agents

Use when coordinating multiple AI agents with Agent Relay's workflow engine and need to pick the right orchestration pattern - covers the 10 core patterns (fan-out, pipeline, hub-spoke, consensus, mesh, handoff, cascade, dag, debate, hierarchical) plus 14 specialized ones, with decision framework and accurate SDK/YAML examples.

Use when creating, updating, or reviewing a Workforce cloud persona (`persona.json`/`persona.ts` + `agent.ts`) for the current deploy/runtime shape. Covers `cloud`, `useSubscription`, integrations with scope mounting and adapter config passthrough, inputs, memory, sandbox modes, `onEvent`, top-level runtime fields, `defineAgent(...)` triggers/schedules/watch/team-dispatcher launch, provider IO via `@relayfile/relay-helpers`, production-correctness traps, vendored examples, and deploy flow. Use for requests like “create a cloud persona”, “write a deployable workforce persona”, “add integrations to a persona”, “configure GitHub materialization for a persona”, “review a workforce persona”, or “author the agent.ts handler for a workforce persona”.

Use when writing agent-relay workflows that must fully validate features end-to-end before merging. Covers the 80-to-100 pattern - going beyond "code compiles" to "feature works, tested E2E locally." Includes repair-before-failure validation gates, review-depth fresh-eyes review/fix loops with test hardening, PGlite for in-memory Postgres testing, mock sandbox patterns, test-fix-rerun loops, verify gates after every edit, and the full lifecycle from implementation through passing tests to commit.

Use when building multi-agent workflows with relay broker-sdk. Covers conversation vs pipeline coordination, WorkflowBuilder/DAG steps, agents, {{steps.X.output}} chaining, Relayfile-backed human assistance, Slack answer injection, integration subscriptions, waitFor gates, repairable verification, review-depth fresh-eyes review/fix loops with test hardening, channels, chat-native recipes, error handling, event listeners, step sizing, lead+workers teams, and parallel waves.

Use when coordinating multiple AI agents with Agent Relay's workflow engine and need to pick the right orchestration pattern - covers the 10 core patterns (fan-out, pipeline, hub-spoke, consensus, mesh, handoff, cascade, dag, debate, hierarchical) plus 14 specialized ones, with decision framework and accurate SDK/YAML examples.

Use when writing agent-relay workflows that must fully validate features end-to-end before merging. Covers the 80-to-100 pattern - going beyond "code compiles" to "feature works, tested E2E locally." Includes repair-before-failure validation gates, review-depth fresh-eyes review/fix loops with test hardening, PGlite for in-memory Postgres testing, mock sandbox patterns, test-fix-rerun loops, verify gates after every edit, and the full lifecycle from implementation through passing tests to commit.

Use when building multi-agent workflows with relay broker-sdk. Covers conversation vs pipeline coordination, WorkflowBuilder/DAG steps, agents, {{steps.X.output}} chaining, Relayfile-backed human assistance, Slack answer injection, integration subscriptions, waitFor gates, repairable verification, review-depth fresh-eyes review/fix loops with test hardening, channels, chat-native recipes, error handling, event listeners, step sizing, lead+workers teams, and parallel waves.

Create consistent, memorable visual graphics for AgentWorkforce agents in the agents repo. Use when asked to generate, design, refresh, or wire README graphics, avatars, badges, cards, banners, or visual identity assets for folders such as granola, hn-monitor, linear, repo-hygiene, review, spotify-releases, and vendor-monitor.

The canonical way to run agent-relay - self-bootstrap the broker and autonomously spawn, monitor, and coordinate a team of worker agents without human intervention. Covers infrastructure startup, agent spawning, lifecycle monitoring, CLI-first reading, and team coordination.

Use when writing Agent Relay or Ricky workflows that must loop review, fix, and validation with fresh agent context until independent signoff agents, typically Claude and Codex, both agree the work is comprehensively complete. Covers fresh-context iterations, repairable gates, dual reviewer verdict contracts, iteration-count reporting, PR signoff comments, and blocked-state handling.

The canonical way to run agent-relay - self-bootstrap the broker and autonomously spawn, monitor, and coordinate a team of worker agents without human intervention. Covers infrastructure startup, agent spawning, lifecycle monitoring, CLI-first reading, and team coordination.