[{"data":1,"prerenderedAt":910},["ShallowReactive",2],{"docs-nav":3,"docs-article-agents\u002Fchat":516},[4,17,27,44,55,67,75,82,94,106,114,122,129,135,144,153,161,169,177,189,201,211,218,227,235,244,251,258,265,272,277,289,304,314,326,335,340,347,355,361,369,376,383,392,397,405,412,420,425,431,443,453,463,470,476,484,494,501,510],{"path":5,"title":6,"description":7,"group":8,"section":6,"order":9,"tags":10,"lastUpdated":16},"\u002Fagents\u002Fagentic-crm","Agentic CRM","Research brief and build plan for an AgencyCore agentic CRM layer, rendered as an interactive page — the core operating loop, the target architecture, the typed-tool risk gateway, the proposed-actions review queue, and the four-slice MVP.","Agents",0,[11,12,13,14,15],"crm","agents","ai","architecture","research","2026-06-12",{"path":18,"title":19,"description":20,"group":8,"section":21,"order":22,"tags":23,"lastUpdated":26},"\u002Fagents\u002Fchat","Chat agent","High-level system design of the AgencyCore chat agent — core components, data flow, and the two abstractions that hold it together.","Reference",1,[12,14,24,25],"chat","system-design","2026-05-13",{"path":28,"title":29,"description":30,"group":8,"section":31,"order":32,"tags":33,"lastUpdated":43},"\u002Fagents\u002Fcompany-enrichment","Company Enrichment","The company enrichment workflow - a cache-first read in front of the company intelligence database that fills firmographic, contact and technographic facts via a fixed-order provider waterfall, and writes every resolved fact back with provenance so the first org pays once and every later search rides free.","Enrichment",2,[12,34,35,36,37,38,39,40,41,42],"workflow","enrichment","companies","waterfall","cache","intelligence-database","firmographics","provenance","sonar","2026-06-10",{"path":45,"title":46,"description":47,"group":8,"section":48,"order":9,"tags":49,"lastUpdated":54},"\u002Fagents\u002Fcompany-sonar","Company Signals","Signal-first company discovery for marketing agencies, on the Claude Agent SDK, with a global intelligence cache and deterministic composite scoring.","Company Sonar",[12,34,42,50,51,52,35,53,14],"company-search","signals","agent-sdk","scoring","2026-06-08",{"path":56,"title":57,"description":58,"group":8,"section":48,"order":22,"tags":59,"lastUpdated":66},"\u002Fagents\u002Fcompany-sonar\u002Fsignal-monitoring","Company Signals Monitoring","Realtime signal capture layer on top of the data graph. Detects hot events, scores them with a Claude managed agent against each agency's ICP, fans out alerts.",[14,51,60,61,62,63,64,65],"intel","icp","alerts","monitoring","sse","managed-agents","2026-06-09",{"path":68,"title":69,"description":70,"group":8,"section":71,"order":22,"tags":72,"lastUpdated":74},"\u002Fagents\u002Fconcepts\u002Fchat-agent-design-principles","Designing chat agents","The 2026 playbook for production chat agents that reach into internal systems via tools — context engineering, memory, tool design, when to add complexity.","Concepts",[12,14,24,73],"context-engineering","2026-05-14",{"path":76,"title":77,"description":78,"group":8,"section":71,"order":32,"tags":79,"lastUpdated":74},"\u002Fagents\u002Fconcepts\u002Fsystem-prompt-architecture","System prompt architecture","How to structure a production chat agent system prompt — eight sections, what each one does, and the rules vendors converge on.",[12,80,81],"prompt-engineering","system-prompt",{"path":83,"title":84,"description":85,"group":8,"section":84,"order":9,"tags":86,"lastUpdated":54},"\u002Fagents\u002Fenvoy","Envoy","High-level system design for the AI outreach engine — the sequence step state machine, the human-in-the-loop draft approval gate, multi-source context enrichment, and the inbox sentiment flow, rendered as an interactive page.",[12,87,88,89,90,91,92,93,14],"envoy","outreach","sales-engagement","sequences","state-machine","human-in-the-loop","nylas",{"path":95,"title":96,"description":97,"group":8,"section":98,"order":9,"tags":99,"lastUpdated":16},"\u002Fagents\u002Fheadhunter","Headhunter","The AI talent-search pipeline on one page - the production six-step design with its current-title relevance gate, and the 2.0 system design with internal-first waterfall sourcing, a pluggable source registry, automatic entity resolution, and a people intelligence graph that compounds every run.","General Search",[12,34,100,101,14,25,102,37,103,104,105],"headhunter","recruiting","multi-source","entity-resolution","people-intelligence","flywheel",{"path":107,"title":108,"description":109,"group":8,"section":21,"order":32,"tags":110,"lastUpdated":113},"\u002Fagents\u002Fpaperclip","Paperclip","Architecture deep dive into the Paperclip orchestration system.",[12,14,111,112],"orchestration","paperclip","2026-04-20",{"path":115,"title":116,"description":117,"group":8,"section":31,"order":22,"tags":118,"lastUpdated":16},"\u002Fagents\u002Fpeople-enrichment","People Enrichment","The people enrichment workflow - a cache-first read in front of the people intelligence database that fills profile, contact and employment facts via a fixed-order provider waterfall, keyed on the LinkedIn URL, and writes every resolved fact back with provenance so the first org