ACAgentic Craft

Hands-on

Guides

Practical walkthroughs that end in an artifact. Seed guides are complete; remaining topics stay on the editorial backlog.

Build Your First Tool-Using Agent

Hands-on HazelJS: install packages, define @Agent/@Tool, wire AgentModule or AgentRuntime, execute with budgets, and add describeAgent tests.

From Agent Demo to Production

Promote a working HazelJS demo through Agent OS: policies, HITL, durable store, contracts, recovery, governance, Inspector, and DNA.

Design an Agent Manifest

Capture HazelJS Agent DNA: exportAgentDna, bootstrapRuntimeFromDna, CLI hazel agent run, and a reviewable YAML/JSON manifest aligned with identity, skills, policy, and SLOs.

Build an Evaluation Harness

Gate HazelJS agents with @hazeljs/testing describeAgent suites and optional @hazeljs/eval golden datasets in CI.

Secure MCP Servers and Agent Tools

Threat-model HazelJS MCP and ToolRegistry surfaces: least tools, guardrails on I/O, Skillgate curation, PolicyEngine, and HITL—not model trust.

Add Human Approval Without Breaking the Run

Pause AgentRuntime with durableSuspend, notify approvers, and continue via approveAndResume without losing checkpoints.

Implement Durable Execution and Recovery

Persist AgentRuns with createDurableRunStore / SQL stores, checkpoints, worker leases, and safe resume after crashes.

Skillgate from OpenAPI to ToolRegistry

Curate REST with Skillgate.fromOpenApi, register governed skills onto ToolRegistry, review gate.report(), and optionally export MCP.

Design a Production Agent Runtime

Starter flagship guide: clone Meridian Ops and learn how App code, DNA, Store, platform, and AgentRuntime fit together for production agents on HazelJS.

Backlog

  • Design a Production Agent Runtime on HazelJS (Phase D flagship)
  • Choose Between a Workflow, Graph, and Agent Loop (HazelJS deep dive)
  • Instrument an Agent with OpenTelemetry (deep dive)
  • Memory Retention and Redaction