> ## 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.

# Glossary

> Plain-language definitions of every Oqoqo product term, with a link to the page that covers each one.

These terms mean the same thing everywhere in Oqoqo. To see how the main parts fit together, read [How Oqoqo works](https://docs.oqoqo.ai/core-concepts.md).

## A

### Agent

The AI agent that does the work in a run, such as Claude Code or Codex, with a model and an effort level. It can be built-in or a [custom agent](#custom-agent), and you choose it at launch. See [Agents](https://docs.oqoqo.ai/setup/agents.md).

### Agent behavior

A **Where to fix** value: the evidence points to the agent's own behavior, not to your product or setup. See [Where to fix](#where-to-fix).

### Agent default

The model choice that lets a custom agent use its own default model. See [Custom agents](https://docs.oqoqo.ai/setup/custom-agents.md).

### Agent mode

The Evals mode in which Oqoqo's evals agent reads the full run and the changed files, and checks the agent's claims before it scores. Agent mode is in private beta. Email [support@oqoqo.ai](mailto:support@oqoqo.ai) to enable it for your organization. See [Agent mode](https://docs.oqoqo.ai/evaluation/agent-mode.md).

### AI assistant

The tool you work in, such as Codex, Claude Code, Cursor, or GitHub Copilot. In MCP terms, it's the MCP host. It operates Oqoqo through the [Oqoqo plugin](#oqoqo-plugin) or the CLI. The same product can also be an [agent](#agent), but the roles differ: your AI assistant launches experiments, and agents do the tasks.

### All experiments

Every experiment in the project, under **Analyze**. See [Read results](https://docs.oqoqo.ai/evaluation/results.md).

### All frictions

Every friction in the project, under **Analyze**, ranked by how many runs never got past it. See [Frictions](https://docs.oqoqo.ai/evaluation/frictions.md).

### All official treatments

**All official skills**, **All official MCPs**, **All official CLIs**, and **All official SDKs**: treatments Oqoqo keeps for you, each with the [official version](#official-version) of every project tool of that kind. See [Treatments (Toolsets)](https://docs.oqoqo.ai/experiments/treatments.md).

### All runs

Every run in the project, under **Analyze**. See [Read results](https://docs.oqoqo.ai/evaluation/results.md).

### API key

A personal key from **Profile → API keys** for places where you can't sign in through a browser, such as CI. The CLI reads it from `OQOQO_API_KEY`, and it acts as you until you revoke it. Organization API keys can't use the CLI, and the plugin signs in with OAuth. See [Profile and API keys](https://docs.oqoqo.ai/setup/profile.md).

### Ask Oqo

The in-app assistant for your project, with the same capabilities as the plugin and the CLI. You give it a model under **Organization settings → Oqoqo AI features**. See [Ask Oqo](https://docs.oqoqo.ai/operate/ask-oqo.md).

### Ask Oqo in Slack

Ask Oqo inside Slack, where the **Oqoqo** app answers direct messages and channel mentions. Ask Oqo in Slack is in private beta. Email [support@oqoqo.ai](mailto:support@oqoqo.ai) to enable it for your organization. See [Use Ask Oqo in Slack](https://docs.oqoqo.ai/operate/ask-oqo-in-slack.md).

### Assets

The earlier name for [Tools](#tools).

## B

### Baseline

The treatment you compare the others with, chosen under **Baseline** at launch. It's usually [Raw Agent](#raw-agent), which gives no tools. See [Baseline and lift](https://docs.oqoqo.ai/experiments/overview.md#baseline-and-lift).

### Brief

What Insights adds to a difference on **Comparisons**: one sentence written by the [Experiment insights model](#experiment-insights-model), and the frictions seen with the side that did worse. It never names a cause. Each Brief has a `brf_` ID. See [Brief](https://docs.oqoqo.ai/evaluation/brief.md).

## C

### Check for updates

Compares a file or skill imported from GitHub with its current source, so you can update it. See [Tools](https://docs.oqoqo.ai/experiments/tools.md).

