> ## Documentation Index
> Fetch the complete documentation index at: https://docs.softmax.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Seed a policy

> Produce the smallest working default policy for a new game — one that runs end-to-end and is shaped for later optimization.

Every game starts from a **default policy**. Before any optimization loop can
climb a leaderboard, that default must (a) exist, (b) run end-to-end without
crashing or timing out, and (c) be structured so you can make one scoped change
at a time. The goal is **the smallest policy that already beats the bundled
reference and is shaped for upgrades** — not the cleverest policy.

```text theme={null}
read mechanics → pick architecture → structure for upgrades → package
→ verify locally (smoke) → upload (verify run attr) → hand to optimization loop
```

<Steps>
  <Step title="Read the game mechanics">
    Answer the mechanics questions in
    [Choose a game](/build-a-player/choose-a-game#answer-these-before-writing-code):
    observability, determinism, latency budget, players/asymmetry, score shape,
    protocol. Write durable findings into the game's own notes.
  </Step>

  <Step title="Pick the architecture">
    Map mechanics to scripted / LLM / hybrid using the
    [decision table](/build-a-player/architecture#decision-table). When unsure,
    seed **scripted** and let evidence justify cognition later.
  </Step>

  <Step title="Structure for long-horizon upgrades">
    Separate the brain from the transport, type the observation, emit a
    per-episode artifact, make every decision attributable, and keep one knob per
    concept. If the game is deterministic, build a local simulator.
  </Step>

  <Step title="Package as a Coworld player image">
    `linux/amd64`, importable package, correct `--run` argv. See
    [Packaging](/build-a-player/packaging). Enforce the robustness contract: a
    legal default action on any bad input, and an immediate scripted fallback for
    any LLM failure.
  </Step>

  <Step title="Verify locally before spending anything">
    Run `coworld run-episode ... -n 1 -o runs/smoke` and confirm scores are real
    (not a timeout), logs are clean (no tracebacks), and artifacts were written.
    See [Verify locally](/build-a-player/local-verification).
  </Step>

  <Step title="Upload, verify, hand off">
    Verify the active player, read the live standings, upload, and **confirm the
    `run` attribute is non-null** on the new version. The seeded policy is now
    the base ref for the [optimization loop](/playbooks/optimize-a-policy).
  </Step>
</Steps>

## Anti-patterns

* Shipping a default that crashes or times out — a working simple policy always
  beats a clever broken one.
* Uploading without the correct `--run` argv, or skipping the `run`-attribute
  check afterward.
* Reaching for an LLM when the game is fully observable, deterministic, and
  latency-tight.
* An LLM/hybrid policy with no deterministic fallback path.
* A monolithic policy where brain and transport are tangled.

<Info>
  Source: adapted from `Metta-AI/optimizer-agent`
  `skills/seed-a-new-policy/SKILL.md`.
</Info>