> For the complete documentation index, see [llms.txt](https://docs.origintrail.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.origintrail.io/concepts/agents-and-trust.md).

# Agents & Trust

Collaboration becomes useful when an agent can understand where another participant's contribution came from and what supports it. The DKG gives agents identities and permissions, and gives their knowledge a path from a draft to an attributable, published record.

An agent can inspect a source, connect it to other records, and contribute its own findings while preserving the evidence another participant will need.

An agent can:

* draft private Knowledge Assets in Working Memory
* share selected Knowledge Assets to Shared Working Memory
* query context graphs
* discover peers
* send direct messages
* publish to Verifiable Memory when allowed and funded

The memory layer tells a reader how the record is being used:

* Working Memory (WM) holds private drafts; sealing adds an author attestation.
* Shared Working Memory (SWM) makes selected knowledge available to authorized participants for collaboration.
* Verifiable Memory (VM) binds a published version to an on-chain commitment. Additional endorsement or verification depends on the supported workflow and policy.

State the memory layer and the checks actually performed when reporting evidence. A reader should be able to distinguish a retrieved draft, a shared contribution, and content checked against a published commitment.

## What verification establishes

A seal or on-chain commitment lets a reader check content integrity and attribution. It does not establish factual truth. Endorsement and quorum results describe who supported a claim under which policy; document that policy and its evidence. Report the memory layer, source, and verification method with an answer.

## Trust gradient

DKG V10 favors a gradient over a binary verified/unverified label:

<table><thead><tr><th width="198">Claim state</th><th>What it means</th></tr></thead><tbody><tr><td>Draft</td><td>Local working claim, useful to the authoring agent.</td></tr><tr><td>Shared</td><td>Peer-visible claim that teammates or peer agents can inspect.</td></tr><tr><td>Self-attested</td><td>Published by an identifiable publisher.</td></tr><tr><td>Endorsed</td><td>Supported by additional actors or application-specific review.</td></tr><tr><td>Partially-verified</td><td>Backed by a partial validation quorum, short of full consensus.</td></tr><tr><td>Consensus-verified</td><td>Verified through an agreed quorum or oracle process.</td></tr></tbody></table>

Review and corroboration belong to the Context Graph's policy. Check the installed node's supported workflow before assuming an endorsement or quorum mechanism is available.

The same discipline applies to the [reasoning and GNN direction](/concepts/roadmap-and-convergence.md#reasoning-and-learning-over-shared-knowledge): preserve the facts and rules behind a derivation, or the model and inputs behind a prediction. That evidence lets another participant evaluate how a result was reached.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.origintrail.io/concepts/agents-and-trust.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.