### CLI

1. **The Oqoqo CLI** (`oqoqo`), installed from **Automate → Oqoqo CLI**. See [Use the CLI](https://docs.oqoqo.ai/operate/cli.md).
2. **A CLI tool**: a command-line tool you give an agent in a treatment, under **Manage → Tools → CLIs**. See [Tools](https://docs.oqoqo.ai/experiments/tools.md).

### Compare

A side-by-side view of two or three runs across **Traces**, **Output**, and **Evals**. See [Compare runs side by side](https://docs.oqoqo.ai/evaluation/results.md#compare-runs-side-by-side).

### Comparisons

The experiment tab that says who did better, how sure that is, and what to do next. It opens with the answers to the experiment's question, then **All N comparisons**. Each result is a **Clear difference**, a **Likely difference**, or a **No clear difference** (which doesn't mean the two are the same). You can [run a **Likely difference** again](https://docs.oqoqo.ai/evaluation/comparisons.md#run-a-comparison-again-to-be-sure) to be sure. Each comparison has a `cmp_` ID. See [Comparisons](https://docs.oqoqo.ai/evaluation/comparisons.md).

### Criterion

One item in a rubric that a run passes or fails, added with **Add criterion**. See [Tasks and rubrics](https://docs.oqoqo.ai/experiments/tasks.md).

### Custom agent

An Agent Client Protocol (ACP) agent your organization adds, which Oqoqo installs in each run's machine and runs like a built-in agent. It shows a **Custom** tag and a status: **Needs values**, **Needs attention**, **Testing**, **Not tested**, or **Ready**. Custom agents are in private beta. Email [support@oqoqo.ai](mailto:support@oqoqo.ai) to enable them for your organization. See [Custom agents](https://docs.oqoqo.ai/setup/custom-agents.md).

## D

### Default

The effort choice that sends no effort level, so the agent uses its own default for the model. Cursor is the exception: it uses the default variant Cursor lists for the model. See [Agents](https://docs.oqoqo.ai/setup/agents.md).

### Download

The run menu that saves recorded work: **Download trajectory**, **Download output files**, and **Download changes (diff)**. See [Run details](https://docs.oqoqo.ai/evaluation/traces.md).

## E

### Edit first

Opens **New experiment** with a finished experiment's tasks, treatments, and agents, so you can change them before you launch. See [Launch an experiment](https://docs.oqoqo.ai/experiments/launch.md).

### Effort level

How much reasoning an agent's model uses, where the model supports it, chosen per agent at launch. Levels can include none, minimal, low, medium, high, xhigh, and max. See [Agents](https://docs.oqoqo.ai/setup/agents.md).

### Eval set

The tasks, machine, files, tools, and treatments that evaluate one product. The [Oqoqo plugin](#oqoqo-plugin) skills build one from a product's docs. See [Build an eval set and read its results](https://docs.oqoqo.ai/operate/plugin.md#build-an-eval-set-and-read-its-results).

### Evals

How Oqoqo scores a finished run. The **Evals model** reads the trajectory and changed files and marks each rubric criterion Pass or Fail, and the **Evals** tab notes when it couldn't read the whole run. Evals run independently of Insights. See [Evals](https://docs.oqoqo.ai/evaluation/evals.md).

### Evals mode

How Evals review each run against the rubric. **Standard** scores in one fast, low-cost pass with your Evals model; **Agent** uses Oqoqo's evals agent for an in-depth review that costs more and takes a few minutes per run. See [Agent mode](https://docs.oqoqo.ai/evaluation/agent-mode.md).

### Evals model

The model that scores runs for Evals, chosen under **Organization settings → Oqoqo AI features**. See [Oqoqo AI features](https://docs.oqoqo.ai/setup/oqoqo-ai.md).

### Experiment

One launch of tasks, treatments, agents, and trials, where each combination is one run. It saves what it launched, so later edits to a task or treatment don't change its results. See [Experiments](https://docs.oqoqo.ai/experiments/overview.md).

### Experiment insights model

The model that groups every run's Insights findings into frictions, and writes the [Brief](#brief). See [Oqoqo AI features](https://docs.oqoqo.ai/setup/oqoqo-ai.md).

## F

### Family

The cause of a friction: **Product**, **Docs & skills**, **Machine**, **Agent software**, **Agent reasoning**, or **Task quality**. Each friction has one. See [Family](https://docs.oqoqo.ai/evaluation/frictions.md#family).

