94},[828,832,836,840,844,848,852,856,860,864,868,872,876,880,884,888,892],{"type":49,"tag":91,"props":829,"children":830},{"style":98},[831],{"type":55,"value":101},{"type":49,"tag":91,"props":833,"children":834},{"style":104},[835],{"type":55,"value":159},{"type":49,"tag":91,"props":837,"children":838},{"style":104},[839],{"type":55,"value":164},{"type":49,"tag":91,"props":841,"children":842},{"style":104},[843],{"type":55,"value":169},{"type":49,"tag":91,"props":845,"children":846},{"style":172},[847],{"type":55,"value":175},{"type":49,"tag":91,"props":849,"children":850},{"style":104},[851],{"type":55,"value":180},{"type":49,"tag":91,"props":853,"children":854},{"style":183},[855],{"type":55,"value":186},{"type":49,"tag":91,"props":857,"children":858},{"style":104},[859],{"type":55,"value":191},{"type":49,"tag":91,"props":861,"children":862},{"style":183},[863],{"type":55,"value":186},{"type":49,"tag":91,"props":865,"children":866},{"style":172},[867],{"type":55,"value":200},{"type":49,"tag":91,"props":869,"children":870},{"style":104},[871],{"type":55,"value":205},{"type":49,"tag":91,"props":873,"children":874},{"style":104},[875],{"type":55,"value":210},{"type":49,"tag":91,"props":877,"children":878},{"style":104},[879],{"type":55,"value":215},{"type":49,"tag":91,"props":881,"children":882},{"style":218},[883],{"type":55,"value":419},{"type":49,"tag":91,"props":885,"children":886},{"style":104},[887],{"type":55,"value":226},{"type":49,"tag":91,"props":889,"children":890},{"style":104},[891],{"type":55,"value":231},{"type":49,"tag":91,"props":893,"children":894},{"style":183},[895],{"type":55,"value":236},{"type":49,"tag":91,"props":897,"children":898},{"class":93,"line":121},[899,903,907,911],{"type":49,"tag":91,"props":900,"children":901},{"style":172},[902],{"type":55,"value":244},{"type":49,"tag":91,"props":904,"children":905},{"style":98},[906],{"type":55,"value":249},{"type":49,"tag":91,"props":908,"children":909},{"style":172},[910],{"type":55,"value":254},{"type":49,"tag":91,"props":912,"children":913},{"style":104},[914],{"type":55,"value":915},"{\n",{"type":49,"tag":91,"props":917,"children":918},{"class":93,"line":262},[919],{"type":49,"tag":91,"props":920,"children":921},{"style":104},[922],{"type":55,"value":923},"      total_tool_calls: (.data | length),\n",{"type":49,"tag":91,"props":925,"children":926},{"class":93,"line":271},[927],{"type":49,"tag":91,"props":928,"children":929},{"style":104},[930],{"type":55,"value":931},"      unique_users: ([.data[] | .attributes.attributes.usr.email] | unique | length),\n",{"type":49,"tag":91,"props":933,"children":934},{"class":93,"line":280},[935],{"type":49,"tag":91,"props":936,"children":937},{"style":104},[938],{"type":55,"value":939},"      top_users: (\n",{"type":49,"tag":91,"props":941,"children":942},{"class":93,"line":289},[943],{"type":49,"tag":91,"props":944,"children":945},{"style":104},[946],{"type":55,"value":947},"        [.data[] | .attributes.attributes.usr.email]\n",{"type":49,"tag":91,"props":949,"children":950},{"class":93,"line":298},[951],{"type":49,"tag":91,"props":952,"children":953},{"style":104},[954],{"type":55,"value":955},"        | group_by(.)\n",{"type":49,"tag":91,"props":957,"children":958},{"class":93,"line":307},[959],{"type":49,"tag":91,"props":960,"children":961},{"style":104},[962],{"type":55,"value":963},"        | map({user: .[0], calls: length})\n",{"type":49,"tag":91,"props":965,"children":966},{"class":93,"line":316},[967],{"type":49,"tag":91,"props":968,"children":969},{"style":104},[970],{"type":55,"value":971},"        | sort_by(-.calls)\n",{"type":49,"tag":91,"props":973,"children":974},{"class":93,"line":325},[975],{"type":49,"tag":91,"props":976,"children":977},{"style":104},[978],{"type":55,"value":979},"        | .