Conversation
A persona exploration run (Program Manager, Designer, Legal/Compliance) scored agentic-workflows guidance 4.4/5.0 but flagged three gaps: monthly compliance-policy auditing lacks explicit trigger/dedup guidance, there's no worked Program Manager digest example, and multi-scenario ad hoc evaluation output format is underspecified.
Changes
- Scheduled compliance-policy audits (
create-agentic-workflow-trigger-details.md): added a concrete example for recurring SECURITY/disclosure/policy file checks —schedule+workflow_dispatchtrigger, monthly reporting window,compliance-audit:<window-id>dedup key, grouping by policy area, andnoop/escalation rules. - Program Manager digest example (
github-agentic-workflows.md): added a full YAML snippet usingschedule+create-issuewithclose-older-issues: true, plus the reporting window (7 days), grouping dimensions (team/repo → status), and dedup key format (pm-digest:<window-id>). - Multi-scenario ad hoc evaluation output (
create-agentic-workflow.md): replaced the ambiguous "one table per scenario" instruction with an explicit combined comparison table (one row per scenario, filled with representative values instead of placeholders) so trigger/tool/safe-output choices can be compared side by side, plus a reminder to flag scenarios that could share a trigger or write path before offering to generate files.
Example of the new combined comparison table format:
| Scenario | Trigger | Scope | Read tools | Safe outputs | Permissions | Noop condition |
|---|---|---|---|---|---|---|
| Information Worker — weekly digest | schedule + workflow_dispatch |
7-day window, grouped by assignee | github (gh-proxy) |
create-issue with close-older-issues: true |
contents: read, issues: write |
window has no assigned issues/PRs |
| Backend Engineer — API contract review | pull_request with paths: |
per-PR, no window | github (gh-proxy) |
add-comment on the PR |
contents: read, pull-requests: write |
no API contract files changed |
All changes are documentation-only, under .github/aw/, not .github/workflows/, so no workflow recompilation is required.
Closed
Copilot
AI
changed the title
[WIP] Explore agent persona findings for compliance auditing
Fill documentation gaps found by Agent Persona Explorer run (schedule-based compliance audits, PM digests, multi-scenario comparisons)
pelikhan marked this pull request as ready for review
August 16, 2026 16:40Copilot AI balanced review requested due to automatic review settings
August 16, 2026 16:40
pelikhan deleted the copilot/agent-persona-exploration branch
August 16, 2026 16:40Copilot stopped reviewing on behalf of pelikhan due to an error
August 16, 2026 16:40Pull request overview
Note
Copilot could not run the full agentic suite for this review because it was automatically requested on a bot-authored pull request. Request a review from Copilot under Reviewers to retry with the full agentic suite. Improved support for bot-authored pull requests is coming soon.
Adds new documentation examples and clarifies expected output formatting for “agentic-workflows” scenario evaluation, especially for recurring/scheduled digests and audits.
Changes:
- Added a Program Manager weekly digest workflow example and guidance.
- Updated multi-scenario comparison guidance to require a single combined comparison table.
- Added a scheduled compliance-policy audit example with prompt guidance and dedup strategy.
| File | Description |
|---|---|
| .github/aw/github-agentic-workflows.md | Adds a concrete scheduled “Program Manager digest” YAML example and reporting guidance. |
| .github/aw/create-agentic-workflow.md | Revises the multi-scenario evaluation output format to a single combined comparison table. |
| .github/aw/create-agentic-workflow-trigger-details.md | Adds a scheduled monthly compliance-policy audit example and associated prompting/dedup guidance. |
Review details
💡 Add a code-review agent skill for context-aware, tailored reviews. Learn more in the docs.
- Files reviewed: 3/3 changed files
- Comments generated: 3
- Review effort level: Lite
Comment on lines +116 to +122
| Expected comparison output: return one combined table with one row per scenario (not a separate table per scenario), so the trigger/tool/safe-output choices can be compared side by side. Use the scenario's persona/task label as the row key and cover these columns: | ||
|
|
||
| | Scenario | Trigger | Scope | Read tools | Safe outputs | Permissions | Noop condition | | ||
| |---|---|---|---|---|---|---| | ||
| | Information Worker — weekly digest | `schedule` + `workflow_dispatch` | 7-day window, grouped by assignee | `github` (`gh-proxy`, default toolset) | `create-issue` with `close-older-issues: true` | `contents: read`, `issues: write` | window has no assigned issues/PRs | | ||
| | Product Manager — backlog triage | `schedule` + `workflow_dispatch` | recurring window, grouped by staleness bucket | `github` (`gh-proxy`, default toolset) | `create-issue` with `close-older-issues: true` | `contents: read`, `issues: write` | no items cross the staleness threshold | | ||
| | Backend Engineer — API contract review | `pull_request` with `paths:` scoped to API/schema files | per-PR, no window | `github` (`gh-proxy`, default toolset) | `add-comment` on the PR | `contents: read`, `pull-requests: write` | no API contract files changed in the PR | |
| - If a CLI/MCP invocation returns `Unknown parameter 'prompt'` (or similarly for `scenario`/`query`), that confirms freeform evaluation is unavailable through that path; fall back to conversation mode and use the recommendation pattern documented above and in [create-agentic-workflow.md](create-agentic-workflow.md#ad-hoc-evaluation-mode) instead of retrying with a different parameter name. | ||
|
|
||
| ### Program Manager digest example | ||
|
|
| ### Scheduled compliance-policy audit example | ||
|
|
||
| Monthly (or otherwise recurring) audits of policy/disclosure files use `schedule` instead of `pull_request`, since there is no single triggering PR event to react to: | ||
|
|
This was referenced
Aug 16, 2026Closed
Merged