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

# Read a run

> See how your agent did, tell real problems from flaky ones, and open the conversation where it broke.

The **Run** tab shows how your agent did on every scenario.

Three plays, not one
Agents vary, so each scenario runs three times to tell a real problem from a lucky draw.

A real-feeling world
A realistic user and a fully wired digital twin, not scripted inputs.

Ready to ship
The difference between a demo that worked once and an agent you can rely on.

![The Run tab of the report](https://mintcdn.com/plurai/V3XeGRFO5iyJejs5/images/report/run.png?fit=max\&auto=format\&n=V3XeGRFO5iyJejs5\&q=85\&s=49c4f85cfc5dd575d58723e1a188813f)

The Run tab: each scenario's three attempts, and how many checks failed.

## Read the grid

Each row is a scenario, and each square is one attempt: green passed, red failed.

| Pattern | What it means | What to do |
| - | - | - |
| All three green | The agent handles this reliably. | Nothing. |
| All three red | A real, repeatable problem. | Start here. |
| Mixed | The agent is flaky in this situation. | Compare a failed attempt with a passing one. |

## See what happened

Select any red square to open that conversation. It opens at the turn where things went wrong, with
**What broke** at the top: the exact words a check objected to, and why.

## Compare with earlier runs

Each run is kept. Pick an earlier one to see whether a change made things better or worse.

For every label in this tab, see [Run results](https://docs.plurai.ai/report/run-results.md).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.