Agent Workflows

WebTest AI treats the model as a bounded decision maker and the runtime as the authority on browser truth. This separation lets an agent factory generate and run tests without giving a model unrestricted control of the browser.

  1. Draft a Markdown goal with explicit success conditions.
  2. Start an isolated browser context at the approved origin.
  3. Collect a fresh observation before every model decision.
  4. Ask the navigator for one allowed action only.
  5. Resolve the action target locally when its name is unique.
  6. Ask Jev to choose from fresh candidates only when the target is ambiguous.
  7. Execute the validated action and capture the resulting observation.
  8. Evaluate fixed assertions and publish evidence with the verdict.

Jev versus the navigator

ComponentInputOutputRole
NavigatorGoal, approved data, URL, visible text, candidate summary, allowed toolsOne bounded action such as click, fill, navigate, wait, done, or blockedPlans the next move
JevElement intent, operation, and fresh visible candidates with contextCandidate reference, confidence, and probability distributionResolves target ambiguity
RuntimeValidated action and current browser sessionBrowser effect, assertion evidence, telemetry, and verdictEnforces policy and truth

For example, two forms in Everyday Goods contain a Save button. The navigator identifies the shipping context. Jev chooses the shipping candidate from the current snapshot. The runtime checks that the reference is still valid before clicking it. If Jev is uncertain, the test becomes INCONCLUSIVE and does not guess.

Agent factory contract

An agent factory can treat each Markdown goal as a work item and the agent-readable report as the result contract:

The MCP surface can expose suite execution, report summaries, and paginated call details to an agent factory without exposing secrets or requiring prompts and model responses to be stored.

Safety bounds

Evidence and cost

Every run writes an HTML report for human review, compact agent JSON, a newline-delimited call ledger, and a manifest. Provider token usage and configured rates are used for cost estimates. When a provider or subscription bridge does not return usage, the report says usage is unavailable rather than fabricating a zero.

Use deterministic fixtures for release gates that need repeatability. Use live navigator and Jev runs for adaptable regression coverage, calibration, and agent capability evaluation. Keep both in the same report format so the difference is visible.