### Files

Folders you attach to a task, which Oqoqo puts in the agent's working directory before the run starts. Create them under **Manage → Files**, by upload or from GitHub. See [Machines and files](https://docs.oqoqo.ai/experiments/machines-and-files.md).

### Friction

One problem that agents hit, tracked across runs and experiments with a stable `frc_` ID, one [family](#family), and one place to fix it. Most come from Insights. A run that fails before the agent answers also counts toward a friction for its cause. See [Frictions](https://docs.oqoqo.ai/evaluation/frictions.md).

### From GitHub

Imports a file or skill from a public `github.com` repository, which you can later compare with **Check for updates**. See [Tools](https://docs.oqoqo.ai/experiments/tools.md).

## I

### ID

A record's stable public identifier, with a prefix for each kind: `exp_` experiments, `tsk_` tasks, `trt_` treatments, `frc_` frictions, `sch_` schedules, and `tag_` tags. The CLI and the plugin use these IDs. See [IDs and limits](https://docs.oqoqo.ai/reference/ids-and-limits.md).

### Inactive

A file or skill no longer offered for new tasks or treatments, but kept visible so past results make sense. A GitHub import becomes inactive when **Check for updates** finds its source removed. See [Tools](https://docs.oqoqo.ai/experiments/tools.md).

### Insights

The analysis of a finished run's trajectory, in which the **Insights model** finds frictions and patterns. Insights run independently of Evals. See [Insights](https://docs.oqoqo.ai/evaluation/insights.md).

### Insights model

The model that finds the frictions and patterns in each run. See [Oqoqo AI features](https://docs.oqoqo.ai/setup/oqoqo-ai.md).

### Integrations

Your personal connections under **Profile → Integrations**: personal provider subscriptions, GitHub, Ask Oqo, and MCP server sign-ins. Select **Disconnect** to stop using a connected account. See [Profile and API keys](https://docs.oqoqo.ai/setup/profile.md).

## L

### Launch again

Launches a new experiment with a finished experiment's tasks, treatments, agents, and settings, using each task's latest version. CLI: `oqoqo experiments rerun`. Plugin: **Launch an experiment again** (`rerun_experiment`). See [Launch again](https://docs.oqoqo.ai/experiments/launch.md#launch-again).

### Launch now

Launches a schedule's experiment right away, under your account, without moving its next launch. See [Schedules](https://docs.oqoqo.ai/experiments/schedules.md).

### Launch plan

An experiment's exact selection as the CLI and the plugin send it: task versions, treatments, agents, trials, and settings. Copy a finished experiment's plan with `oqoqo experiments clone-plan` or `get_experiment_plan` to change and relaunch it. See [`oqoqo experiments launch`](https://docs.oqoqo.ai/cli/experiments#oqoqo-experiments-launch).

### Lift

The difference in pass rate between a treatment and the baseline on the same tasks and agents. See [Baseline and lift](https://docs.oqoqo.ai/experiments/overview.md#baseline-and-lift).

## M

### Machine

The environment a run executes in, set on the task. The default is the **Standard Dev Machine**, and you create others under **Manage → Machines (Environments)**. See [Machines and files](https://docs.oqoqo.ai/experiments/machines-and-files.md).

### Machine and task frictions

Frictions in the **Machine** or **Task quality** family. They come from the experiment's own machine or task, not the product you measure, so check them before you trust the results. Don't confuse them with **Setup** under **Where to fix**. See [Machine and task frictions](https://docs.oqoqo.ai/evaluation/frictions.md#machine-and-task-frictions).

### Main comparisons

The comparisons that answer an experiment's question, such as each treatment against the baseline for all agents together. **Comparisons** shows them first, and checks the others (the breakdowns) more strictly. See [Main comparisons and breakdowns](https://docs.oqoqo.ai/evaluation/comparisons.md#main-comparisons-and-breakdowns).

### Matrix

An experiment's first tab: a heat map of tasks by agent and treatment. Each cell shows the chosen metric: **Evals** (the pass rate), **Steps**, **Tool calls**, **Treatment use**, **Frictions**, **Tokens**, **Cost**, or **Duration**. See [Matrix](https://docs.oqoqo.ai/evaluation/results.md#matrix).