[:5]\n",{"type":49,"tag":91,"props":981,"children":982},{"class":93,"line":334},[983],{"type":49,"tag":91,"props":984,"children":985},{"style":104},[986],{"type":55,"value":987},"      ),\n",{"type":49,"tag":91,"props":989,"children":991},{"class":93,"line":990},12,[992],{"type":49,"tag":91,"props":993,"children":994},{"style":104},[995],{"type":55,"value":996},"      actions_breakdown: (\n",{"type":49,"tag":91,"props":998,"children":1000},{"class":93,"line":999},13,[1001],{"type":49,"tag":91,"props":1002,"children":1003},{"style":104},[1004],{"type":55,"value":1005},"        [.data[] | .attributes.attributes.action]\n",{"type":49,"tag":91,"props":1007,"children":1009},{"class":93,"line":1008},14,[1010],{"type":49,"tag":91,"props":1011,"children":1012},{"style":104},[1013],{"type":55,"value":955},{"type":49,"tag":91,"props":1015,"children":1017},{"class":93,"line":1016},15,[1018],{"type":49,"tag":91,"props":1019,"children":1020},{"style":104},[1021],{"type":55,"value":1022},"        | map({action: .[0], count: length})\n",{"type":49,"tag":91,"props":1024,"children":1026},{"class":93,"line":1025},16,[1027],{"type":49,"tag":91,"props":1028,"children":1029},{"style":104},[1030],{"type":55,"value":1031},"        | sort_by(-.count)\n",{"type":49,"tag":91,"props":1033,"children":1035},{"class":93,"line":1034},17,[1036],{"type":49,"tag":91,"props":1037,"children":1038},{"style":104},[1039],{"type":55,"value":987},{"type":49,"tag":91,"props":1041,"children":1043},{"class":93,"line":1042},18,[1044],{"type":49,"tag":91,"props":1045,"children":1046},{"style":104},[1047],{"type":55,"value":1048},"      resource_types: (\n",{"type":49,"tag":91,"props":1050,"children":1051},{"class":93,"line":32},[1052],{"type":49,"tag":91,"props":1053,"children":1054},{"style":104},[1055],{"type":55,"value":1056},"        [.data[] | .attributes.attributes.asset.type]\n",{"type":49,"tag":91,"props":1058,"children":1060},{"class":93,"line":1059},20,[1061],{"type":49,"tag":91,"props":1062,"children":1063},{"style":104},[1064],{"type":55,"value":955},{"type":49,"tag":91,"props":1066,"children":1068},{"class":93,"line":1067},21,[1069],{"type":49,"tag":91,"props":1070,"children":1071},{"style":104},[1072],{"type":55,"value":1073},"        | map({type: .[0], count: length})\n",{"type":49,"tag":91,"props":1075,"children":1077},{"class":93,"line":1076},22,[1078],{"type":49,"tag":91,"props":1079,"children":1080},{"style":104},[1081],{"type":55,"value":1031},{"type":49,"tag":91,"props":1083,"children":1085},{"class":93,"line":1084},23,[1086],{"type":49,"tag":91,"props":1087,"children":1088},{"style":104},[1089],{"type":55,"value":1090},"      )\n",{"type":49,"tag":91,"props":1092,"children":1094},{"class":93,"line":1093},24,[1095,1100],{"type":49,"tag":91,"props":1096,"children":1097},{"style":104},[1098],{"type":55,"value":1099},"    }",{"type":49,"tag":91,"props":1101,"children":1102},{"style":172},[1103],{"type":55,"value":345},{"type":49,"tag":73,"props":1105,"children":1107},{"id":1106},"anomaly-flags",[1108],{"type":55,"value":1109},"Anomaly Flags",{"type":49,"tag":1111,"props":1112,"children":1113},"table",{},[1114,1133],{"type":49,"tag":1115,"props":1116,"children":1117},"thead",{},[1118],{"type":49,"tag":1119,"props":1120,"children":1121},"tr",{},[1122,1128],{"type":49,"tag":1123,"props":1124,"children":1125},"th",{},[1126],{"type":55,"value":1127},"Signal",{"type":49,"tag":1123,"props":1129,"children":1130},{},[1131],{"type":55,"value":1132},"Governance concern",{"type":49,"tag":1134,"props":1135,"children":1136},"tbody",{},[1137,1159,1178,1191,1204],{"type":49,"tag":1119,"props":1138,"children":1139},{},[1140,1154],{"type":49,"tag":1141,"props":1142,"children":1143},"td",{},[1144,1146,1152],{"type":55,"value":1145},"AI performing ",{"type":49,"tag":64,"props":1147,"children":1149},{"className":1148},[],[1150],{"type":55,"value":1151},"deleted",{"type":55,"value":1153}," actions on monitors or dashboards",{"type":49,"tag":1141,"props":1155,"children":1156},{},[1157],{"type":55,"value":1158},"Review whether destructive AI operations are