{"schemaVersion":"0.1","generatedAt":"2026-10-09T19:36:02.770Z","entry":{"knowledgeKey":"ai-decision-accountability","kind":"question","entityKey":"agent-delegation","locale":"en","primaryQuestion":"How does MeshQu govern decisions an AI agent proposes, and can we use our own agent with it?","questionVariants":[{"question":"What is AI agent governance?"},{"question":"Does MeshQu replace our AI agent?"},{"question":"Is there a MeshQu MCP server?"},{"question":"Can our agent write the rules MeshQu applies?"}],"title":"AI agent governance, and bringing your own agent","answer":"MeshQu does not replace your agent. At the point a consequential decision is made, your agent, or the application around it, calls MeshQu. MeshQu assesses the proposed decision against the policy your organisation approved and returns a verdict with a signed Decision Receipt; your systems decide what happens next. Bring your own agent through MeshQu’s OAuth-secured MCP server or documented API. Availability is for research, evaluation and design-partner deployments.","explanation":"AI agent governance means deciding in advance what an agent may settle alone, and keeping a record of how each consequential decision it proposes was assessed. Your policy states which outcomes an agent may not settle alone. Cases outside the agent’s authority, or above a threshold, route to the right level of review, and an override or exception becomes its own linked record, with who acted and why, as your systems record it. Working with MeshQu, your agent can also turn the requirements in your source material into rules MeshQu can apply, flag what the source leaves unclear for your people to settle and ratify, check a case against the policy in force and ask questions of the decisions you have recorded. People review and ratify the rules before they are used. None of this needs an autonomous business workflow, and the decision itself can stay with your team. Qu, the assistant on this website, explains MeshQu and can help you scope a 30-minute mapping call. It cannot see your organisation’s records.","applications":[{"value":"Put a policy check, a verdict and a signed record at the point an agent proposes a consequential outcome."},{"value":"Reserve named outcomes for people, and route cases beyond an agent’s authority to the right level of review."},{"value":"Let your own agent draft rules from your source material, with people settling what is unclear and ratifying the rules before use."},{"value":"Ask questions of the decisions you have recorded, in MeshQu or through your own agent, within what your deployment records."}],"limitations":[{"value":"No named vendor integration is claimed. Bringing your own agent through the MCP server or the API is offered within research, evaluation and design-partner availability, not as a generally available service."},{"value":"MeshQu does not intercept your agent’s actions. Your systems call MeshQu and enforce the verdict."},{"value":"The receipt does not record which model, version or configuration produced a proposal. The actor identifier is supplied by your systems and is not authenticated by MeshQu."},{"value":"A receipt does not establish whether the inputs were true, whether the agent’s reasoning was sound or whether the decision was correct or fair."},{"value":"What you can ask about recorded decisions depends on what your deployment records."},{"value":"Qu, the assistant on this website, cannot see your organisation’s records."},{"value":"The supplier onboarding walkthrough is fictional. No customer production deployment is claimed."},{"value":"MeshQu is currently available for research, evaluation and design-partner deployments. Production availability and support commitments are agreed per engagement."}],"nextStep":{"label":"AI action gate recipe","href":"https://docs.meshqu.com/guides/recipes/ai-action-gate"},"claims":[{"claimKey":"agent-calls-meshqu","statement":"Your agent, or the application around it, calls MeshQu before a consequential action, and your systems enforce the verdict. MeshQu does not intercept the agent’s actions.","qualification":"Holds for the documented pre-execution pattern. Enforcement stays with the calling application."},{"claimKey":"mcp-or-api","statement":"Bring your own agent through MeshQu’s OAuth-secured MCP server or documented API.","qualification":"Stated on the MeshQu website. The public documentation does not yet describe the MCP server. Offered within research, evaluation and design-partner availability; production availability and support are agreed per engagement."},{"claimKey":"agent-drafts-humans-ratify","statement":"Your agent can draft rules from your source material and flag what the source leaves unclear. People review and ratify the rules before they are used.","qualification":"The documentation states that review, ratification and activation stay with people."},{"claimKey":"reserved-outcomes","statement":"A policy can reserve outcomes for people and send cases beyond an agent’s authority to review.","qualification":"Your systems route the case on the verdict; MeshQu does not hold or release it."},{"claimKey":"query-recorded-decisions","statement":"Recorded decisions can be listed and retrieved through the documented API.","qualification":"What can be asked depends on what a deployment records and makes available."},{"claimKey":"no-model-identity","statement":"The receipt does not identify which model, version or configuration produced a proposal.","qualification":"The actor identifier is a caller-supplied assertion. As at the 17 July 2026 register, AI-actor fields are absent from the live receipt schema."}],"statementKind":"capability","availability":"limited-pilot","evidenceStrength":"founder-reported","publicSources":[{"title":"MeshQu docs — Recipe: AI action gate","url":"https://docs.meshqu.com/guides/recipes/ai-action-gate","context":"Calling MeshQu before an agent's consequential action, with the calling runtime enforcing the verdict."},{"title":"MeshQu docs — Integration patterns","url":"https://docs.meshqu.com/guides/integration-patterns","context":"The calling application owns enforcement; MeshQu returns the verdict."},{"title":"MeshQu docs — Authoring capabilities: pending work","url":"https://docs.meshqu.com/api-reference/authoring-capabilities/list-the-pending-work-in-this-api-keys-authoring-capabilitys-scope","context":"Agent-drafted policy work stays subject to human review, ratification and activation."},{"title":"MeshQu docs — Responsible AI: Evidence and Intent","url":"https://docs.meshqu.com/concepts/responsible-ai-evidence","context":"What a Decision Receipt does and does not evidence about an AI-assisted decision."}],"revision":"9dff9e943eaf5012e7cde201733c523ece91b9460520bd5689fd6dab8b6f958b","updatedAt":"2026-10-09T11:40:10.123Z","canonicalUrl":"https://www.meshqu.com/ai-decision-governance","related":[{"key":"responsible-ai-evidence","url":"https://www.meshqu.com/knowledge/responsible-ai-evidence.json"},{"key":"actor-identity","url":"https://www.meshqu.com/knowledge/actor-identity.json"},{"key":"policy-application","url":"https://www.meshqu.com/knowledge/policy-application.json"},{"key":"what-meshqu-does","url":"https://www.meshqu.com/knowledge/what-meshqu-does.json"},{"key":"human-in-the-loop-automation","url":"https://www.meshqu.com/knowledge/human-in-the-loop-automation.json"},{"key":"decision-receipts","url":"https://www.meshqu.com/knowledge/decision-receipts.json"}]}}