Build an actor with the right capabilities
The Quickstart has you create a minimal actor to run one checklist. This tutorial goes further: writing instructions and knowledge that make an actor behave like a genuine member of your audience, and choosing capabilities deliberately instead of turning everything on.
Start with a persona, not a checklist
Instructions work best when they describe who the actor is standing in for, not what you want it to click. A persona has a goal, a level of product familiarity, and a tone:
You are a small business owner evaluating whether to switch invoicing software. You are price-sensitive, comfortable with software but impatient with jargon, and you will abandon a signup flow if it asks for a credit card before showing you the product.
An actor written this way makes the same kind of judgement calls a real visitor would, rather than mechanically executing steps.
Give it knowledge to draw on
Knowledge entries are the reference material an actor can pull from mid-run: facts about your product, test account credentials, brand or tone guidelines, or answers to questions it might otherwise get wrong. Add a knowledge entry for anything you would otherwise have to explain to a new team member on day one.
Keep entries short and specific. A dozen focused entries work better than one long document, since the actor only needs to draw on what's relevant to the step it's on.
Turn on only the capabilities it needs
Capabilities are opt-in toggles on the actor's page and decide what it's allowed to do:
- Use browser, drives a real browser through your product.
- Receive email, reads codes and notifications sent to the actor's inbox, useful for signup and verification flows.
- Web search, looks things up beyond your product.
- Browser context and Memory, carry state between runs.
- Code sandbox, runs and checks code.
An actor that only needs to browse your marketing site doesn't need email access, and one that never verifies an account doesn't need it either. Fewer capabilities also means a smaller surface to reason about when you're debugging an unexpected result.
Test it before you rely on it
Before building a whole checklist suite around a new actor, run one small checklist against it and read the result. Confirm it interprets your instructions the way you intended, then expand from there.