pays once and every later search rides free. The fill step Headhunter and People Signals both call.",[12,34,35,119,37,38,39,120,41,100,121],"people","linkedin","people-sonar",{"path":123,"title":124,"description":125,"group":8,"section":126,"order":9,"tags":127,"lastUpdated":54},"\u002Fagents\u002Fpeople-sonar","People Signals","Signal-first people discovery for marketing agencies, built on the headhunter pipeline, with a composite score weighted by signal strength, source reputation, recency, and ICP fit.","People Sonar",[12,34,121,128,51,100,35,53,14],"people-search",{"path":130,"title":131,"description":132,"group":8,"section":126,"order":22,"tags":133,"lastUpdated":54},"\u002Fagents\u002Fpeople-sonar\u002Fpeople-signal-monitoring","People Signals Monitoring","Forward-looking design for the push layer that tracks known people - champions, past contacts, target-company decision-makers - and fires a warm lead the moment they change jobs, get promoted, or their company has an event.",[14,51,60,119,63,134],"warm-leads",{"path":136,"title":137,"description":138,"group":139,"section":140,"order":22,"tags":141,"lastUpdated":143},"\u002Fengineering\u002Fguides\u002Fagent-execution-stack","The Agent Execution Stack","Durable workflows over pluggable agent backends — how AgencyCore runs AI agents on Inngest over a webhook-driven Claude Managed Agents backend.","Engineering","Guides",[12,142,14,25],"inngest","2026-06-25",{"path":145,"title":146,"description":147,"group":139,"section":140,"order":9,"tags":148,"lastUpdated":143},"\u002Fengineering\u002Fguides\u002Fagent-runtime","Agent runtime","How AgencyCore runs AI agents on a provider-neutral runtime — the abstraction layer that lets us swap the agent backend, with Claude managed agents as the current provider.",[12,149,14,150,151,152,25],"runtime","anthropic","claude","providers",{"path":154,"title":155,"description":156,"group":139,"section":21,"order":157,"tags":158,"lastUpdated":160},"\u002Fengineering\u002Freference\u002Fagno-to-agent-sdk-migration","Agno → Claude Agent SDK migration","System-design spec for moving the ac-python-api workflow engine off Agno onto Anthropic's Claude Agent SDK \u002F Managed Agents, tiered by control-flow shape.",10,[12,14,159,52,65],"migration","2026-06-06",{"path":162,"title":163,"description":164,"group":139,"section":21,"order":22,"tags":165,"lastUpdated":54},"\u002Fengineering\u002Freference\u002Fcloudflare-agent-sandbox","Cloudflare agent sandbox","Cloudflare's Workers-based agent platform, evaluated as an alternative sandbox for our Agno workflows.",[12,166,167,168,159],"sandbox","cloudflare","workers",{"path":170,"title":171,"description":172,"group":139,"section":21,"order":32,"tags":173,"lastUpdated":176},"\u002Fengineering\u002Freference\u002Fvirtual-filesystem-rag","Virtual filesystem for AI assistants","How ChromaFs provides AI agents with structured file access.",[12,174,14,175],"rag","chromafs","2026-04-18",{"path":178,"title":179,"description":180,"group":181,"section":182,"order":183,"tags":184,"lastUpdated":66},"\u002Flearnings\u002Fagentic-sdlc","The agentic SDLC","How AI agents move from autocomplete to owning the loop across the software lifecycle, and why that shifts the bottleneck from coding to verification.","Learnings",null,30,[12,185,186,187,188],"sdlc","engineering","verification","review",{"path":190,"title":191,"description":192,"group":181,"section":182,"order":193,"tags":194,"lastUpdated":200},"\u002Flearnings\u002Fagi-to-asi","From AGI to ASI","What lies beyond human-level AI. The four technological pathways from AGI to artificial superintelligence, the formal ceiling that bounds them, and the six bottlenecks that could stall the climb - distilled from the DeepMind report.",50,[195,196,197,198,199],"ai-futures","asi","agi","scaling","recursive-self-improvement","2026-06-19",{"path":202,"title":203,"description":204,"group":181,"section":182,"order":205,"tags":206,"lastUpdated":66},"\u002Flearnings\u002Fai-native-company-playbook","AI native company playbook","Why AI should be the operating system your company runs on, not a tool it uses, and the concrete practices that follow - closed loops, a queryable org, software factories, and token maxing.",40,[207,208,12,209,210],"ai-native","company-building","gtm","founders",{"path":212,"title":213,"description":214,"group":181,"section":182,"order":157,"tags":215,"lastUpdated":54},"\u002Flearnings\u002Fbuying-intent-signals","Buying intent signals","How buyers leak their intent before they ever fill in a form, and how to read those signals before the window closes.",[216,51,209,217],"intent","sales",{"path":219,"title":220,"description":221,"group":181,"section":182,"order":222,"tags":223,"lastUpdated":54},"\u002Flearnings\u002Fcold-outbound-system","Cold outbound system","A high-level study of an open-source 29-skill cold email system, organized into five sequential tracks from ICP to iteration.",20,[224,225,209,226],"outbound","cold-email","systems",{"path":228,"title":229,"description":230,"group":181,"section":182,"order":231,"tags":232,"lastUpdated":234},"\u002Flearnings\u002Fswan-gtm-skills-architecture","Swan GTM skills architecture","A research note on