### Max Concurrency

How many agent sessions can run at once in a launch. It doesn't control Evals or Insights. See [Launch an experiment](https://docs.oqoqo.ai/experiments/launch.md).

### MCP

1. **The Oqoqo MCP server**: how your [AI assistant](#ai-assistant) operates Oqoqo, through the [Oqoqo plugin](#oqoqo-plugin). See the [Plugin (MCP) reference](https://docs.oqoqo.ai/mcp-server/overview.md).
2. **An MCP server tool**: an MCP server you give an agent in a treatment, under **Manage → Tools → MCP servers**. See [Tools](https://docs.oqoqo.ai/experiments/tools.md).

### Members

The people in your organization, who share its projects, model providers, agents, and run balance. Manage them under **Organization settings → Members**. See [Set up your organization](https://docs.oqoqo.ai/setup/organization.md).

### Metrics

A run's steps, tool calls, tokens, cost, and duration: how hard the agent worked, not only whether it passed. See [Read results](https://docs.oqoqo.ai/evaluation/results.md).

### Model providers

Your organization's API keys and gateways under **Organization settings → Model providers**, and the personal subscriptions that each member connects under **Profile → Integrations**. Agents and Oqoqo AI features use their models. See [Model providers](https://docs.oqoqo.ai/setup/model-providers.md).

## N

### Notifications

Your in-app notifications, under the header bell. Set Email and In-app delivery per type under **Profile → Notifications**. See [Notifications](https://docs.oqoqo.ai/setup/notifications.md).

## O

### Official version

The one version of a tool that the project marks as part of its intended interface, shown with an official mark and used by the **All official** treatments. See [Tools](https://docs.oqoqo.ai/experiments/tools.md).

### Oqoqo AI features

Your organization's model choices for Oqoqo's own work: the **Evals model**, **Insights model**, **Experiment insights model**, and **Ask Oqo model**. You can add custom instructions for Evals, Insights, and Experiment insights. See [Oqoqo AI features](https://docs.oqoqo.ai/setup/oqoqo-ai.md).

### Oqoqo plugin

The package for your [AI assistant](#ai-assistant) that connects the Oqoqo MCP server and adds skills for building [eval sets](#eval-set), launching experiments, and reading results. See [Install the Oqoqo plugin](https://docs.oqoqo.ai/operate/plugin.md).

### Organization

Your company's account, which holds its projects, members, model providers, and run balance. Change it under **Organization settings**. See [Set up your organization](https://docs.oqoqo.ai/setup/organization.md).

### Output

The run tab for what the agent delivered: its final message under **Answer**, and changed files with diffs under **Files**. See [Run details](https://docs.oqoqo.ai/evaluation/traces.md).

## P

### Parent experiment

The experiment that another one was launched from, with **Launch again**, **Edit first**, or a schedule. Experiment lists show it as **Parent:** and its name, and **Open parent experiment** opens it. The experiments launched from it are its child experiments. See [Launch an experiment](https://docs.oqoqo.ai/experiments/launch.md#launch-again).

### Pass rate

The share of runs that passed the task's rubric. Hover over a **Matrix** cell to see the count, such as "3 of 4 trials passed". See [Pass rate and lift](https://docs.oqoqo.ai/evaluation/results.md#pass-rate-and-lift).

### Pause

Stops a schedule's launches until you select **Resume**. Oqoqo also pauses a schedule that needs a fix and marks it **Needs attention**. See [Schedules](https://docs.oqoqo.ai/experiments/schedules.md).

### Plan runs

The runs your free or paid plan gives your organization each billing period. Unused plan runs don't roll over. See [Runs and billing](https://docs.oqoqo.ai/setup/billing.md).

### Project

The place that holds your tasks, files, machines, tools, treatments, experiments, and schedules. An organization can have many, and you switch between them in the header. See [Projects](https://docs.oqoqo.ai/setup/projects.md).

### Public experiment link

A link that lets anyone view an experiment's results without an account, created with **Share** on a finished experiment. Updates go live only when you publish them. See [Share results](https://docs.oqoqo.ai/evaluation/share.md).

