OLM is designed to be legible to both humans and AI systems. Most educational frameworks are too narrative or loosely defined to constrain an LLM — programs generated from them drift, invent structure, and assert outcomes they didn't earn.

These four files give any LLM what it needs to produce content in OLM's canonical vocabulary — governed, validated, and self-contained. Drop one into Claude, ChatGPT, or any capable LLM. Nothing else needs to be fetched.

Registry v1.2 12 patterns · 21 routines · 19 artifacts 5 evidence · 9 constraints · 8 HDDs

Files

Three primary files plus a changelog. Each is a stable URL — the _latest suffix always points at the current revision. When the registry changes, all three files are republished together.

System prompt
A self-contained prompt for interactive use. Drop into any LLM as a system message (or first user message in tools without a system role). Contains the full canonical registry, layer rules, validation constraints, and output shape.
Download olm_system_prompt_latest.md →
v1.2 · markdown · ~10 KB
Context bundle
The comprehensive one-fetch bundle. Constitution summary, full registry, layer contracts, generation and validation rules, and a worked example. For agents and tools that need to reason about OLM as well as generate from it.
Download olm_context_bundle_latest.md →
v1.2 · markdown · ~17 KB
Canonical registry
Machine-readable YAML. The authoritative list of valid OLM IDs — patterns, routines, artifacts, evidence, constraints, HDDs. For validators, automated scripts, and code that checks IDs against the registry.
Download canonical_registry_latest.yaml →
v1.2 · yaml · ~3 KB

Not sure which to pick?

Three files, three jobs. Most users want the first.

  • olm_system_prompt_latest.md — you're an educator or designer who wants to use Claude or ChatGPT to draft Core Mappings or Educator Briefs from program briefs.
  • olm_context_bundle_latest.md — you're building an agent, tool, or evaluation that needs to understand OLM, not just produce content in it.
  • canonical_registry_latest.yaml — you're writing code that validates OLM packets against the canonical vocabulary.

Quick usage

The fastest path is to copy the system prompt into your LLM and send a program brief. Three steps.

Copy the system prompt

Open olm_system_prompt_latest.md and copy its contents into your LLM as a system message — or the first user message in tools without a system role.

Send a program brief

Describe the learning experience you want to design — free text, no specific structure required. Duration, audience, what learners do and produce.

Get a Core Mapping

The model returns a Core Mapping in OLM's canonical vocabulary, ready to feed into a Playbook stage or to validate against the registry. If a concept in your brief has no canonical equivalent, the model notes the gap rather than inventing an ID.

For an end-to-end interactive flow with brief input and prompt assembly, the prompt builder on the main page wraps the system prompt with a task and your brief in one click.

Programmatic use

For agents, pipelines, or scripts, fetch the files directly. URLs are stable.

# System prompt — interactive use, smallest footprint curl https://openlearningmap.org/ai/olm_system_prompt_latest.md # Context bundle — for agents and tools that reason about OLM curl https://openlearningmap.org/ai/olm_context_bundle_latest.md # Machine-readable registry — for validators and ID-checking code curl https://openlearningmap.org/ai/canonical_registry_latest.yaml

The repository at Meta-Humans/olm is the authoritative source. These files mirror canonical/canonical_registry.yaml and the AI assets on every release.

Why three files

OLM is a structural framework with a governed vocabulary. LLMs work well within it because the constraints are explicit — but only when the model can see the rules. The three primary files exist to give you three useful slices of the same source of truth.

The system prompt is the smallest workable unit. It contains the rules and registry an LLM needs to produce a Core Mapping or Playbook in canonical vocabulary, and nothing more. Use it for interactive work — pasting into a Claude or ChatGPT conversation.

The context bundle adds the constitution summary, the full layer contracts, and a worked example. It's larger, and it's the right choice when your tool or agent needs to reason about OLM rather than just generate within it. Evaluations, validators, and second-pass reviewers all benefit from the worked example.

The canonical registry YAML is the canonical list of valid IDs in a format your code can read. The repo's canonical/canonical_registry.yaml is the authoritative source; this file is its public mirror.