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

# Run profile

> See whether the agent used each tool in the treatment, where its tool calls and time went, and what stood out in the run.

Check **Run profile** in the right rail of any run (or at the top of each column in **Compare**) to verify whether the agent actually used your treatment tools before interpreting pass rates. Counts and timings are always exact—Oqoqo never estimates missing metrics.

![Run profile rail with the run's metrics, a skill marked Used, tool calls split by what served them, and time split into setup and working phases.](https://mintcdn.com/oqoqo/YO1ysyUx4SPwBwoz/images/screenshots/run-profile-light.png?fit=max\&auto=format\&n=YO1ysyUx4SPwBwoz\&q=85\&s=d8d21d77943820acfcf48384f767cc82)

## Treatment use

**Treatment use** tracks each skill, MCP server, CLI, or SDK in the treatment (and rolls up to one state per run on the **Runs** list):

| State | Meaning |
| - | - |
| **Used** | The agent log shows direct usage, with call count and first step/turn. |
| **Not used** | The tool was available all run and never called. |
| **Not measured** | Usage is invisible in agent logs (for example, an SDK imported in code or a machine service). |
| **Can't tell** | Logs lack detail or ran the tool indirectly (such as a CLI invoked inside a script, `npx`, or `sudo`). |

Oqoqo detects **Used** when an agent reads a skill file or calls its skill tool, calls an MCP server tool, or invokes a CLI command (or any binary installed by an exact npm/crates.io/Go CLI package) directly in a shell call. **Not used** is an observation, not a pass/fail verdict.

## Tool calls

**Tool calls** groups every call the agent made by what served it—each launched skill, MCP server, or CLI, or **Other tools**. Calls matching multiple tools are excluded from individual totals and flagged in **Evidence warnings**.

## What stood out

**What stood out** highlights notable execution patterns that cross fixed thresholds, linking directly to the matching turn or step in **Traces**:

* Repeated identical tool calls with the same input
* Single-turn context growth of at least 10,000 tokens and 10%
* Slow tool calls taking at least 5 seconds and 5% of agent working time
* Gaps between turns of at least 10 seconds and 3× the run's median gap (when not explained by a slow tool call)

An empty list means no pattern crossed these thresholds.

## Time

**Time** breaks the run into recorded phases (hiding phases with no recorded duration, or noting if overlapping phases cannot be split):

| Phase | What it measures |
| - | - |
| **Machine setup** | Building and starting the machine and services |
| **Agent setup** | Installing and configuring the agent |
| **Agent working** | The agent's own turns and tool calls (split into **Treatment tools** and **Other tools** when reported; runs whose agent never started report none) |
| **Saving output** | Saving changed files and outputs and scrubbing secrets after the agent finishes (does not grade the run) |
| **Other overhead** | Elapsed time outside the phases above, such as teardown |

Token totals and USD cost appear alongside timing (unreported costs stay blank rather than showing `$0`).

## When the profile cannot answer

Once the run finishes, if logs are missing, incomplete, or ambiguous, **Evidence warnings** states exactly what could not be verified—for example, no readable agent log, missing launch metadata, unattributed calls, or calls matching multiple tools—without guessing causes. If a CLI shows **Can't tell**, list its executable names under [**Commands**](https://docs.oqoqo.ai/experiments/tools.md#clis-and-sdks); if a tool shows **Not used**, see [Measure a tool's impact](https://docs.oqoqo.ai/guides/measure-tool-lift.md#interpret-the-results).

## From the CLI and the plugin

| Task | CLI | Plugin (MCP) |
| - | - | - |
| Read one run's profile | [`oqoqo runs profile`](https://docs.oqoqo.ai/cli/runs#oqoqo-runs-profile) | [`get_run_profile`](https://docs.oqoqo.ai/mcp-server/runs-and-results#get_run_profile) |
| List runs with treatment use | [`oqoqo runs list`](https://docs.oqoqo.ai/cli/runs#oqoqo-runs-list) | [`list_runs`](https://docs.oqoqo.ai/mcp-server/runs-and-results#list_runs) |

## Next steps

> [card] [Evals](https://docs.oqoqo.ai/evaluation/evals.md)
>
> See how Evals grade runs against task rubrics.

> [card] [Frictions](https://docs.oqoqo.ai/evaluation/frictions.md)
>
> Identify recurring issues across runs.

> [card] [Measure a tool's impact](https://docs.oqoqo.ai/guides/measure-tool-lift.md)
>
> Combine Treatment use and Matrix lift to judge a tool.

> [card] [oqoqo runs and results](https://docs.oqoqo.ai/cli/runs.md#oqoqo-runs-profile)
>
> Inspect run profiles from the terminal.


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