Swan AI's foundations and maps model for GTM agents, with ASCII diagrams and ideas AgencyCore can borrow.",60,[209,12,73,233,14],"swan","2026-07-01",{"path":236,"title":237,"description":238,"group":239,"section":182,"order":240,"tags":241,"lastUpdated":43},"\u002Fmission-control\u002Fciops-agent","CIOps agent","High-level system architecture and design notes for the Mission Control CIOps agent.","Mission Control",14,[242,12,243,14],"mission-control","ciops",{"path":245,"title":246,"description":247,"group":239,"section":182,"order":248,"tags":249,"lastUpdated":43},"\u002Fmission-control\u002Fcostops-agent","CostOps agent","High-level system architecture and design notes for the Mission Control CostOps agent.",11,[242,12,250,14],"finops",{"path":252,"title":253,"description":254,"group":239,"section":182,"order":222,"tags":255,"lastUpdated":54},"\u002Fmission-control\u002Fdashboard","Dashboard","The Mission Control product UI - a dark cockpit with a fleet-nav rail, company-state grid, a working escalation queue, live ledger and a global kill switch.",[242,12,256,257],"dashboard","ui",{"path":259,"title":260,"description":261,"group":239,"section":182,"order":262,"tags":263,"lastUpdated":43},"\u002Fmission-control\u002Fproduct-analytics-agent","ProductAnalytics agent","High-level system architecture and design notes for the Mission Control ProductAnalytics agent.",13,[242,12,264,14],"product-analytics",{"path":266,"title":267,"description":268,"group":239,"section":182,"order":269,"tags":270,"lastUpdated":43},"\u002Fmission-control\u002Frevenueops-agent","RevenueOps agent","High-level system architecture and design notes for the Mission Control RevenueOps agent.",12,[242,12,271,14],"revops",{"path":273,"title":274,"description":275,"group":239,"section":182,"order":157,"tags":276,"lastUpdated":54},"\u002Fmission-control\u002Fsystem-design","System design","One screen for the whole company, watched by a guardrailed fleet of ops agents that explain, propose, act and learn overnight.",[242,12,250,14],{"path":278,"title":279,"description":280,"group":281,"section":182,"order":32,"tags":282,"lastUpdated":288},"\u002Fproduct-design\u002Fonboarding-flow","Onboarding flow","Product design for the signup wizard and how TAM building folds into it. Analyzes the flow today (account, profile, company), the gap (no ICP, empty dashboard), and the integration of a new \"who you sell to\" ICP step plus a build-and-reveal screen that lands the user on a populated, ranked list.","Product Design",[283,61,284,285,286,287],"onboarding","tam","activation","ux","user-journey","2026-06-11",{"path":290,"title":291,"description":292,"group":281,"section":182,"order":293,"tags":294,"lastUpdated":303},"\u002Fproduct-design\u002Fpricing-entitlements","Pricing tiers, entitlements and usage credits","Specification for subscription tiers with gated platform access: composable plan entitlements, a unified usage-credit currency, plan-sourced limits, per-module trials and a two-ticket delivery plan built on the Stripe billing foundation. Written for discussion; the Linear document is the canonical copy with ticket links.",3,[295,296,297,298,299,300,301,302],"pricing","entitlements","billing","credits","subscriptions","plans","seats","trials","2026-07-06",{"path":305,"title":306,"description":307,"group":281,"section":182,"order":293,"tags":308,"lastUpdated":288},"\u002Fproduct-design\u002Fsales-signals-ux","Designing Signals","Product design for the sales-signals experience in ac-frontend: the 14-type taxonomy and its color system, the anatomy of a signal card across four densities, the 0-10 lead score scale, the origin tag (sonar pull vs proactive push), the seven surfaces where signals render (launchpad, sonar app, company detail, timeline, activities, data layer, Envoy), and the interaction rules that keep them consistent.",[51,286,309,11,42,310,311,312,313],"design-system","lead-score","origin","pull","push",{"path":315,"title":316,"description":317,"group":318,"section":319,"order":320,"tags":321,"lastUpdated":43},"\u002Fproprietary-data\u002Fcrm\u002Factivities","Activities","Deep dive on crm_activities, the interaction + task log of the CRM — where it is served from, how a row is born and read, and its full schema, relationships and rules.","Proprietary data","CRM",4,[11,322,323,324,325],"activities","tasks","data-model","schema",{"path":327,"title":328,"description":329,"group":318,"section":319,"order":330,"tags":331,"lastUpdated":43},"\u002Fproprietary-data\u002Fcrm\u002Fcommunications","Communications","Deep dive on crm_communications and crm_communication_events, the unified email\u002Fcall\u002Fmessage log and its per-message engagement tracking — where it is served from, the outbound message lifecycle, and the full schema, relationships and rules.",5,[11,332,333,334,324],"communications","email","engagement",{"path":336,"title":337,"description":338,"group":318,"section":319,"order":22,"tags":339,"lastUpdated":43},"\u002Fproprietary-data\u002Fcrm\u002Fcompanies","Companies","Deep dive on crm_companies, the account record at the centre of the CRM — where it is served from, how a row is born and read, and its full schema, relationships and