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

# L5 · Capability Catalog & Agents

> The fixed menu of moves the AI is allowed to make. No free-form prompting.

export const Abstention = () => <Tooltip tip="When the AI declines to answer because it is not confident enough. In Forge this is treated as a good behavior, not a failure.">abstention</Tooltip>;

export const Capability = () => <Tooltip tip="A named, versioned, rule-bound move the AI is allowed to make. The AI cannot invent new moves on the fly.">capability</Tooltip>;

<Note>
  **In plain terms:** The AI cannot do whatever it wants. Every move it makes is a
  defined <Capability /> from a fixed, versioned catalog. There is no
  "prompt-the-model-and-see-what-happens" path anywhere in Forge.
</Note>

## What a capability is

A <Capability /> is a named, versioned, rule-bound move the AI is allowed to make.
Each one has:

* a **typed input** (for example: "here is a fuel system geometry, here are the
  candidate USCG sections")
* a **typed output** (for example: "here is the applicability assessment with
  citations")
* a **confidence threshold**
* a **risk tier**
* an **autonomy bound** (observe-only / draft-only / propose-with-review /
  execute-after-approval)

Examples: "retrieve prior similar designs," "draft a rule applicability assessment,"
"compute a clearance," "propose a material substitution."

## What agents can and cannot do

Agents in Forge string capabilities together, but they are **orchestrators over
governed capabilities, not free-form prompts.** They cannot:

* invent new capabilities at runtime
* use a capability outside its declared autonomy bound

If a task is not in the catalog, it is not doable until the catalog is extended
through a governed process. Capability changes go through a review checklist (12
points) before they ship.

## Why it is built this way

This is a structural defense against the failure mode where a model confidently
fabricates a result because nothing in the architecture would catch it. By making
every AI action the invocation of a catalog entry, behavior becomes **boxable,
auditable, and reversible.** If a capability behaves badly, it gets rolled back like
any other versioned software change, not patched at runtime with a different prompt.

## Confidence and abstention (L5.5)

Sitting just above the catalog is the confidence filter. It catches low-confidence
outputs before they reach formal verification. The posture is **"abstain over
assert."** If the agent is not confident, it asks for more context, retrieves more
sources, or routes to human review. This is <Abstention />, and it is treated as a
quality behavior with a target above 98%.

## What L5 outputs

* `capability_invocation`
* `agent_proposal`
* `structured_output`
* plus, from L5.5: `confidence_score`, `abstention_reason`, `retry_context_request`