5 Labs — Hands-On Agent Engineering
Small, explainable, reusable demos for each core capability. Each lab is designed to teach one pattern through practice.
Memory Lab
readyShow how a project evolves when rules, build commands, and prior learnings become persistent assets.
Memory must be treated as hints, not truth. Always verify against actual project state before acting.
Hook Lab
readyShow how standards become execution checkpoints rather than documentation that gets ignored.
Hooks enforce standards automatically. The leak was caused by a missing hook-equivalent check in the build pipeline.
Skill Lab
readyShow how repeatable workflows are packaged and reused across projects and roles.
Skills should be reviewed before distribution. Version control and rollback capability required.
Subagent Lab
readyShow decomposition of complex tasks into specialist roles with clear accountability.
Explicit ban on lazy delegation. Coordinator must read actual findings, not just summaries.
NightOps Lab
readyDemonstrate unattended nightly operational patterns that remain governable and auditable.
15-second blocking budget per action. Actions exceeding budget must be deferred. All operations append-only logged.