rules.",[11,36,324,325,14],{"path":341,"title":342,"description":343,"group":318,"section":319,"order":293,"tags":344,"lastUpdated":43},"\u002Fproprietary-data\u002Fcrm\u002Fdeals","Deals","Deep dive on the deal pipeline — crm_deals, crm_pipeline_stages and crm_pipeline_config. Where it is served from, the life of a deal, and its full schema, relationships and rules.",[11,345,346,324,325],"deals","pipeline",{"path":348,"title":349,"description":350,"group":318,"section":319,"order":351,"tags":352,"lastUpdated":43},"\u002Fproprietary-data\u002Fcrm\u002Flists","Lists","Deep dive on crm_lists and crm_list_members, the static or dynamic member collections of the CRM — where they are served from, how a list and its members come to be and are read, and their schema, relationships and rules.",6,[11,353,354,324,325],"lists","segments",{"path":356,"title":357,"description":358,"group":318,"section":319,"order":32,"tags":359,"lastUpdated":43},"\u002Fproprietary-data\u002Fcrm\u002Fpeople","People","Deep dive on crm_people, the contact record of the CRM — where it is served from, how a row is born and read, and its full schema, relationships and rules.",[11,119,360,324,325],"contacts",{"path":362,"title":363,"description":364,"group":318,"section":319,"order":365,"tags":366,"lastUpdated":43},"\u002Fproprietary-data\u002Fcrm\u002Fsaved-filters","Saved filters","Deep dive on crm_saved_filters, the named reusable filter snapshots over the company, person and signal list views — where it is served from, how a saved view is born and applied, and its full schema, relationships and rules.",8,[11,367,368,324,325],"saved-filters","views",{"path":370,"title":371,"description":372,"group":318,"section":319,"order":373,"tags":374,"lastUpdated":288},"\u002Fproprietary-data\u002Fcrm\u002Fsignals","Signals","Deep dive on the signals tables - signals, company_signals and person_signals, the CRM's sales-intelligence layer. Where signals are served from, how one is born and attached, and the full schema, relationships and rules.",7,[11,51,375,324,325],"intelligence",{"path":377,"title":378,"description":379,"group":318,"section":380,"order":22,"tags":381,"lastUpdated":43},"\u002Fproprietary-data\u002Fintelligence-databases\u002Fcompany-intelligence-database","Company Intelligence Database","Decided architecture for ENG-669, the cross-org company intelligence layer that acts as a read-through cache in front of enrichment providers, with public-facts-only privacy and provenance-tracked write-back.","Intelligence databases",[14,60,36,51,38,382],"eng-669",{"path":384,"title":385,"description":386,"group":318,"section":380,"order":320,"tags":387,"lastUpdated":288},"\u002Fproprietary-data\u002Fintelligence-databases\u002Forg-signal-feed","Org Signal Feed","The per-org activation layer on top of the shared signals store. One immutable intel_signals row fans out to many orgs through scoring (signal-type weight times ICP fit times recency decay) and materializes as ranked, tiered rows in intel_org_signal_feed - the only org-scoped, RLS-per-org table of the signal stack, the door the launchpad, inbox and digest all read through. Signals enter by two ingest classes - a user's sonar pull (ungated) or an automated push (gated by threshold plus an optional competitor-ICP check) - logged in intel_signal_ingests, and each feed row records its origin.",[14,60,51,388,53,389,390,285,391,312,313,311],"feed","decay","rls","ingest",{"path":393,"title":394,"description":395,"group":318,"section":380,"order":32,"tags":396,"lastUpdated":288},"\u002Fproprietary-data\u002Fintelligence-databases\u002Fpeople-intelligence-database","People Intelligence Database","Decided architecture for the cross-org people intelligence layer - a read-through cache in front of headhunter research and Hunter email lookups, with LinkedIn-URL identity, append-only employment edges, per-tier freshness stamps on the flat profile, shared intel_sources provenance, unified intel_signals, and a GDPR erasure path.",[14,60,119,51,38,100],{"path":398,"title":399,"description":400,"group":318,"section":380,"order":293,"tags":401,"lastUpdated":288},"\u002Fproprietary-data\u002Fintelligence-databases\u002Fsignals-intelligence-database","Signals Intelligence Database","Decided v1 architecture for the unified signal store - one polymorphic append-only intel_signals table that holds both company and person signals, with a shared taxonomy, source-ranked provenance, an intel_signal_ingests log that records which pipeline found each signal, decay at read time, and a person-to-company rollup so a champion job change surfaces on the company feed.",[14,60,51,402,389,403,388,404,41,312,313],"polymorphic","taxonomy","ingests",{"path":406,"title":407,"description":408,"group":318,"section":182,"order":9,"tags":409,"lastUpdated":16},"\u002Fproprietary-data\u002Foverview","Data Layer Overview","The AgencyCore data layer in one map - the org-scoped CRM plane in production today and the global intelligence plane designed to sit in front of it, with interactive diagrams of both, the end-to-end data flow, freshness and precedence rules, the privacy seam, and the rollout