Use cases
Your users need an outcome, not an orchestration framework. Build the experience around the work they need to do, with Inlay underneath.
01 / Product pattern
A planning workspace that builds a useful document, not just a reply.
Bind live outputs and tables to your interface. Let the agent call your app's tools and remember user context between conversations.
Typed clients / live state / client tools
Connect an agent to your UI02 / Product pattern
A research assistant that works from a customer's own knowledge base.
Combine retrieval with web tools, assemble a structured result, and surface the supporting passages. Inspect and evaluate retrieval separately from the final prose.
Retrieval / citations / structured outputs
Build with your knowledge03 / Product pattern
An outreach draft or proposed support resolution that a person reviews.
Present a client-tool approval in your app. Reopen a saved pending decision, request a revision, and explicitly resume with the user's answer.
Client tools / saved pauses / history
Add a human review step04 / Product pattern
A recurring research brief that is ready when your user starts the day.
Schedule non-interactive agents with a timezone and user identity. Use scoped memory and inspect each resulting run. Keep interactive approval flows separate.
Schedules / memory / observability
Schedule the workThese are illustrative product patterns, not customer case studies. You supply the interface, permissions, and domain integrations. Inlay supplies the agent infrastructure underneath.
Add plans, credits, and hosted payments to your own product.
Tell us who it's for and what the agent needs to do. Inlay is in private beta, with access reviewed and onboarding handled manually.