> For the complete documentation index, see [llms.txt](https://docs.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.icustomer.ai/concepts/worked-example.md).

# Worked example

One arc, end to end: a cold account comes back, and the loop turns it into a meeting, with receipts.

One arc, end to end. The numbers are illustrative; the mechanics are exactly what the platform does.

{% stepper %}
{% step %}

## A signal arrives

An account your team closed-lost last year returns to your pricing page.

* To an analytics tool: an anonymous session.
* Here: an **event** entering the loop.
  {% endstep %}

{% step %}

## It resolves

Identity matching ties the visit to the account.

* The visitor's earlier anonymous activity re-attributes to the same record.
* The old opportunity, the past emails, the fit you already established: one story again.
  {% endstep %}

{% step %}

## The score moves

Pricing-page intent from a good-fit, previously engaged account moves Intent and Recency sharply.

* The account flips **Hot**.
* The reason is attached: not "score changed," but *which* signal moved it and why it matters.
  {% endstep %}

{% step %}

## A decision is made

iHarness diagnoses the moment: a win-back situation, not a cold outreach one. Before anything runs, it:

* selects the play whose lever matches,
* chooses the audience slice and the channel,
* states what it expects to happen,
* and writes the [trace](/concepts/decisions-and-traces.md).
  {% endstep %}

{% step %}

## You approve

The proposal arrives in [Pulse](/pulse/queue.md) as a stall waiting on your call: the account, the reasoning, the plan, one primary action. You approve; the gate opens.
{% endstep %}

{% step %}

## It activates

The activation goes to your outbound channel, personalized against everything the context knows, inside the guardrails:

* the contact is claimed by this one cadence,
* suppression checked,
* your CRM updated rather than overwritten.
  {% endstep %}

{% step %}

## The outcome comes back

A reply, a meeting booked.

* The outcome joins on the trace ID.
* It credits the decision that caused it, not the last click, not the loudest channel.
  {% endstep %}

{% step %}

## The loop learns

Expected versus actual is recorded. The next time a closed-lost account warms up, the diagnosis is sharper because this arc happened.

That is the whole platform, once: signal, identity, score, decision, gate, activation, outcome, learning, one trace ID from start to finish.
{% endstep %}
{% endstepper %}


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.icustomer.ai/concepts/worked-example.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.