expected",{"type":49,"tag":1119,"props":1160,"children":1161},{},[1162,1173],{"type":49,"tag":1141,"props":1163,"children":1164},{},[1165,1167],{"type":55,"value":1166},"AI acting as ",{"type":49,"tag":64,"props":1168,"children":1170},{"className":1169},[],[1171],{"type":55,"value":1172},"SUPPORT_USER",{"type":49,"tag":1141,"props":1174,"children":1175},{},[1176],{"type":55,"value":1177},"Datadog support using AI on behalf of org",{"type":49,"tag":1119,"props":1179,"children":1180},{},[1181,1186],{"type":49,"tag":1141,"props":1182,"children":1183},{},[1184],{"type":55,"value":1185},"First-time user invoking AI tools",{"type":49,"tag":1141,"props":1187,"children":1188},{},[1189],{"type":55,"value":1190},"New user accessing AI assistant",{"type":49,"tag":1119,"props":1192,"children":1193},{},[1194,1199],{"type":49,"tag":1141,"props":1195,"children":1196},{},[1197],{"type":55,"value":1198},"High volume of tool calls in short window",{"type":49,"tag":1141,"props":1200,"children":1201},{},[1202],{"type":55,"value":1203},"Automated\u002Fbatch AI usage",{"type":49,"tag":1119,"props":1205,"children":1206},{},[1207,1212],{"type":49,"tag":1141,"props":1208,"children":1209},{},[1210],{"type":55,"value":1211},"AI accessing resources outside user's normal scope",{"type":49,"tag":1141,"props":1213,"children":1214},{},[1215],{"type":55,"value":1216},"Potential over-permissioned AI session",{"type":49,"tag":73,"props":1218,"children":1220},{"id":1219},"output-format",[1221],{"type":55,"value":1222},"Output Format",{"type":49,"tag":80,"props":1224,"children":1228},{"className":1225,"code":1227,"language":55},[1226],"language-text","AI Activity Audit — [Org] — [Date Range]\n\nTotal MCP tool calls: [N]\nUnique users: [N]\n\nTop users:\n  [user@example.com]: [N] calls\n\nActions breakdown:\n  accessed: [N]\n  modified: [N]\n  created: [N]\n  deleted: [N]\n\nResource types affected:\n  dashboard: [N]\n  monitor: [N]\n\nAnomalies:\n  [List any flagged events with timestamp, user, action, resource]\n",[1229],{"type":49,"tag":64,"props":1230,"children":1231},{"__ignoreMap":85},[1232],{"type":55,"value":1227},{"type":49,"tag":73,"props":1234,"children":1236},{"id":1235},"context",[1237],{"type":55,"value":1238},"Context",{"type":49,"tag":58,"props":1240,"children":1241},{},[1242],{"type":55,"value":1243},"This skill is most useful for:",{"type":49,"tag":1245,"props":1246,"children":1247},"ul",{},[1248,1260,1270],{"type":49,"tag":1249,"props":1250,"children":1251},"li",{},[1252,1258],{"type":49,"tag":1253,"props":1254,"children":1255},"strong",{},[1256],{"type":55,"value":1257},"Security reviews:",{"type":55,"value":1259}," Verifying AI actions were authorized and within expected scope",{"type":49,"tag":1249,"props":1261,"children":1262},{},[1263,1268],{"type":49,"tag":1253,"props":1264,"children":1265},{},[1266],{"type":55,"value":1267},"Compliance audits:",{"type":55,"value":1269}," Demonstrating AI activity is logged and attributable to specific users",{"type":49,"tag":1249,"props":1271,"children":1272},{},[1273,1278],{"type":49,"tag":1253,"props":1274,"children":1275},{},[1276],{"type":55,"value":1277},"Governance reports:",{"type":55,"value":1279}," Understanding adoption and risk surface of the AI assistant across the org",{"type":49,"tag":58,"props":1281,"children":1282},{},[1283],{"type":55,"value":1284},"No other observability vendor audits their AI assistant's actions at this level of detail.",{"type":49,"tag":73,"props":1286,"children":1288},{"id":1287},"references",[1289],{"type":55,"value":1290},"References",{"type":49,"tag":1245,"props":1292,"children":1293},{},[1294,1306,1316],{"type":49,"tag":1249,"props":1295,"children":1296},{},[1297],{"type":49,"tag":1298,"props":1299,"children":1303},"a",{"href":1300,"rel":1301},"https:\u002F\u002Fdocs.datadoghq.com\u002Fbits_ai\u002F",[1302],"nofollow",[1304],{"type":55,"value":1305},"Bits AI SRE