path.",[410,14,60,11,51,38,25,411],"data-layer","overview",{"path":413,"title":414,"description":415,"group":416,"section":182,"order":9,"tags":417,"lastUpdated":54},"\u002Froadmap","Roadmap - June 2026","June 2026 product plan across four themes. The spine is moving our agents onto an isolated sandbox runtime and rebuilding the core agents and workflows on it, then standing up a read-through intelligence data store and shipping the Stripe billing system. Knowledge base, assistant, and credit tracking carry into the July roadmap.","Roadmap",[418,419],"roadmap","planning",{"path":421,"title":422,"description":423,"group":416,"section":182,"order":22,"tags":424,"lastUpdated":54},"\u002Froadmap\u002Fjuly-2026","Roadmap - July 2026","July 2026 product plan across three themes, all carried over from June. Building on June's sandbox runtime, July grounds the agents in a knowledge base, launches the AI chat assistant, and meters every action with per-action credit tracking that reconciles into the Stripe billing system shipped in June.",[418,419],{"path":426,"title":427,"description":428,"group":416,"section":182,"order":32,"tags":429,"lastUpdated":234},"\u002Froadmap\u002Fjune-2026-slides","Roadmap slides - June 2026","Board-review slide deck for the June 2026 product roadmap, rendered directly from the original PPTX in the docs site.",[418,419,430],"slides",{"path":432,"title":433,"description":434,"group":435,"section":8,"order":222,"tags":436,"lastUpdated":16},"\u002Fsymphony\u002Fagents\u002Fdevops-agent","DevOps agent","Interactive design for a Slack-first Symphony DevOps agent that wraps production promotion, rollback, audit, and operational jobs behind policy gates, typed runbooks, and an auditable ledger.","Symphony",[437,438,439,440,441,442],"symphony","slack","devops","production","runbooks","operations",{"path":444,"title":445,"description":446,"group":435,"section":8,"order":157,"tags":447,"lastUpdated":16},"\u002Fsymphony\u002Fagents\u002Foncall-agent","Oncall agent","Interactive design for a Symphony oncall agent that turns Sentry incidents into rich Linear tickets, investigates with Codex, opens fix PRs, and resolves Sentry after merge.",[437,448,449,450,451,452],"sentry","linear","oncall","incident-response","codex",{"path":454,"title":455,"description":456,"group":435,"section":457,"order":157,"tags":458,"lastUpdated":16},"\u002Fsymphony\u002Fhousekeeping\u002Fcodex-vacuum","Codex vacuum","Interactive design for the Symphony housekeeping timer that checkpoints and vacuums Codex sqlite stores on the VPS.","Housekeeping",[437,459,460,452,461,462],"timed-jobs","housekeeping","sqlite","vps",{"path":464,"title":465,"description":466,"group":435,"section":457,"order":183,"tags":467,"lastUpdated":16},"\u002Fsymphony\u002Fhousekeeping\u002Fhost-cleanup","Host cleanup","Interactive design for the Symphony housekeeping timer that removes stale \u002Ftmp debris, vacuums the journal, and optionally cleans the apt package cache.",[437,459,460,462,468,469],"disk","cleanup",{"path":471,"title":472,"description":473,"group":435,"section":457,"order":222,"tags":474,"lastUpdated":16},"\u002Fsymphony\u002Fhousekeeping\u002Fworkspace-cleanup","Workspace cleanup","Interactive design for the Symphony housekeeping timer that prunes idle per-issue workspaces after their TTL.",[437,459,460,475,469,462],"workspaces",{"path":477,"title":478,"description":479,"group":435,"section":182,"order":9,"tags":480,"lastUpdated":66},"\u002Fsymphony","Symphony orchestration","How AgencyCore runs OpenAI Symphony as a long-running daemon that turns Linear tickets into isolated, autonomous Codex runs, reviewed by Claude and merged by humans. High-level workflow, system architecture, and the engineer playbook.",[437,452,449,481,111,462,482,483],"claude-review","qa","automation",{"path":485,"title":486,"description":487,"group":435,"section":488,"order":205,"tags":489,"lastUpdated":16},"\u002Fsymphony\u002Ftimed-jobs\u002Fdaily-security-agent","Daily security agent","Interactive design for a report-only Symphony timed job that reviews the last 24h of commits, scans the system for vulnerabilities, and opens focused follow-up tickets.","Timed jobs",[437,490,459,452,491,492,493],"security","semgrep","threat-model","ownership",{"path":495,"title":496,"description":497,"group":435,"section":488,"order":183,"tags":498,"lastUpdated":16},"\u002Fsymphony\u002Ftimed-jobs\u002Fdaily-sentry-triage","Daily Sentry triage","Interactive design for the Symphony timed job that performs read-only Sentry triage, deduplicates existing tracked clusters, and creates focused ENG bugs for new actionable errors.",[437,459,448,499,500,449],"observability","triage",{"path":502,"title":503,"description":504,"group":435,"section":488,"order":157,"tags":505,"lastUpdated":16},"\u002Fsymphony\u002Ftimed-jobs\u002Fnightly-local-staging-e2e","Nightly local staging E2E","Interactive design for the Symphony timed job that seeds local Supabase, runs ac-frontend Playwright E2E against the local staging stack, uploads evidence, and cleans artifacts.",[437,459,506,507,508,509],"e2e","playwright","staging","frontend",{"path":511,"title":512,"description":513,"group":435,"section":488,"order":222,"tags":514,"lastUpdated":16},"\u002Fsymphony\u002Ftimed-jobs\u002Fnightly-staging-qa","Nightly