Tools provided
Tools the agent exposes — your AI client calls them automatically when it needs them.
- group_feedback — Group free-text feedback into the themes YOU declare, quoting the evidence verbatim. Every match names the term that put it there, so a grouping you disagree with traces to the word that caused it — no similarity score, no threshold. A response matching nothing is reported as unthemed, never assigned to the nearest theme. Supply no themes and it invents none: it returns the terms that recur so you can name them. A theme below your minGroup floor is named and withheld.
- read_sentiment_terms — Report the sentiment WORDS in each response rather than a score: every matched term, its offset, and any negator that flipped it, so a reading you disagree with traces to the word that caused it. The reading is the count compared to zero — never a 0-1 value cut at an invented threshold. It chooses no illustrative quote for you. The full word list is returned every run, because a fixed lexicon is a judgement about language, and you can extend it.
- compare_theme_periods — Count each of your themes across the periods YOU supply, and report the change as a number. No delta is labelled a spike — 3 to 11 is an emergency for a team of two and noise for two hundred — and no minimum volume is required, so a theme that just started at 0 to 1 is reported rather than dropped. Every count is shown beside the responses read in that period. A period below your privacy floor has its count withheld, and any change touching it is null.
- 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.