documentation",{"type":49,"tag":1249,"props":1307,"children":1308},{},[1309],{"type":49,"tag":1298,"props":1310,"children":1313},{"href":1311,"rel":1312},"https:\u002F\u002Fdocs.datadoghq.com\u002Faccount_management\u002Faudit_trail\u002Fevents\u002F",[1302],[1314],{"type":55,"value":1315},"Audit Trail events — Bits AI SRE category",{"type":49,"tag":1249,"props":1317,"children":1318},{},[1319],{"type":49,"tag":1298,"props":1320,"children":1323},{"href":1321,"rel":1322},"https:\u002F\u002Fdocs.datadoghq.com\u002Fbits_ai\u002Fmcp_server\u002F",[1302],[1324],{"type":55,"value":1325},"MCP Server setup",{"type":49,"tag":1327,"props":1328,"children":1329},"style",{},[1330],{"type":55,"value":1331},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":1333,"total":1509},[1334,1351,1369,1380,1394,1408,1424,1438,1450,1462,1474,1494],{"slug":1335,"name":1335,"fn":1336,"description":1337,"org":1338,"tags":1339,"stars":28,"repoUrl":29,"updatedAt":1350},"agent-install","install Datadog Agent on Kubernetes","Install the Datadog Agent on Kubernetes using the Datadog Operator — required before enabling Single Step Instrumentation (SSI), which automatically instruments applications for APM without code changes. Only use if no Datadog Agent is deployed on the cluster yet.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1340,1341,1344,1347],{"name":20,"slug":21,"type":15},{"name":1342,"slug":1343,"type":15},"Deployment","deployment",{"name":1345,"slug":1346,"type":15},"Kubernetes","kubernetes",{"name":1348,"slug":1349,"type":15},"Observability","observability","2026-04-15T04:57:27.489805",{"slug":1352,"name":1352,"fn":1353,"description":1354,"org":1355,"tags":1356,"stars":28,"repoUrl":29,"updatedAt":1368},"agent-observability-auto-experiment","run iterative code improvements using Datadog data","Run an iterative code-improvement hill-climb against real Datadog LLM-Obs data, locally, with Claude Code as the agent. Establishes a baseline eval, makes one focused change, re-scores with the same harness, keeps the change if it improves the score in the goal's direction (labeling within-noise gains tentative), and repeats. Use when the user says \"run an auto experiment\", \"hill-climb this code\", \"iteratively improve X and measure the delta\", \"optimize this prompt\u002Ffile against my traces\", \"auto-optimize against LLM-Obs\", or wants the local equivalent of the auto_experiments worker. Works from a local dataset file, an ml_app, a dataset_id, or a list of trace_ids.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1357,1358,1361,1364,1367],{"name":20,"slug":21,"type":15},{"name":1359,"slug":1360,"type":15},"Debugging","debugging",{"name":1362,"slug":1363,"type":15},"Evals","evals",{"name":1365,"slug":1366,"type":15},"LLM","llm",{"name":1348,"slug":1349,"type":15},"2026-07-31T05:52:13.711906",{"slug":1370,"name":1370,"fn":1371,"description":1372,"org":1373,"tags":1374,"stars":28,"repoUrl":29,"updatedAt":1379},"agent-observability-eval-bootstrap","bootstrap evaluators from production traces","Bootstrap evaluators from production traces — by default propose online LLM-judge evaluators and, after you confirm, create them in Datadog as disabled drafts (never auto-enabled); on request emit Python SDK code or a framework-agnostic JSON spec instead. Use when user says \"bootstrap evaluators\", \"generate evaluators\", \"create evals from traces\", \"eval bootstrap\", \"write evaluators\", \"build eval suite\", \"publish evaluators\", or wants to generate BaseEvaluator\u002FLLMJudge code or online judge configs from production LLM trace data. Works with ml_app and optional RCA report or failure hypothesis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1375,1376,1377,1378],{"name":20,"slug":21,"type":15},{"name":1362,"slug":1363,"type":15},{"name":1365,"slug":1366,"type":15},{"name":1348,"slug":1349,"type":15},"2026-06-19T09:04:19.259734",{"slug":1381,"name":1381,"fn":1382,"description":1383,"org":1384,"tags":1385,"stars":28,"repoUrl":29,"updatedAt":1393},"agent-observability-eval-pipeline","run