{"slug": "agency-agents-needs-a-role-handoff-card-before-it-needs-more-personas", "title": "agency-agents Needs a Role Handoff Card Before It Needs More Personas", "summary": "A developer proposes adding a handoff card to the agency-agents repository, a collection of specialized AI agent roles, to track authority and responsibility transitions between roles. The handoff card would document the from/to roles, reason, evidence, unresolved items, authority level, and base revision, with rejections requiring a reason and returning ownership. The developer also outlines a research protocol to test design safety by measuring whether participants can predict tool effects before approving handoffs.", "body_md": "[ msitarzewski/agency-agents](https://github.com/msitarzewski/agency-agents) is an MIT-licensed collection of specialized AI agent roles with different personalities, processes, and deliverables. The repository is popular partly because a named role is easy to understand: frontend specialist, product manager, marketing expert.\n\nBut a convincing persona does not tell a reviewer what authority changed when work moved between roles.\n\nThe UI needs a handoff card.\n\n``` php\nRequest\n  -> Role selected\n  -> Evidence gathered\n  -> Draft produced\n  -> Handoff requested\n  -> Human or next role accepts/rejects\n```\n\nEvery transition should remain visible. Replacing one chat avatar with another is not sufficient.\n\nA handoff card should answer:\n\nExample:\n\n```\nfrom: frontend-specialist\nto: accessibility-reviewer\nreason: interaction implementation complete\nevidence:\n  - src/Dialog.tsx\n  - test/dialog.keyboard.spec.ts\nunresolved:\n  - screen-reader announcement wording\nauthority_requested: review-only\nbase_revision: 81d09a2\n```\n\nThe reviewer must be able to reject the handoff without losing prior evidence. A rejection should require a reason and return ownership to the prior role. If the underlying revision changes, mark the old handoff stale rather than silently refreshing it.\n\nGive five participants the same multi-role task and ask them to predict the next tool effect before approving a handoff. Measure:\n\nStop the session if a participant approves an action they believe is read-only when it can mutate state. That is a design safety failure, not user error.\n\nThe handoff history needs a semantic ordered list, clear headings, keyboard-operable approve/reject controls, and status text that does not depend on agent color or avatar. Announce important state changes without streaming every intermediate thought.\n\nThis is a proposed interface and research protocol. I have not evaluated the repository's user interface or tested these personas with participants. Check the current README for actual installation and role definitions.\n\nSpecialization becomes useful when responsibility moves cleanly. A persona explains style; a handoff card explains accountability.", "url": "https://wpnews.pro/news/agency-agents-needs-a-role-handoff-card-before-it-needs-more-personas", "canonical_source": "https://dev.to/haaaaaley/agency-agents-needs-a-role-handoff-card-before-it-needs-more-personas-521", "published_at": "2026-07-22 04:32:00+00:00", "updated_at": "2026-07-22 04:58:09.681537+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "developer-tools"], "entities": ["msitarzewski", "agency-agents"], "alternates": {"html": "https://wpnews.pro/news/agency-agents-needs-a-role-handoff-card-before-it-needs-more-personas", "markdown": "https://wpnews.pro/news/agency-agents-needs-a-role-handoff-card-before-it-needs-more-personas.md", "text": "https://wpnews.pro/news/agency-agents-needs-a-role-handoff-card-before-it-needs-more-personas.txt", "jsonld": "https://wpnews.pro/news/agency-agents-needs-a-role-handoff-card-before-it-needs-more-personas.jsonld"}}