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

# Evidence Discipline

> Myrm's default agent ships with built-in evidence discipline—it never turns failed checks, empty results, or unverified assumptions into confident claims.

# Evidence Discipline

Most AI failures are not spectacular hallucinations. More often, a plausible intermediate result gets promoted into a stronger conclusion:

* a command exits successfully, so the agent says the system is fixed;
* a file was changed, so the agent says the feature works;
* a local build passes, so the agent says the deployment is live;
* a search returns no result, so the agent says nothing exists;
* you state a premise, so the agent repeats it as independently verified fact.

Myrm's **Evidence Discipline** skill makes these failures rare by enforcing a **claim-to-evidence contract** on every answer the default agent (`builtin-economy`) produces.

## What it does

The skill separates claims by evidence type and applies a **proof obligation** scaled to how strong the claim is:

| Evidence state    | Meaning                                                                                         |
| ----------------- | ----------------------------------------------------------------------------------------------- |
| **Observed**      | The agent directly saw it via a tool, file, log, or runtime check                               |
| **Source-backed** | Backed by a named source the agent can point to                                                 |
| **User-reported** | You told the agent—repeated as your report, **not** independently verified                      |
| **Inferred**      | Reasoned from other facts, labeled as inference                                                 |
| **Unknown**       | Could not verify—stated as unknown, not papered over                                            |
| **Contradicted**  | Conflicting evidence exists—the agent preserves the uncertainty instead of forcing a conclusion |

## Safety contract

Beyond labeling evidence, the skill blocks the common ways agents quietly lie:

* **Never claim access to resources that were not actually available in the task.**
* **Never present a plan or an attempted action as an action that already happened.**
* **Never reinterpret tool errors, empty results, partial sync, or inaccessible data as successful verification.**
* **Never perform unrelated destructive actions merely to gain stronger evidence.**
* **Bound negative claims** (e.g. "nothing exists") to the surfaces actually checked.

## Built-in balance against over-caution

Evidence discipline cuts both ways, so the skill also prevents the opposite failure:

* **Don't overuse "UNKNOWN".** When evidence is reasonably available, verify it—don't use caution as an excuse to skip the check.
* **Check before you ask.** If you can inspect the evidence yourself, do it before asking the user to repeat information.

The result: an agent that is honest about what it doesn't know, actively verifies what it can, and never offloads its own homework onto you.

## How to use it

**Zero configuration.** The skill is bound by default to the built-in general agent (`builtin-economy`) and active on every conversation—including Web, scheduled tasks, and channels.

You can also:

* **View it** under **Settings → Skills** — it appears alongside other prebuilt skills.
* **Bind it to any agent** you create, or remove it from an agent that doesn't need it.
* **Give it a stronger trigger** in an agent's custom system prompt, e.g. *"Prove important claims before you answer."*

## Verification & contract tests

The skill's behavioral contract is guarded by **33 architecture contract tests** that assert every clause is present and the frontmatter version stays valid, so the skill can't silently drift or degrade. The full pipeline (sync → binding → visibility) is covered by integration tests without mocks.

## Related

* [Skill Discovery & Registry Mirror](/docs/guides/skill-discovery) — install and manage prebuilt skills
* [Skill Evolution](/docs/guides/skill-evolution) — auto-improve skills after installation
* [Layered Verification Playbook](/docs/guides/layered-verification-playbook) — architecture-level verification on top of expression-level discipline