Build, evaluate, and operate AgencyCore agents.

System design

One screen for the whole company, watched by a guardrailed fleet of ops agents that explain, propose, act and learn overnight.

CostOps agent

High-level system architecture and design notes for the Mission Control CostOps agent.

RevenueOps agent

High-level system architecture and design notes for the Mission Control RevenueOps agent.

ProductAnalytics agent

High-level system architecture and design notes for the Mission Control ProductAnalytics agent.

CIOps agent

High-level system architecture and design notes for the Mission Control CIOps agent.

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.

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 - 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.

Roadmap slides - June 2026

Board-review slide deck for the June 2026 product roadmap, rendered directly from the original PPTX in the docs site.

Company Signals

Signal-first company discovery for marketing agencies, on the Claude Agent SDK, with a global intelligence cache and deterministic composite scoring.

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.

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 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.

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.

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.

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.

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.

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.

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.

System prompt architecture

How to structure a production chat agent system prompt — eight sections, what each one does, and the rules vendors converge on.

Chat agent

High-level system design of the AgencyCore chat agent — core components, data flow, and the two abstractions that hold it together.

Paperclip

Architecture deep dive into the Paperclip orchestration system.

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.

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.

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.

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.

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.

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.

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.

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.

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.

Communications

Deep dive on crm_communications and crm_communication_events, the unified email/call/message log and its per-message engagement tracking — where it is served from, the outbound message lifecycle, and the full schema, relationships and rules.

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.

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.

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.

Agentic platform

The whole agentic platform on one page - who starts a run, the one boundary every run passes, how the work executes, and what comes back.

Mission Control

The internal Company OS. Six layers and one policy plane put a person in control of company state and of autonomous execution.

Platform contract

One platform behind chat, interactive channels, triggers, approvals and background runs, with one Agno runtime, one tool layer, one state layer, and three cross-cutting planes.

Surfaces

Every product surface and its API contract. Web chat goes through the gateway; every schema-native surface calls the domain API.

Channel gateway

The only layer that knows both an interactive channel and the platform. One message shape converges inbound, one intent shape diverges outbound, and no model call happens here.

Front door

The conversational control layer. It turns a request into one structured decision, then deterministic application code answers or hands work to RunManager.

Triggers

A Run with no person. Every producer emits one Event, matching is deterministic, and dispatch reuses RunManager, Policy and Inngest.

Agent access (CLI and MCP)

How an outside AI agent reaches AgencyCore. The ac CLI works today as a user seat. An MCP server is planned and not designed.

Agentic runtime

One Run contract, one Agno agent runtime, one deterministic workflow model, and the component boundaries that keep the framework replaceable.

Runtime definitions

Editable drafts, one published configuration per definition, template forks, deterministic validation, and the Run snapshot that keeps in flight work stable.

Runtime execution

The Run record, the Inngest step boundaries, agent segments, workflow nodes, approvals, cancellation, failure handling and live events.

Tools and integrations

A tool is the one way an agent reaches the world. AgencyCore owns the model facing contract, the invoke path, the credentials and the result boundary.

State and knowledge

What a run may know. One deterministic context builder over application state, knowledge and memory, one owner for every fact, and memory that is written through a tool.

Policy and governance

One deterministic plane answers may this happen, at three checkpoints, with one grant model, one approval model and one decision log.

Observability and operations

One run row, one span tree and one usage meter. Sentry reports system failure; AgencyCore spans explain what the agent did.

Idempotency

One durable PostgreSQL key service prevents duplicate effects and freezes mutable input before selected Run starts. A Run start is guarded by a unique index on the Run row.

Company, People and Signals contracts

The five Phase 7 product capabilities, their bounded inputs, stable references, permissions and results.

Capability design scenarios

Normal, failure and recovery cases for the Phase 7 capability contracts, with implementation owners.

Agentic CRM

The AgencyCore CRM loop for turning signals and discovery into qualified organization prospects, CRM relationships and outreach.

Signals Search

One bounded discovery workflow that finds companies, verifies signals, finds relevant people, and produces evidence-backed organization prospects without prematurely creating CRM records.

Email sequence workflow

Envoy durable outreach for one or many people, with fresh context, approvals, reply waits, follow-ups and Nylas transport.

Front door general chat

The default conversational answer path for AgencyCore. It answers from supplied context, cites what it used, asks when context is insufficient, and delegates real work through the normal Front Door.

Front door builder chat

Conversational authoring for organization-specific Agent and Workflow definitions, entered through the normal Front Door and backed by the existing DefinitionService.

Human review inbox

One product page for every agentic action that is paused because a person must authorize an exact proposal. It is a view over the shared approval primitive, not a second review system.

Workflow visualizer

One constrained workflow graph, reused to author a draft, read a published definition, and watch a Run. Build mode edits the draft; run mode overlays Run and span state on the frozen snapshot.

Experience

L6. Where a person observes and controls the company, and the one rule that keeps the UI out of the business.

Intelligence

L5. The agent is the primitive. A skill is how it works, a tool is how it reaches the world, and the two are never the same thing.

Orchestration

L4. Workflow, run, step, trigger and event. Five nouns that turn a decision into durable execution.

Company context

L3. Company state, knowledge and memory are three different things. One deterministic builder turns them into one brief.

Tools and integrations

L2. One contract for every capability. The tool is the only route to the world, and it is where policy, audit and tenancy meet.

Foundation

L1. Generic infrastructure with no business logic in it. The test is that another product could run on it unchanged.

Policy and governance

A plane, not a layer. One place decides what an agent may do, under what conditions, and how much. Human approval is one of its three answers.

Metrics and connectors

A worked example across every layer. Three vendors, one metric pipeline, three views, and the rule that decides what we store.

Company search

Implementation notes for company.search. Search resolves and gates company identities; enrichment is a separate capability.

People search

Implementation notes for people.search. Bounded company scope and persona gates return selectable person identities without enrichment.

Enrichment

Reusable company and people enrichment workflows with canonical Intelligence write-back, existing tier freshness and bounded asynchronous email.

Signals search

Superseded. The earlier on-demand buying-signal search component, kept as a record of the design that the agentic platform Signals Search workflow replaces.

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.

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.

Cloudflare agent sandbox

Cloudflare's Workers-based agent platform, evaluated as an alternative sandbox for our Agno workflows.

Virtual filesystem for AI assistants

How ChromaFs provides AI agents with structured file access.

Agno → Claude Agent SDK migration

System-design spec for moving the ac-python-api workflow engine off Agno onto Anthropic's Claude Agent SDK / Managed Agents, tiered by control-flow shape.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

Codex vacuum

Interactive design for the Symphony housekeeping timer that checkpoints and vacuums Codex sqlite stores on the VPS.

Workspace cleanup

Interactive design for the Symphony housekeeping timer that prunes idle per-issue workspaces after their TTL.

Host cleanup

Interactive design for the Symphony housekeeping timer that removes stale /tmp debris, vacuums the journal, and optionally cleans the apt package cache.

High-level design

The Symphony daemon end to end — the standing agent workforce and its label-routed workflows, then the runtime that polls, dispatches, runs and writes back.

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.

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.

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.

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.

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.

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.