### Public sharing

The **Organization settings** tab that lists every public experiment link in the organization. See [Share results](https://docs.oqoqo.ai/evaluation/share.md).

### Publish

Creates a public experiment link, or updates it with the latest results. CLI: `oqoqo experiments publish`. Plugin: **Publish an experiment** (`publish_experiment`). See [Share results](https://docs.oqoqo.ai/evaluation/share.md).

## R

### Raw Agent

The treatment with no tools: the agent as its vendor ships it. It's the usual baseline. See [Treatments (Toolsets)](https://docs.oqoqo.ai/experiments/treatments.md).

### Recovery

Whether the agent got past a friction: **Recovered**, **Unrecovered**, or **Unknown**. See [Recovery](https://docs.oqoqo.ai/evaluation/frictions.md#recovery).

### Repeat

When a schedule launches: every hour, day, weekday, week, or month, or on a custom cron expression. Schedules start on the quarter hour. See [Schedules](https://docs.oqoqo.ai/experiments/schedules.md).

### Rerun evals

Rescores the same recorded work without rerunning the agent, such as after a rubric or Evals model change. Before Evals have run, the action is **Run evals**. See [Run Evals again](https://docs.oqoqo.ai/evaluation/evals.md#run-evals-again).

### Rerun Insights

Analyzes the same recorded work again without rerunning the agent. Before Insights have run, the action is **Run insights**. See [Run Insights again](https://docs.oqoqo.ai/evaluation/insights.md#run-insights-again).

### Rubric

The criteria that Evals check each run against to decide whether it passes the task. See [Tasks and rubrics](https://docs.oqoqo.ai/experiments/tasks.md).

### Run

One agent's attempt at one task with one treatment, and the unit you pay for. Errored or cancelled runs don't count against your organization's run balance. See [Runs and billing](https://docs.oqoqo.ai/setup/billing.md).

### Run profile

The side rail on a run that shows treatment use, tool calls, what stood out, and where the time went. CLI: `oqoqo runs profile`. Plugin: **Get a run profile** (`get_run_profile`). See [Run profile](https://docs.oqoqo.ai/evaluation/run-profile.md).

### Runs

1. **The Runs tab**: the tab on an experiment, task, tool, treatment, machine, file, agent, or schedule that lists its runs.
2. **Run balance**: the runs your organization can spend, from plan runs and top-up runs. See [Runs and billing](https://docs.oqoqo.ai/setup/billing.md).

## S

### Schedule

A rule under **Automate → Schedules** that launches a finished experiment again on a [repeat](#repeat), as a new experiment that uses runs. It runs as whoever created it, resumed it, or last changed its repeat or experiment. See [Schedules](https://docs.oqoqo.ai/experiments/schedules.md).

### SDK

A software development kit you give an agent in a treatment, created under **Manage → Tools → SDKs**. See [Tools](https://docs.oqoqo.ai/experiments/tools.md).

### Share

Opens the **Share experiment** dialog on a finished experiment, where you create a public experiment link or invite a teammate to view it. See [Share results](https://docs.oqoqo.ai/evaluation/share.md).

### Skill

A folder of instructions and files, with a `SKILL.md`, that an agent can read when a treatment includes it. Create skills under **Manage → Tools → Skills**. See [Tools](https://docs.oqoqo.ai/experiments/tools.md).

### Standard Dev Machine

The default machine for a task: Ubuntu 24.04 with Node.js 24, Python 3.12, and Git. See [Standard Dev Machine](https://docs.oqoqo.ai/experiments/machines-and-files.md#standard-dev-machine).

### Standard mode

The default Evals mode, which scores each run in one pass with your Evals model. See [Evals mode](#evals-mode).

## T

### Tag

A label with a stable `tag_` ID that groups tasks, files, machines, tools, treatments, or experiments, so you can filter lists with **Tags**. Tags don't change a run. See [Tags](https://docs.oqoqo.ai/experiments/tags.md).

### Task

The work an agent attempts: instructions, a rubric, files, and a machine. Create tasks under **Manage → Tasks**. See [Tasks and rubrics](https://docs.oqoqo.ai/experiments/tasks.md).

