Loading page…
Loading page…
Find candidate agents and evaluate their behavior against a defined task.
Developer project · Proposed Act workflow.
Mole’s TypeScript runtime uses the Claude Agent SDK and a custom HTTP adapter for Darwin Search. Its demonstration trials locally runnable candidates in Sparta test environments; other Darwin matches are recorded as discovery results rather than treated as tested agents.
Mole discovers candidate agents and evaluates their behavior against a task’s requirements, using controlled tests to inform the developer’s choice.
Darwin supplies candidates to compare against explicit requirements. Mole separates declared capabilities from evidence of performance.
A candidate could run against permitted test inputs while Mole records outputs, errors, and resource use. Follow-up tests would address gaps in the evidence.
A task-specific evaluation record that supports an adoption decision. A passing test establishes only what was tested.
Search. Find candidates that claim to meet the task’s explicit requirements.
Act. Clarify supported inputs and test conditions before evaluating performance.
Outcome. A shortlist with declared capabilities, missing evidence, and proposed checks.
Search. Select a candidate and define the evaluation environment and limits.
Act. Invoke the candidate under the agreed limits while Mole records behavior and errors.
Outcome. Test conditions, outputs, failures, and limits on what the results establish.
Search. Compare the evaluation evidence with the original criteria.
Act. Request a follow-up test or clarification where evidence is missing.
Outcome. A task-specific recommendation with untested conditions and remaining reliability questions.
Inspect the candidate’s claims, observed behavior, and untested conditions before deciding where to use it.
Deliverable: A shortlist with declared capabilities, missing evidence, and proposed checks.
Review criteria: Return claims separately from evidence. Keep candidates out of production while we evaluate them.
Deliverable: Test conditions, outputs, failures, and limits on what the results establish.
Review criteria: Stay within the test budget and environment. Record failures and incomplete evidence without hiding them.
Deliverable: A task-specific recommendation with untested conditions and remaining reliability questions.
Review criteria: Do not generalize from one passing test. Identify what remains untested and keep deployment separate.
TypeScript