staging QA","Interactive design for the Symphony timed job that seeds a staging QA Linear issue, runs an agent-browser crawl, validates feature-map coverage, and files focused follow-up work.",[437,459,508,482,515,449],"agent-browser",{"id":517,"title":19,"body":518,"customComponent":182,"description":20,"extension":901,"group":8,"lastUpdated":26,"meta":902,"navigation":903,"order":22,"path":18,"related":904,"section":21,"seo":906,"stem":907,"tags":908,"__hash__":909},"docs\u002Fagents\u002Fchat\u002Findex.md",{"type":519,"value":520,"toc":890},"minimark",[521,526,530,537,542,553,556,591,595,601,604,608,615,621,624,669,674,677,683,690,694,700,703,707,714,721,725,747,751],[522,523,525],"h1",{"id":524},"chat-agent-system-design","Chat agent: system design",[527,528,529],"p",{},"The AgencyCore chat agent is a single-agent loop sitting behind a streaming HTTP endpoint. It receives a user message, assembles everything the model needs to see, runs a tool-using loop against an LLM, and streams the result back. This article describes the components and how a turn flows through them. Framework choices (Agno, OpenAI Responses, Supabase, Redis) are recorded in code; this is the layer above.",[527,531,532,533,536],{},"For the industry-wide playbook behind these choices — context engineering, memory split, tool design, when to add complexity — see ",[534,535,69],"a",{"href":68},".",[538,539,541],"h2",{"id":540},"core-components","Core components",[543,544,549],"pre",{"className":545,"code":547,"language":548},[546],"language-text","┌───────────────────────────────────────────────────────────────────┐\n│                          ac-frontend                              │\n│                        (SSE chat client)                          │\n└───────────────────────────────────────────────────────────────────┘\n                    │  POST \u002Fchat (stream)\n                    ▼\n┌───────────────────────────────────────────────────────────────────┐\n│  Router               auth, rate limit, idempotency               │\n│  Guardrails           input length, topic checks                  │\n├───────────────────────────────────────────────────────────────────┤\n│  Agent loop           model → tool → model → ... → final text     │\n│       │                                                           │\n│       ├─► Context builder  ────────► ChatContext (envelope)       │\n│       │                                                           │\n│       ├─► Tools            scoped CLI toolkit                     │\n│       │                                                           │\n│       └─► Tool pipeline    summarize \u002F map tool results           │\n├───────────────────────────────────────────────────────────────────┤\n│  Persistence          threads, messages, rolling summary          │\n│  Tool budget          per-thread call cap                         │\n└───────────────────────────────────────────────────────────────────┘\n        │                       │                       │\n        ▼                       ▼                       ▼\n   Supabase                 Redis                   LLM provider\n   (threads, msgs,          (budget,                (model + tool\n    summary)                 dedupe keys)            execution)\n","text",[550,551,547],"code",{"__ignoreMap":552},"",[527,554,555],{},"Three boundaries do the load-bearing work:",[557,558,559,576,585],"ul",{},[560,561,562,566,567,571,572,575],"li",{},[563,564,565],"strong",{},"Context builder"," owns ",[568,569,570],"em",{},"everything the model sees",". It has one entry point and returns a ",[550,573,574],{},"ChatContext"," envelope. Changing what reaches the model is a one-function edit.",[560,577,578,566,581,584],{},[563,579,580],{},"Tool pipeline",[568,582,583],{},"what we do with each tool result"," before it re-enters the conversation. Filtering noisy payloads happens here, not in the agent loop.",[560,586,587,590],{},[563,588,589],{},"Persistence + memory split"," keeps short-term state in the prompt and long-term state in stores the agent fetches from on demand.",[538,592,594],{"id":593},"data-flow-of-one-turn","Data flow of one turn",[543,596,599],{"className":597,"code":598,"language":548},[546],"POST \u002Fchat\n   │\n   ▼\nagent.stream_chat_response\n   │\n   ├── 1. pre-flight (concurrent)\n   │     ownership · history load · doc scope · tool-budget\n   │\n   ├── 2. persist user message\n   │\n   ├── 3. build_chat_context()  ──►  ChatContext\n   │        • load rolling summary from Supabase\n   │        • compose history tail after summary cutoff\n   │        • pre-retrieve scoped documents\n   │        • build per-turn preamble (page state, date)\n   │\n   ├── 4. stream model run\n   │        loop:  model → tool call → tool pipeline → model\n   │                                                    │\n   │                                                    ▼\n   │                                              final text (SSE)\n   │\n   ├── 5. finalize context\n   │        persist new rolling summary if history was compacted\n   │\n   └── 6. persist assistant message\n            background: usage