> 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/what-it-does.md).

# What iHarness does

iHarness is the AI you talk to: it reasons over your context, decides what to do for each audience, and coordinates the agents.

iHarness is the AI you work with. It says "I'm iHarness," and it is the only voice you deal with: it reads your [context](/concepts/context-and-memory.md), decides what to do for each audience, and puts the right [agent](/reference/agent-catalog.md) on the job, with no hand-offs for you to manage.

It works two ways, all the time:

* **When you ask.** Tell it what you want in plain language, in the app or in Slack. "Set up a reactivation play for dormant accounts." "Why did we pause LinkedIn last week?"
* **On its own.** The loop runs over your audiences without prompting: it watches for signals, decides, and tells you what it did or what it needs from you.

## Decision-first

iHarness decides *what* should happen before it decides *where*. Engage, nurture, suppress, or escalate comes first. The channel is the output of that decision, never the input, and that order is what keeps spend honest and measurement clean.

## It proposes, you dispose

Anything that goes live, a play, a budget, a sequence, reaches you as a proposal first, and approvals land in [Pulse](/pulse/queue.md). Where you have granted autonomy, it acts within those bounds and shows its work. Where you have not, it waits at the [gate](/iharness/gates.md).

## It shows its work

Every decision is recorded as a [trace](/concepts/decisions-and-traces.md): the signal, the reasoning, the authority, the action, and the outcome. Ask "why?" about anything and iHarness answers from the record, not from memory.

## What it holds

* **Goals and targets.** Your objective function: pipeline, revenue. Goals are the input to the whole system, and without one nothing runs. What does it optimize for? Whatever you told it to. See [Goals, KPIs and targets](/iharness/goals-kpis-targets.md).
* **Pulse.** The human channel: alerts, approvals, and your autopilot settings. What does it do without asking you? Whatever you have approved it to do. Everything else waits in [Pulse](/pulse/queue.md).
* **Orchestration.** Runs plays through agents. Plays live here: they are the patterns Orchestration executes, not a separate product.

## What it runs on

iHarness runs on your Growth Brain: it reasons over your [context and memory](/concepts/context-and-memory.md), chooses plays by [diagnosis](/iharness/plays-to-decisions.md), and paces your [goals and targets](/iharness/goals-kpis-targets.md). The better the context, the better every decision downstream.


---

# 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/what-it-does.md?ask=<question>&goal=<endgoal>
```

`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.