agent observability and evaluation pipelines","End-to-end Agent Observability pipeline for an instrumented ml_app — classify production traces, root-cause failures, bootstrap evaluators, then (optionally) sample + publish a dataset, generate + run an experiment, and analyze results. Six narrated phases with a standardized banner and a \"continue\" checkpoint between each. Pure orchestration over the agent-observability sub-skills (`agent-observability-session-classify`, `agent-observability-trace-rca`, `agent-observability-eval-bootstrap`, `agent-observability-experiment-py-bootstrap`, `agent-observability-experiment-analyzer`). Use when user says \"run the eval pipeline\", \"go from traces to evals\", \"bootstrap evals end to end\", \"classify then RCA then bootstrap\", \"build an eval set from scratch\", \"onboard me to datasets and experiments\", \"walk me through experiments\", \"I have an ml_app, now what\", \"Agent Observability onboarding\", \"guided experiment setup\", \"from traces to experiments\", or wants a deterministic, narrated tour from production data through evaluators, datasets, and experiments. Stop early with `--stop-after \u003Cphase>` to short-circuit at evaluators or dataset, or resume mid-flow with `--start-at \u003Cphase>`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1386,1387,1390,1391,1392],{"name":26,"slug":27,"type":15},{"name":1388,"slug":1389,"type":15},"Data Pipeline","data-pipeline",{"name":20,"slug":21,"type":15},{"name":1362,"slug":1363,"type":15},{"name":1348,"slug":1349,"type":15},"2026-06-19T09:04:17.231423",{"slug":1395,"name":1395,"fn":1396,"description":1397,"org":1398,"tags":1399,"stars":28,"repoUrl":29,"updatedAt":1407},"agent-observability-experiment-analyzer","analyze LLM experiment results","Analyze LLM experiment results. Handles single or comparative experiments, exploratory or Q&A modes. Use when user says \"analyze experiment\", \"compare experiments\", \"analyze against baseline\", or provides one or two experiment IDs for analysis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1400,1403,1404,1405,1406],{"name":1401,"slug":1402,"type":15},"Analytics","analytics",{"name":20,"slug":21,"type":15},{"name":1362,"slug":1363,"type":15},{"name":1365,"slug":1366,"type":15},{"name":1348,"slug":1349,"type":15},"2026-06-19T09:04:21.212498",{"slug":1409,"name":1409,"fn":1410,"description":1411,"org":1412,"tags":1413,"stars":28,"repoUrl":29,"updatedAt":1423},"agent-observability-experiment-py-bootstrap","generate Python experiment clients for LLM observability","Generates a self-contained Python experiment client that uses the ddtrace.llmobs SDK. Emits either a runnable .py script or a Jupyter .ipynb notebook matching the canonical DataDog reference notebook style. Use when the user says \"generate Python experiment\", \"write an SDK experiment\", \"create a ddtrace experiment\", \"Python notebook experiment\", \"use the Agent Observability SDK\", or has `ddtrace` installed and wants idiomatic SDK code.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1414,1415,1418,1419,1420],{"name":20,"slug":21,"type":15},{"name":1416,"slug":1417,"type":15},"Jupyter","jupyter",{"name":1365,"slug":1366,"type":15},{"name":1348,"slug":1349,"type":15},{"name":1421,"slug":1422,"type":15},"Python","python","2026-06-19T09:04:22.640384",{"slug":1425,"name":1425,"fn":1426,"description":1427,"org":1428,"tags":1429,"stars":28,"repoUrl":29,"updatedAt":1437},"agent-observability-replay-trace","iterate on LLM traces with local code","Use when a developer wants to iterate on ONE specific Agent Observability \u002F LLM Obs trace whose output they didn't like — re-running that trace against their LOCAL code, seeing a concise diff of the old vs new output, and looping (change code → replay → diff) until satisfied. Invoked as \u002Fagent-observability-replay-trace \u003Ctrace-id> [changes to