logging, eval, escalations\n",[550,600,598],{"__ignoreMap":552},[527,602,603],{},"Step 3 is the hinge. The agent loop never assembles a prompt directly — it asks the context layer for an envelope and feeds it whole to the model. To inspect what the model saw, log the envelope.",[538,605,607],{"id":606},"context-construction","Context construction",[527,609,610,611,614],{},"The context builder is the single most important component in the system. Quality lives here. The builder assembles a layered prompt per turn — a stable cacheable prefix on top, fresh per-turn evidence near the user's question. The ",[534,612,613],{"href":68},"design principles article"," explains why this shape; the diagram below is how we implement it.",[543,616,619],{"className":617,"code":618,"language":548},[546],"┌─────────────────────────────────────────────────────────────────┐\n│  CACHEABLE PREFIX  (byte-stable across turns)                   │\n│  ┌───────────────────────────────────────────────────────────┐  │\n│  │ system prompt          context\u002Fsystem_prompt.py           │  │\n│  │   identity, scope, tool-use rules, output format          │  │\n│  │   hash-pinned · rotates only via PROMPT_VERSION bump      │  │\n│  ├───────────────────────────────────────────────────────────┤  │\n│  │ tool schema            tools.py + tool_schema_fingerprint │  │\n│  │   names, args, when-to-use docstrings                     │  │\n│  │   hash-pinned · rotates only via TOOL_VERSION bump        │  │\n│  └───────────────────────────────────────────────────────────┘  │\n│ ─────────────────── cache boundary ─────────────────────────── │\n│  FRESH PER TURN                                                 │\n│  ┌───────────────────────────────────────────────────────────┐  │\n│  │ rolling summary        context\u002Fhistory.py                 │  │\n│  │   synthetic recap of turns older than cutoff              │  │\n│  ├───────────────────────────────────────────────────────────┤  │\n│  │ history tail           context\u002Fhistory.py                 │  │\n│  │   raw messages newer than the summary cutoff              │  │\n│  ├───────────────────────────────────────────────────────────┤  │\n│  │ scoped documents       context\u002Freferences.py              │  │\n│  │   pre-retrieved RAG hits for this thread's doc scope      │  │\n│  ├───────────────────────────────────────────────────────────┤  │\n│  │ per-turn preamble      context\u002Fpreamble.py                │  │\n│  │   page state · doc scope hint · today's date              │  │\n│  │   deduped by preamble_hash if unchanged from last turn    │  │\n│  ├───────────────────────────────────────────────────────────┤  │\n│  │ user message                                              │  │\n│  └───────────────────────────────────────────────────────────┘  │\n└─────────────────────────────────────────────────────────────────┘\n                                │\n                                ▼\n                          ChatContext envelope\n",[550,620,618],{"__ignoreMap":552},[527,622,623],{},"Five rules govern the layering:",[625,626,627,633,647,653,659],"ol",{},[560,628,629,632],{},[563,630,631],{},"The cacheable prefix never varies turn to turn."," All dynamic content lives below the cache boundary. Anything that drifts into the prefix silently doubles per-turn cost across every active conversation.",[560,634,635,638,639,642,643,646],{},[563,636,637],{},"History is summarized, not truncated."," When the live window crosses ~80% of budget, the builder generates a synthetic summary and carries it on the envelope. ",[550,640,641],{},"finalize_context()"," persists it to ",[550,644,645],{},"chat_threads.summary_text"," with a cutoff timestamp. The next turn loads summary + messages newer than the cutoff — no recomputation.",[560,648,649,652],{},[563,650,651],{},"Evidence is retrieved before the model sees the turn."," Doc scope checks and RAG hits happen in pre-flight, not via a tool call. The model gets the citations as text, not as a search problem.",[560,654,655,658],{},[563,656,657],{},"The preamble is dedupe-aware."," A short hash on page state + scope lets the builder skip re-injection if nothing changed, saving tokens on quick follow-up turns.",[560,660,661,664,665,668],{},[563,662,663],{},"Token attribution is tracked."," ",[550,666,667],{},"token_breakdown"," records per-source token cost on the envelope for telemetry, so context regressions show up in dashboards instead of in customer complaints.",[670,671,673],"h3",{"id":672},"the-chatcontext-envelope","The ChatContext envelope",[527,675,676],{},"The builder's output is one dataclass passed whole to the agent loop:",[543,678,681],{"className":679,"code":680,"language":548},[546],"ChatContext\n├── agent_input            what gets handed to the model\n├── history_snapshot       (role, content) pairs for retrieval rewriting\n├── preamble               page state + doc scope (per turn)\n├── preamble_hash          short SHA, dedupes re-injection\n├── token_breakdown        per-source token estimate (telemetry)\n└── new_summary            set when this turn freshly compacted history\n",[550,682,680],{"__ignoreMap":552},[527,684,685,686,689],{},"The agent