> ## Documentation Index
> Fetch the complete documentation index at: https://docs.rulebase.co/llms.txt
> Use this file to discover all available pages before exploring further.

# Coaching overview

> Turn QA results into two kinds of coaching: logged 1:1 sessions and AI role-play simulations.

Coaching connects your QA program to agent development. Rulebase gives you two
tools:

* **Coaching sessions** — a logged 1:1 record you keep for one agent, built from
  real tickets and their QA scores. Use it to document a coaching conversation
  and give the agent something to refer back to.
* **Coaching simulations** — an AI role-play exercise you assign to agents. The
  AI plays a customer through a scenario, the agent handles it, and Rulebase
  scores the attempt automatically. Use it to build skills before agents face
  the situation live.

Both are gated by a single feature. If you don't see **Coaching** in the
sidebar, ask an admin to enable it under [Settings > Features](https://app.rulebase.co/settings/features).

## Sessions vs simulations

|                            | Coaching sessions                                                   | Coaching simulations                                                                  |
| -------------------------- | ------------------------------------------------------------------- | ------------------------------------------------------------------------------------- |
| **Purpose**                | Document real coaching, grounded in real tickets                    | Practice a scenario safely before it happens                                          |
| **Where you create it**    | The agent's performance page                                        | The **Coaching** page (**New**)                                                       |
| **What it contains**       | A date, markdown notes, and linked tickets + QA scores ("evidence") | A generated persona and scenario, an optional scorecard, a due date, and a time limit |
| **Who does the work**      | The coach writes it; the agent reads it                             | The agent completes an assigned role-play                                             |
| **Scoring**                | None — it's a record, not a test                                    | Auto-scored into a report, pass/fail against a passing score                          |
| **Assignment & due dates** | No                                                                  | Yes, with reminders for unattempted assignments                                       |

<Note>
  The **Coaching** page in the sidebar lists **simulations**, even though its
  heading reads "Coaching." Coaching **sessions** don't appear there; they live
  on each agent's performance page. See [Run a coaching
  session](/guides/coaching/run-a-session).
</Note>

<img src="https://mintcdn.com/rulebase/r5Wr8jebJAzAsiac/images/coaching-list.png?fit=max&auto=format&n=r5Wr8jebJAzAsiac&q=85&s=29b32359714ac8817231f47f1a296486" alt="The Coaching page listing coaching simulations" width="2880" height="2000" data-path="images/coaching-list.png" />

## From evaluation to coaching

Coaching is most useful when it's tied to evidence:

1. AI QA (and your reviewers) evaluate interactions and produce scores.
2. On an agent's performance page you spot a pattern worth addressing.
3. You log a **coaching session**, attaching the specific tickets and
   evaluations that illustrate the point, plus your notes.
4. Where a skill needs practice, you assign a **simulation** so the agent can
   rehearse and get scored on it.
5. Later evaluations and simulation reports show whether the coaching landed.

## Who can do what

* **Coaches and admins** create and edit coaching sessions, and author and
  assign simulations.
* **Agents** see their own coaching sessions read-only, and complete the
  simulations assigned to them.

## Related

* [Run a coaching session](/guides/coaching/run-a-session)
* [Coaching simulations](/guides/coaching/simulations)