Skip to main content
Before Dubot can act inside a product, it needs to know what the product can do. That knowledge comes from three inputs, each with a different level of maturity today.

Ingest

A backend crawl of a public help center. No login required. Produces the knowledge corpus.

Crawl

An in-development browser pass explores the logged-in product and produces candidate actions, page summaries, and brand styles.

Record

A person uses the product normally while the browser extension records the calls triggered by the workflow. Dubot turns the captured calls into candidate actions for review.

​
What each input produces

Recording works before any SDK is installed. The extension observes calls made during normal, logged-in product use; it does not add those calls to the action catalog automatically.

​
Record, review, and add

1

Record a real workflow

Start recording in the extension, then use the product normally. The extension captures the calls triggered by the workflow so the recording reflects the product’s actual behavior.
2

Review discovered calls

Finish the recording and inspect the candidate actions Dubot found. Choose the calls that represent useful product operations rather than adding every request indiscriminately.
3

Define the action contract

Review the method and endpoint, correct the description and assumptions, decide which inputs come from product context or the conversation, and choose which response data an agent can use.
4

Set the runtime policy

Decide whether the action can run automatically, requires confirmation, or must not be available to an agent. Add it to the catalog only after that review is complete.
Nothing captured is used blindly. A recorded call remains a candidate until a person reviews its contract and explicitly adds it to the action catalog.
Recording does not make an action agent-callable by itself. A person must review and approve each candidate before it becomes part of an agent experience.

​
Why not just record selectors

Recording learns from the product calls behind a workflow rather than relying only on selectors for visible controls. The reviewed action contract describes the operation an agent can use, while navigation is resolved separately at runtime. See How Dubot works for the runtime model.