test]. Signals: \"replay this trace\"; \"iterate on a trace\"; \"this trace's output is wrong, fix it and re-run\"; \"re-run trace \u003Cid> with \u003Cchange>\"; pasting a trace id from the Agent Observability UI with a description of what to fix. It fetches the trace via the datadog-llmo MCP or the pup CLI, edits code, re-runs the app to emit a NEW trace, and diffs the two — no local server, no browser. For agents traced with ddtrace \u002F LLM Obs (Python first-class), with JSON-serializable entry input. Do NOT use for: scored Experiments or the browser \"Replay\" button (that's agent-observability-replay-experiment), building an experiment from a dataset\u002FCSV, writing evaluators, root-causing failed traces, or RUM\u002FHTTP session replay.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1430,1431,1432,1433,1434],{"name":20,"slug":21,"type":15},{"name":1359,"slug":1360,"type":15},{"name":1365,"slug":1366,"type":15},{"name":1348,"slug":1349,"type":15},{"name":1435,"slug":1436,"type":15},"Tracing","tracing","2026-07-31T05:52:08.594182",{"slug":1439,"name":1439,"fn":1440,"description":1441,"org":1442,"tags":1443,"stars":28,"repoUrl":29,"updatedAt":1449},"agent-observability-session-classify","evaluate user intent satisfaction in sessions","Classify whether user intent was satisfied in a Datadog Agent Observability trace or session. Three modes: (1) session_id — classify a single CMD+I assistant session with RUM; (2) trace_id — classify a single Agent Observability trace without RUM; (3) ml_app — sample and classify multiple sessions or traces from a given LLM app. Output is compact by default (verdict + one-sentence reason). Use when evaluating satisfaction, classifying sessions\u002Ftraces, labeling data, or generating signal for agent-observability-eval-pipeline or agent-observability-trace-rca.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1444,1445,1446,1447,1448],{"name":1401,"slug":1402,"type":15},{"name":20,"slug":21,"type":15},{"name":1362,"slug":1363,"type":15},{"name":1365,"slug":1366,"type":15},{"name":1348,"slug":1349,"type":15},"2026-06-19T09:04:26.341497",{"slug":1451,"name":1451,"fn":1452,"description":1453,"org":1454,"tags":1455,"stars":28,"repoUrl":29,"updatedAt":1461},"agent-observability-trace-rca","diagnose LLM application failures from traces","Root cause analysis on production LLM traces. Diagnoses why an LLM application is failing — works from eval judge verdicts, runtime errors, or structural anomalies depending on what signals are present. Walks the span tree from symptom to root cause. Use when user says \"what's wrong with my app\", \"why is my eval failing\", \"analyze errors\", \"root cause analysis\", \"diagnose failures\", or wants to understand production failure patterns.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1456,1457,1458,1459,1460],{"name":20,"slug":21,"type":15},{"name":1359,"slug":1360,"type":15},{"name":1362,"slug":1363,"type":15},{"name":1365,"slug":1366,"type":15},{"name":1348,"slug":1349,"type":15},"2026-06-19T09:04:24.316244",{"slug":1463,"name":1463,"fn":1464,"description":1465,"org":1466,"tags":1467,"stars":28,"repoUrl":29,"updatedAt":1473},"agent-skills","use Datadog observability skills","Datadog skills for AI agents. Essential monitoring, logging, tracing and observability.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1468,1469,1472],{"name":20,"slug":21,"type":15},{"name":1470,"slug":1471,"type":15},"Monitoring","monitoring",{"name":1348,"slug":1349,"type":15},"2026-04-06T18:08:33.337476",{"slug":1475,"name":1475,"fn":1476,"description":1477,"org":1478,"tags":1479,"stars":28,"repoUrl":29,"updatedAt":1493},"datadog-app","build and manage Datadog applications","Guides developers building Datadog Apps with TypeScript, React, the @datadog\u002Fapps scaffolder, and @datadog\u002Fvite-plugin. Use when a user wants to scaffold, run, debug, upgrade, build, upload, publish, upload without publishing (draft upload), add an upload-no-publish script, set up CI\u002FCD, use OAuth or API\u002Fapplication key auth, trigger\u002Fpoll Workflow Automation, choose DDSQL or Action Catalog for backend data access, or query app datastores with DDSQL, including backend function troubleshooting.