On-page step-by-step guides
Draws a step-by-step guide directly on the page when an agent makes a tool call.
Coding / product dossier
An API that lets AI agents launch in-app step-by-step guides and see user context.
Product brief
Most in-app AI agents answer "how do I do this?" with a wall of text, because they can't see the screen. The Frigade Assist API is one tool call your existing agent makes. Frigade draws a step-by-step guide right on the page, hands the agent a plain answer when it can't, and tells it what the user is looking at. It knows your product because browser agents used it first, and it relearns every release. Works with the Vercel AI SDK or anything that can call a tool.
Why we selected it
A focused, deployable answer to a common product-agent failure mode: text-only help when users need in-context guidance. The API lets an existing agent trigger on-page walkthroughs, provides fallback answers, and returns
Product preview saved with our daily selection
Capability scan
Only capabilities supported by the product information we collected are listed here.
Draws a step-by-step guide directly on the page when an agent makes a tool call.
Hands the agent a plain answer when it cannot provide an on-page guide.
Tells the agent what the user is looking at.
Relearns every release based on product use by browser agents.
Works with the Vercel AI SDK or anything that can call a tool.
Best-fit use cases
FAQ
It is an API that lets an existing AI agent trigger in-page guides for users.
Frigade draws a step-by-step guide on the page.
It gives the agent a plain answer when it cannot.
It tells the agent what the user is looking at.
The description says it works with the Vercel AI SDK or anything that can call a tool.