Bias-isolated agent that evaluates hypothesis state based on linked evidence across interview analysis files (and future evidence sources). Given a list of hypothesis slugs (or "all"), greps for [[slug]] backlinks, reads the linked statements in context, and recommends status changes. For each hypothesis it also…
Bias-isolated agent that turns one customer discovery interview transcript (or recollection) into a structured analysis file — extracted statements with.
Bias-isolated assessment agent that evaluates a startup project's current state against lean startup methodology and recommends plan updates. Dispatched by the whats-next skill — not invoked directly by the founder. Returns structured recommendations as text; does not write files or interact with the user.
General-purpose web research worker. Dispatched by the main agent for any multi-source information-gathering task — competitor discovery, market landscape, review mining, problem-space validation, live benchmark actualization. Inputs are task and context, plus optional entities, focus, exclude, alreadyknown…