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1480,1481,1484,1487,1490],{"name":20,"slug":21,"type":15},{"name":1482,"slug":1483,"type":15},"Frontend","frontend",{"name":1485,"slug":1486,"type":15},"React","react",{"name":1488,"slug":1489,"type":15},"TypeScript","typescript",{"name":1491,"slug":1492,"type":15},"Vite","vite","2026-06-18T08:01:32.562331",{"slug":1495,"name":1495,"fn":1496,"description":1497,"org":1498,"tags":1499,"stars":28,"repoUrl":29,"updatedAt":1508},"dd-apm","query Datadog APM traces","APM - install, onboard, instrument, enable, set up, configure, traces, services, dependencies, performance analysis. Use for any request involving Datadog APM setup, instrumentation (SSI, ddtrace, agent install), or analysis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1500,1501,1504,1505],{"name":20,"slug":21,"type":15},{"name":1502,"slug":1503,"type":15},"Distributed Tracing","distributed-tracing",{"name":1348,"slug":1349,"type":15},{"name":1506,"slug":1507,"type":15},"Performance","performance","2026-04-06T18:08:34.575282",35,{"items":1511,"total":1566},[1512,1519,1527,1534,1542,1550,1558],{"slug":1335,"name":1335,"fn":1336,"description":1337,"org":1513,"tags":1514,"stars":28,"repoUrl":29,"updatedAt":1350},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1515,1516,1517,1518],{"name":20,"slug":21,"type":15},{"name":1342,"slug":1343,"type":15},{"name":1345,"slug":1346,"type":15},{"name":1348,"slug":1349,"type":15},{"slug":1352,"name":1352,"fn":1353,"description":1354,"org":1520,"tags":1521,"stars":28,"repoUrl":29,"updatedAt":1368},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1522,1523,1524,1525,1526],{"name":20,"slug":21,"type":15},{"name":1359,"slug":1360,"type":15},{"name":1362,"slug":1363,"type":15},{"name":1365,"slug":1366,"type":15},{"name":1348,"slug":1349,"type":15},{"slug":1370,"name":1370,"fn":1371,"description":1372,"org":1528,"tags":1529,"stars":28,"repoUrl":29,"updatedAt":1379},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1530,1531,1532,1533],{"name":20,"slug":21,"type":15},{"name":1362,"slug":1363,"type":15},{"name":1365,"slug":1366,"type":15},{"name":1348,"slug":1349,"type":15},{"slug":1381,"name":1381,"fn":1382,"description":1383,"org":1535,"tags":1536,"stars":28,"repoUrl":29,"updatedAt":1393},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1537,1538,1539,1540,1541],{"name":26,"slug":27,"type":15},{"name":1388,"slug":1389,"type":15},{"name":20,"slug":21,"type":15},{"name":1362,"slug":1363,"type":15},{"name":1348,"slug":1349,"type":15},{"slug":1395,"name":1395,"fn":1396,"description":1397,"org":1543,"tags":1544,"stars":28,"repoUrl":29,"updatedAt":1407},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1545,1546,1547,1548,1549],{"name":1401,"slug":1402,"type":15},{"name":20,"slug":21,"type":15},{"name":1362,"slug":1363,"type":15},{"name":1365,"slug":1366,"type":15},{"name":1348,"slug":1349,"type":15},{"slug":1409,"name":1409,"fn":1410,"description":1411,"org":1551,"tags":1552,"stars":28,"repoUrl":29,"updatedAt":1423},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1553,1554,1555,1556,1557],{"name":20,"slug":21,"type":15},{"name":1416,"slug":1417,"type":15},{"name":1365,"slug":1366,"type":15},{"name":1348,"slug":1349,"type":15},{"name":1421,"slug":1422,"type":15},{"slug":1425,"name":1425,"fn":1426,"description":1427,"org":1559,"tags":1560,"stars":28,"repoUrl":29,"updatedAt":1437},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1561,1562,1563,1564,1565],{"name":20,"slug":21,"type":15},{"name":1359,"slug":1360,"type":15},{"name":1365,"slug":1366,"type":15},{"name":1348,"slug":1349,"type":15},{"name":1435,"slug":1436,"type":15},34]