Skip to content

docs: build an autonomous agent guide#492

Merged
bradygaster merged 1 commit intodevfrom
squad/208-autonomous-agent-guide
Mar 22, 2026
Merged

docs: build an autonomous agent guide#492
bradygaster merged 1 commit intodevfrom
squad/208-autonomous-agent-guide

Conversation

@bradygaster
Copy link
Copy Markdown
Owner

Summary

New guide at \docs/src/content/docs/guide/build-autonomous-agent.md\ showing how to build a CLI-wrapped autonomous agent pipeline using the Squad SDK.

Working as PAO (DevRel).

What's covered

  • What autonomous agents are in the Squad context
  • Project setup with Squad SDK (
    pm install @bradygaster/squad-sdk)
  • Defining agents with \defineAgent()\
  • Composing squads with \defineSquad()\
  • CLI wrapper pattern for unattended invocation (cron, CI, terminal)
  • The autonomous pipeline loop: assign → execute → coordinate → repeat
  • Coordination tools (\squad_route, \squad_decide, \squad_memory)
  • Observability with \CostTracker\ and OpenTelemetry
  • Complete working example you can copy and run

Inspired by

Brady's ask about Lori's docs agent — how to build a squad that can be wrapped in a CLI and invoked autonomously. Pattern drawn from \samples/autonomous-pipeline/.

Test sync

Updated \ est/docs-build.test.ts\ EXPECTED_GUIDES array to include \�uild-autonomous-agent. All 23 docs tests pass.

Closes #208

Create docs/src/content/docs/guide/build-autonomous-agent.md covering:
- What autonomous agents are in the Squad context
- Project setup with Squad SDK
- Defining agents with defineAgent()
- Composing squads with defineSquad()
- CLI wrapper pattern for unattended invocation
- The autonomous pipeline loop (assign → execute → coordinate → repeat)
- Coordination tools (squad_route, squad_decide, squad_memory)
- Observability with CostTracker and OpenTelemetry
- Complete working example

Update test/docs-build.test.ts EXPECTED_GUIDES to include the new page.

Closes #208

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
@bradygaster bradygaster force-pushed the squad/208-autonomous-agent-guide branch from 796cb49 to d68b203 Compare March 22, 2026 08:07
@bradygaster bradygaster merged commit b5a163f into dev Mar 22, 2026
0 of 2 checks passed
chrislomonico pushed a commit to clomonico/squad that referenced this pull request Mar 26, 2026
Session: 2026-02-24-wave-d-kickoff
Requested by: Brady

Changes:
- Logged orchestration for Hockney (PR bradygaster#487), Keaton (issues bradygaster#488bradygaster#493), Fenster (timeout fix)
- Created session log for Wave D kickoff with summary and next steps
- Merged Wave D readiness assessment from inbox into decisions.md
- Notified Cheritto, Kovash, Fortier of Wave D Batch 1 assignments via history.md updates
- Cross-agent updates: Cheritto assigned P1 UX items (bradygaster#488bradygaster#490), Kovash P2 hardening (bradygaster#491bradygaster#492), Fortier streamBuffer cleanup (bradygaster#493)

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
chrislomonico pushed a commit to clomonico/squad that referenced this pull request Mar 26, 2026
Change streamingContent from a single { agentName, content } object to a
per-agent Map<string, string> so multiple agents can stream simultaneously
without overwriting each other.

- App.tsx: state is now Map<string, string>; setStreamingContent() wraps
  the Map; new clearAgentStream() method clears a single agent's entry
- MessageStream.tsx: iterates over Map entries to render all active streams
- AgentPanel.tsx: updated prop type to Map<string, string>
- index.ts: dispatchToAgent/dispatchToCoordinator use clearAgentStream()
  instead of setStreamingContent(null); handleCancel still clears all
- Tests updated to pass Map instances instead of object literals

Closes bradygaster#492

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Doc request - how to build an autonomous agent on Squad

1 participant