Answer: For each supported action, the automation rates its confidence as high, medium, or low. The repository's automation level sets the confidence threshold, so changes rated below it are held as suggestions and changes at or above it apply automatically. Status: Confirmed Entry: tool/github-copilot/agents-and-automation/copilot-confidence-levels Revision: 2 Digest: sha256:99ad369ee8a57ef5 (changes whenever the content changes) Timeline: Created: 2026-11-13T03:19:32Z Last changed: 2026-11-18T12:48:03Z (at or above threshold: — → apply automatically) Last verified: 2026-11-20T12:54:47Z Next check: 2026-11-21T12:54:47Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of confidence levels | high, medium, or low | [1] | 2026-11-20 below threshold | held as suggestions | [1] | 2026-11-20 at or above threshold | apply automatically | [1] | 2026-11-20 default automation level | Cautious (default) | [1] | 2026-11-20 Sources: [1] GitHub. "About rationale, confidence, and approvals for issues - GitHub Docs". https://docs.github.com/en/copilot/concepts/agent-capabilities/agent-powered-workflows-and-operations/about-automation-rationale-and-approvals Role: primary. Accessed: 2026-11-20T12:54:47Z Quote: "the automation rates its confidence as high, medium, or low" (Supports: confidence levels) Quote: "changes rated below it are held as suggestions" (Supports: below threshold) Quote: "changes at or above it apply automatically" (Supports: at or above threshold) Quote: "Cautious (default): Only high-confidence changes are applied automatically." (Supports: default automation level) Snapshot SHA-256: 82f31327dad9610ab3e81629821603daa26683030376bc6cf6aa403a171a236b (captured 2026-11-18T12:48:01Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. On this check the text of [1] was unchanged since 2026-11-18T12:48:03Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T12:54:47Z. No independent second source is configured for this entry Last successful check: 2026-11-20T12:54:47Z Last attempt: 2026-11-20T12:54:47Z Notes and limitations: Extracted automatically from a single official source (section "Confidence"). Related: https://latestn.com/tool/github-copilot/agents-and-automation/copilot-rationale-for-actions What rationale does GitHub Copilot provide for its automated issue actions? https://latestn.com/tool/github-copilot/agents-and-automation/create-add-agent-skill How do I create and add an agent skill for GitHub Copilot CLI? https://latestn.com/tool/github-copilot/agents-and-automation/create-add-skill How do I create and add a skill for GitHub Copilot? https://latestn.com/tool/github-copilot/agents-and-automation/continue-session-another-client How do I continue a GitHub Copilot agent session from another client? https://latestn.com/tool/github-copilot/agents-and-automation/control-automations-repositories How do I control automations in my repositories with GitHub Copilot? https://latestn.com/tool/github-copilot/agents-and-automation/copilot-approvals-for-issues How do approvals work for GitHub Copilot when it automates issue work? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-18T12:48:03Z | changed | at or above threshold: — → apply automatically | [1] 2026-11-18T12:48:03Z | changed | below threshold: — → held as suggestions | [1] 2026-11-18T12:48:03Z | changed | threshold behavior: changes rated below it are held as suggestions, and changes at or above it apply automatically → — | [1] 2026-11-13T03:19:32Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/github-copilot/agents-and-automation/copilot-confidence-levels/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/github-copilot/agents-and-automation/copilot-confidence-levels POST: https://latestn.com/dispute/tool/github-copilot/agents-and-automation/copilot-confidence-levels with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/github-copilot/agents-and-automation/copilot-confidence-levels?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How does GitHub Copilot determine confidence levels when working on issues? Revision 2, last verified 2026-11-20T12:54:47Z. https://latestn.com/tool/github-copilot/agents-and-automation/copilot-confidence-levels (accessed 2026-11-21T09:57:50Z). @misc{LatestN_tool_github_copilot_agents_and_automation_copilot_confidence_levels_r2, title = {How does GitHub Copilot determine confidence levels when working on issues?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/github-copilot/agents-and-automation/copilot-confidence-levels}}, note = {Revision 2; digest sha256:99ad369ee8a57ef5; last verified 2026-11-20T12:54:47Z; accessed 2026-11-21T09:57:50Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/github-copilot/agents-and-automation/copilot-confidence-levels