Build an agent (C11 / C12)
Agent Starter is the canonical developer accelerator for composing a Commerce Agent in code: define a goal, reach the registry, execute through Commerce Gateway, apply a Loop Engine–style guard, then return a recorded outcome.
C12 — Say it this way: agents use Registry to discover, Gateway to act, and Loop Engine to govern. Do not describe agents as an autonomous AI platform, agent product, or a system separate from the gateway.
Agent Starter is an example (CLI + config in the monorepo). It is not a Better Data product feature, billing SKU, or workspace module.
What you get
| Step | Surface | In this starter |
|---|
| 1 | Goal | goal.query in agent.config.json |
| 2 | Query Registry | HTTP ping to registry.endpointUrl (swap for Registry MCP JSON-RPC in production) |
| 3 | Execute via Gateway | POST to gateway.baseUrl + queryPath with bearer token (same contract as Commerce Demo / demo-gateway) |
| 4 | Loop Engine guard | Pure TypeScript policy + confidence floor (illustrative; replace with real Loop Engine APIs) |
| 5 | Return result | JSON on stdout |
Monorepo package
- Path:
packages/agent-starter
- Copy
agent.config.example.json → agent.config.json, set GATEWAY_API_TOKEN (or the env name in config), then:
cd packages/agent-starter
pnpm install
pnpm dev -- --config=agent.config.json
Configuration (minimal)
- Registry —
registry.endpointUrl + mode: "httpPing" (GET reachability). Production agents should call Registry MCP tools (@shop, gateway resolution).
- Gateway —
gateway.baseUrl, gateway.bearerTokenEnv, optional queryPath (default /api/gateway/query).
- Loop guard —
loopGuard.policy, minConfidence, blockWrites (aligned with the governed demo rail, not a live Loop Engine deployment).
