learn-harness-engineering

Was war die Idee?

Learn Harness Engineering > **A project-based course on building the environment, state management, verification, and control mechanisms that make AI coding agents work reliably.** Learn Harness Engineering is a course d

Warum angefangen?

Gestartet, um wiederholte Arbeit zu operationalisieren: Kontext sammeln, Entscheidungen sichtbar machen und Agentenarbeit prüfbar machen.

Warum nicht fertig?

Nicht fertig, weil Abschluss-Signale fehlen: 40 TODO/FIXME-Hinweise

Was ist heute wertvoll?

Heute wertvoll als Agent-Control-System, dokumentierte Absicht, Git-Historie

Score-Reasons

• git repo
• 40 TODO/FIXME/WIP hints
• README present
• agentized

TODO/FIXME-Auszug

• /home/smlflg/Projekte/learn-harness-engineering/README.md:105 — │ │ definition │ │ handoff note for next session │ │
• /home/smlflg/Projekte/learn-harness-engineering/README.md:120 — - **State** — Track what's been done, what's in progress, and what's next. Persisted to disk so the next session picks up exactly where the last one left off.
• /home/smlflg/Projekte/learn-harness-engineering/README.md:123 — - **Session Lifecycle** — Initialize at the start. Clean up at the end. Leave a clean restart path for the next session.
• /home/smlflg/Projekte/learn-harness-engineering/README.md:147 — you fix it again you review, not rescue
• /home/smlflg/Projekte/learn-harness-engineering/README.md:302 — | [L12](./docs/lectures/lecture-12-why-every-session-must-leave-a-clean-state/index.md) | Why must every session leave a clean state? | The next session's success depends on this s
• /home/smlflg/Projekte/learn-harness-engineering/README.md:336 — Each project's solution becomes the next project's starter.