SKINBOT for AI Agents
SKINBOT is callable by AI agents as a skin analysis and selection sub-agent: an A2A skill with a verifiable verdict.
When a universal agent, a marketplace assistant or a brand's own AI needs a skincare selection for a user, it does not need to become a skincare expert. It can delegate. The agent keeps the conversation; SKINBOT runs the skin analysis inside the session, selects from the partner's live catalog and returns a structured verdict the agent can verify before passing it on.
Why a neutral verdict matters to a calling agent
An agent that relays a recommendation inherits responsibility for it. SKINBOT is built so that responsibility is checkable: the basis of every selection is declared in the response itself.
"ranking_basis": "session skin profile + live catalog match"
"sponsored": false
"brand_weighting": "none"The calling agent can verify the basis of the selection instead of trusting a claim. SKINBOT's revenue is not coupled to any brand's outcome, so the layer is indifferent to which product wins. The selection is driven by the session's skin profile and the partner's live assortment, nothing else.
What the sub-agent does
- Runs an AI skin analysis inside the session: skin type, goals, constraints, optionally a photo signal
- Selects products from the partner's live catalog, applying inclusion and exclusion rules
- Explains every product in the selection: the user sees why each item was chosen
- Returns a structured verdict with the neutrality fields above
- Stores nothing: stateless by design, the analysis disappears with the session (aligned with GDPR, EU AI Act, 152-FZ and UAE PDPL expectations by construction)
Discovery and status
Agent Card: published at /.well-known/agent-card.json
Machine-readable overview: /llms.txt
Architecture: designed for agent-to-agent delegation. The verdict engine already runs behind API, QR and iframe in live retail deployments; a JSON-RPC endpoint for direct agent calls is the next integration surface.
Integration surfaces
One engine, four doors: API for agent platforms and partner backends, QR for physical shelves, iframe for storefronts, and widget for partner apps. An agent call is the same verdict engine that already serves retail sessions, exposed to a machine caller.
FAQ
What does an AI agent get when it calls SKINBOT? A structured verdict: a skincare selection from the partner's live catalog with an explanation for each product and machine-verifiable neutrality fields in the response. The calling agent owns the conversation; SKINBOT holds the verdict.
Where is SKINBOT's Agent Card? At /.well-known/agent-card.json on SKINBOT's domains.
Does SKINBOT store user data between calls? No. SKINBOT is stateless: the skin analysis exists inside the session and disappears with it.
How does an agent platform get API access? By request: ekaterina.sh@skinbot.ru.