> For the complete documentation index, see [llms.txt](https://docs.aloop.icustomer.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.aloop.icustomer.ai/iharness/ask-iharness.md). # Ask iHarness Talking to iHarness: ask it to do things, ask it questions, and brainstorm without spending anything. Chat is how you work with iHarness, in the app or in Slack, and it works three ways. ## Ask it to do things Say what you want in plain language: "build a list of Hot accounts that visited pricing this month," "set up a reactivation play for dormant accounts," "suppress everyone in this cohort from paid." iHarness plans the work, shows you the plan, and anything that commits spend or records waits at the [gate](/iharness/gates.md) for your confirmation. ## Ask it questions It answers from the record, not from vibes: "why did we pause LinkedIn last week?" reads the trace; "how is the target pacing?" reads the outcomes; "what changed in my audience this week?" reads the scores. If the honest answer is "that number is not readable from your connected sources," that is the answer you get. ## Brainstorm and simulate Think out loud safely. Sketch a play, weigh a budget split, explore "what would happen if", none of it commits anything. Simulation never spends: no credits drawn, no sends, no audience claimed. When a sketch is worth running, iHarness turns it into a real proposal and *then* asks for your approval. ## It knows where you are Chat is context-aware: on a list, "these" means that list; on an account, "this account" needs no explanation. Multi-select works too, pick twelve contacts and act on exactly those. {% hint style="info" %} One more habit worth forming: when a proposal arrives, ask "why this?" before approving. The reasoning is always on record, and reading it is how you calibrate how much [autonomy](/iharness/autonomy-levels.md) to extend. {% endhint %} --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.aloop.icustomer.ai/iharness/ask-iharness.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.