loop never assembles a prompt directly. To change what the model sees: edit ",[550,687,688],{},"build_chat_context()",". To inspect what the model saw: log the envelope.",[538,691,693],{"id":692},"memory-model","Memory model",[543,695,698],{"className":696,"code":697,"language":548},[546],"   ┌──── short-term (in prompt) ────┐    ┌──── long-term (outside model) ────┐\n   │ recent turns                   │    │ vector store: prior chats, docs   │\n   │ tool results (current loop)    │◄──►│ KV store:    user prefs, facts    │\n   │ rolling summary                │    │ Supabase:    threads + messages   │\n   └────────────────────────────────┘    └───────────────────────────────────┘\n",[550,699,697],{"__ignoreMap":552},[527,701,702],{},"The rolling summary is short-term in shape (lives in the prompt this turn) but long-lived in content (represents turns that scrolled out of the live window). Persisting it is the bridge between the two stores.",[538,704,706],{"id":705},"tool-result-hygiene","Tool result hygiene",[527,708,709,710,713],{},"When a CLI tool returns 100 rows, the raw payload would flow into history and re-cost on every follow-up turn. The tool pipeline intercepts large list responses and replaces the body with ",[550,711,712],{},"{summarized, total_count, preview: first 10, hint: \"narrow with filters\"}"," before the result re-enters context. The model keeps the signal, history stays small.",[527,715,716,717,720],{},"This is the second-most-important boundary in the system after context construction. Filtering happens once, in ",[550,718,719],{},"tool_pipeline\u002Foutput_summary.py"," — not scattered across each tool implementation.",[538,722,724],{"id":723},"what-we-deliberately-did-not-build","What we deliberately did not build",[557,726,727,737],{},[560,728,729,732,733,736],{},[563,730,731],{},"No multi-agent orchestration."," One loop with a sharp toolset handles everything we ship today. If we ever split, ",[550,734,735],{},"agent.py"," is the orchestrator boundary — the context layer stays as-is.",[560,738,739,742,743,746],{},[563,740,741],{},"No physical split of the system prompt into per-section files."," One triple-quoted string + a module-load regex emits ",[550,744,745],{},"PROMPT_SECTIONS"," for diff attribution. Splitting would have hurt review for no production payoff.",[538,748,750],{"id":749},"where-to-look-in-the-code","Where to look in the code",[752,753,754,767],"table",{},[755,756,757],"thead",{},[758,759,760,764],"tr",{},[761,762,763],"th",{},"Topic",[761,765,766],{},"File",[768,769,770,781,791,801,810,820,830,840,850,860,870,880],"tbody",{},[758,771,772,776],{},[773,774,775],"td",{},"Streaming agent loop",[773,777,778],{},[550,779,780],{},"ac-python-api\u002Fsrc\u002Fdomains\u002Fchat\u002Fagent.py",[758,782,783,786],{},[773,784,785],{},"HTTP surface",[773,787,788],{},[550,789,790],{},"ac-python-api\u002Fsrc\u002Fdomains\u002Fchat\u002Frouter.py",[758,792,793,796],{},[773,794,795],{},"Context envelope",[773,797,798],{},[550,799,800],{},"ac-python-api\u002Fsrc\u002Fdomains\u002Fchat\u002Fcontext\u002Fenvelope.py",[758,802,803,805],{},[773,804,565],{},[773,806,807],{},[550,808,809],{},"ac-python-api\u002Fsrc\u002Fdomains\u002Fchat\u002Fcontext\u002Fbuilder.py",[758,811,812,815],{},[773,813,814],{},"History + rolling summary",[773,816,817],{},[550,818,819],{},"ac-python-api\u002Fsrc\u002Fdomains\u002Fchat\u002Fcontext\u002Fhistory.py",[758,821,822,825],{},[773,823,824],{},"Per-turn preamble",[773,826,827],{},[550,828,829],{},"ac-python-api\u002Fsrc\u002Fdomains\u002Fchat\u002Fcontext\u002Fpreamble.py",[758,831,832,835],{},[773,833,834],{},"System prompt (cacheable)",[773,836,837],{},[550,838,839],{},"ac-python-api\u002Fsrc\u002Fdomains\u002Fchat\u002Fcontext\u002Fsystem_prompt.py",[758,841,842,845],{},[773,843,844],{},"Tool definitions",[773,846,847],{},[550,848,849],{},"ac-python-api\u002Fsrc\u002Fdomains\u002Fchat\u002Ftools.py",[758,851,852,855],{},[773,853,854],{},"Tool schema byte-pin",[773,856,857],{},[550,858,859],{},"ac-python-api\u002Fsrc\u002Fdomains\u002Fchat\u002Ftool_schema_fingerprint.py",[758,861,862,865],{},[773,863,864],{},"Tool result post-processing",[773,866,867],{},[550,868,869],{},"ac-python-api\u002Fsrc\u002Fdomains\u002Fchat\u002Ftool_pipeline\u002F",[758,871,872,875],{},[773,873,874],{},"Persistence",[773,876,877],{},[550,878,879],{},"ac-python-api\u002Fsrc\u002Fdomains\u002Fchat\u002Fservice.py",[758,881,882,885],{},[773,883,884],{},"Rolling summary columns",[773,886,887],{},[550,888,889],{},"ac-backend\u002Fsupabase\u002Fmigrations\u002F20260512120000_add_chat_thread_rolling_summary.sql",{"title":552,"searchDepth":32,"depth":293,"links":891},[892,893,894,897,898,899,900],{"id":540,"depth":32,"text":541},{"id":593,"depth":32,"text":594},{"id":606,"depth":32,"text":607,"children":895},[896],{"id":672,"depth":293,"text":673},{"id":692,"depth":32,"text":693},{"id":705,"depth":32,"text":706},{"id":723,"depth":32,"text":724},{"id":749,"depth":32,"text":750},"md",{},true,[905],"agents\u002Fconcepts\u002Fchat-agent-design-principles",{"title":19,"description":20},"agents\u002Fchat\u002Findex",[12,14,24,25],"-r-O7g2hX1HvbKcTvAECskOJkGRHRXgBppMAjc-zqR8",1783345923029]