Tools provided
Tools the agent exposes — your AI client calls them automatically when it needs them.
- plan_experiment — Size an A/B test: the sample needed per variant to detect the effect you name, at the alpha and power you name, and the days that takes at your traffic. The effect_basis is REQUIRED and never guessed — relative and absolute readings of the same number differ by orders of magnitude. Only conventional alpha and power values are accepted; an interpolated critical value is refused rather than approximated.
- read_experiment — Read a finished or running A/B test. The decision order is load-bearing: no data, then not enough data, then a test you say you looked at, then a regressed guardrail, and only then the primary metric - so a ship decision is the LAST thing reachable. The sample check is called underpowered, not a peeking guard: looking leaves no trace in the counts. Two arms differ only when their 95% intervals do not overlap, and overlap is reported as not-established, never as no-difference.
- run_full — Run every capability you supplied the input for, in registry order, and return one report. Capabilities whose input is missing are listed as skipped with the fields they need — never run against a fixture and never reported as zero.
- list_capabilities — List what this agent can do: every tool it advertises, what each one is for, and the arguments each one reads. Useful for discovery before the first call.
- plan_inputs — Plan the inputs for a tool: returns the questions to ask, the JSON schema of the arguments, and a ready-to-edit example. Every argument it names is an argument the tool actually reads.
- discover_intent — Understand your goal and co-design the exact input through clarifying questions before anything runs.
- open_form — Use this the moment the user wants to run this agent on their own input. It opens an interactive form that collects the run arguments. Do NOT check credentials, do NOT ask clarifying questions in chat, and do NOT run any analysis before calling this — the form is the entry point for running the agent.
- run_form — Internal: invoked by the open_form form when the user submits. Reads exactly the same arguments as run_full and forwards all of them. Not for direct use.
