By the end you'll know why Agent = Model + Harness, why models commoditize, and why Alembic is a conductor — not a fourth generic orchestrator.
The blind planning prompt opens with an anchor thesis from the harness corpus: if you're not the model, you're the harness. TerminalBench leaders don't win on bigger prompts — they win on thinner, better-engineered harnesses. Pi tops benchmarks with four tools and 200–1000 token prompts. LangChain showed the same model jumping rank 30→5 by changing harness alone.
An agent is not a chat model. It is Model + Harness: the loop, tools, state, guardrails, verification, permissions, and orchestration that turn inference into reliable work. Prompt engineering is what you ask; context engineering is what fits in the window; harness engineering is everything else that makes the system operate.
Alembic is the product name for that harness layer in the Appfy stack — repo appfy/alembic, packages @alembic/*, state at ~/.alembic/runs/<id>/. It is deliberately not a fourth copy of Droid/Claude/Kimi UIs. It is the conductor that fuses three operational primitives (Mission, Workflow, Swarm) under Loop Engineering gates.
Think of it like… an orchestra. The LLM is one instrument section — powerful, interchangeable. The harness is the conductor, score, rehearsal rules, and recording booth. Alembic holds the baton: it does not play every note, but nothing reliable happens without it.
Source: synthesis-harness-distribution/source.md embedded in PROMPT-CORPUS-EMBEDS.md. Key claims the blind agent must operationalize, not parrot: Cloud Code leak ~80% value in deterministic harness code; Terminus top-three with 1-keystroke harness; Dan (yt-156): "Without the agent harness there are no agents".
Orchestration loop · Tools + scoping · Memory · Context · State · Errors · Guardrails · Verification · Permissions · Subagents · Observability · Co-evolution. Alembic plans must map each to a concrete runtime verb — not a bibliography.
| Layer | What it is | Alembic role |
|---|---|---|
| Prompt engineering | What to ask | Unit prompts, forge grill |
| Context engineering | Window fuel | Compaction, embeds injection |
| Harness engineering | How system operates | @alembic/harness core |
| Loop engineering | Meta control plane | Prelude + Coda gates |
Alembic's existing spine — what blind plans must extend, not greenfield.
# Already implemented spine HarnessCore.start | fanout | poll | report EventBus + swimlanes Council NO_GO → abort fanout (fail-closed) CLI · HTTP+SSE · MCP read-onlyloop-engineering/SKILL.md — control plane
LEARN → ANALYZE → EXECUTE ONE → VERIFY → DECIDE Gates: Scope | Proof | Course | Publish Validator ≠ builder
alembic run --goal GOAL.md --yes ≥1 Mission-sequential segment ≥1 Workflow-script (alembic.plan.ts) ≥1 Swarm-parallel (items[] + ramp) Council GO · Proof Gate exit 0 · Validator ≠ builder Artifacts: ~/.alembic/runs/<id>/events.jsonl, wire.jsonl, review.md
Click each layer. See where commoditization stops and harness investment begins.
/missions, /workflows, /swarm UIs.