### Template

A ready-made experiment on **Home**. Selecting one adds its tasks, tools, and treatments to your project and opens **New experiment**. See [Templates](https://docs.oqoqo.ai/experiments/templates.md).

### Test agent

Launches one short run with the **Raw Agent** treatment (no tools) to check that a custom agent installs, starts, and answers. It uses one run from your balance. See [Custom agents](https://docs.oqoqo.ai/setup/custom-agents.md).

### Timeline

The top of the **Traces** tab, showing when tool calls happened, grouped by model turn when the run recorded turns. See [Timeline](https://docs.oqoqo.ai/evaluation/traces.md#timeline).

### Tools

Skills, MCP servers, CLIs, and SDKs, under **Manage → Tools**. You attach them to treatments, not tasks. See [Tools](https://docs.oqoqo.ai/experiments/tools.md).

### Toolset

The set of tools in a treatment. See [Treatment (toolset)](#treatment-toolset).

### Top-up runs

Runs you buy on top of your plan, which never expire. See [Runs and billing](https://docs.oqoqo.ai/setup/billing.md).

### Traces

The run tab with the recorded trajectory: the **Timeline**, then the transcript grouped by model turn. See [Run details](https://docs.oqoqo.ai/evaluation/traces.md).

### Transcript

A run's recorded trajectory, shown on **Traces** grouped by model turn. To save it, choose **Download → Download trajectory** on the run. See [Run details](https://docs.oqoqo.ai/evaluation/traces.md).

### Treatment (toolset)

One set of tools you compare: the skills, MCP servers, CLIs, and SDKs an agent gets in a run. [Raw Agent](#raw-agent) gives none. Create treatments under **Manage → Treatments (Toolsets)**. See [Treatments (Toolsets)](https://docs.oqoqo.ai/experiments/treatments.md).

### Treatment use

Whether the agent used the treatment's tools: **Used**, **Not used**, **Not measured**, **Can't tell**, or **Not applicable**. It shows in the **Run profile** and the **Runs** tab. See [Treatment use](https://docs.oqoqo.ai/evaluation/run-profile.md#treatment-use).

### Trial

One repeat of the same task, treatment, and agent, set at launch. Each trial is one run against your run balance. See [Launch an experiment](https://docs.oqoqo.ai/experiments/launch.md).

## U

### Unpublish

Stops sharing an experiment, so its public link no longer works. See [Share results](https://docs.oqoqo.ai/evaluation/share.md).

### Upload

Adds a local folder or ZIP archive as a file or skill, or imports tasks from a ZIP archive. CLI: `oqoqo uploads` commands. Plugin: **Start an archive upload** (`create_upload`). See [`oqoqo uploads create`](https://docs.oqoqo.ai/cli/catalog#oqoqo-uploads-create).

## V

### Version

A saved state of a task or tool. An experiment records the versions it launched, while **Launch again** and schedules use each task's latest version. See [Tasks and rubrics](https://docs.oqoqo.ai/experiments/tasks.md).

## W

### What the agent did

One sentence on a fixable friction that says what the agent did, shown after the suggested fix. It isn't the change to make. See [Where to fix](https://docs.oqoqo.ai/evaluation/frictions.md#where-to-fix).

### Where it happens most

On a friction, the agent or treatment that hits it more often than the others in the same experiments. See [Where it happens most](https://docs.oqoqo.ai/evaluation/frictions.md#where-it-happens-most).

### Where to fix

The main friction filter: **Product**, **Custom agent**, **Setup**, or [Agent behavior](#agent-behavior). Each friction's suggested fix names one place your team controls. See [Where to fix](https://docs.oqoqo.ai/evaluation/frictions.md#where-to-fix).

## Related

> [card] [How Oqoqo works](https://docs.oqoqo.ai/core-concepts.md)
>
> See how the parts fit together.

> [card] [IDs and limits](https://docs.oqoqo.ai/reference/ids-and-limits.md)
>
> Look up ID prefixes and limits.

> [card] [FAQ](https://docs.oqoqo.ai/reference/faq.md)
>
> Find answers to common questions.

> [card] [Quickstart](https://docs.oqoqo.ai/quickstart.md)
>
> Launch your first experiment.


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