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

# Terminal UI

> Use CloudEval's terminal UI for interactive review and explicit CLI commands for automation.

CloudEval has two terminal modes: an interactive terminal UI for humans and explicit commands for scripts, agents, and CI jobs.

<Frame caption="The terminal UI opens directly into a project-aware chat workspace with starter prompts, project context, model, mode, and status controls.">
  <img src="https://mintcdn.com/ganakailabs-db727e50/Q5sxR4Wz8SD3FHrz/assets/images/cli/tui-chat-reasoning.jpeg?fit=max&auto=format&n=Q5sxR4Wz8SD3FHrz&q=85&s=6cb1d69091260eff28d60a1358f18680" alt="CloudEval terminal UI chat workspace with reasoning progress, project context, model, mode, input controls, and account status" width="2048" height="1201" data-path="assets/images/cli/tui-chat-reasoning.jpeg" />
</Frame>

## When to use the terminal UI

Use the terminal UI when you want to stay in a terminal but still inspect CloudEval interactively.

```bash theme={null}
cloudeval
cloudeval tui
cloudeval tui --tab reports --project <project-id>
```

<Frame caption="The overview tab gives a fast terminal-native read on projects, report status, connection health, and recent activity.">
  <img src="https://mintcdn.com/ganakailabs-db727e50/9uUc6pZVXStvEpYp/assets/images/cli/overview.png?fit=max&auto=format&n=9uUc6pZVXStvEpYp&q=85&s=e8027f381960389659ec04815938be44" alt="CloudEval terminal UI overview tab showing plan, credits, projects, connections, reports, and activity" width="2450" height="1812" data-path="assets/images/cli/overview.png" />
</Frame>

The terminal UI is useful for:

* browsing projects
* jumping into project reports
* reviewing chat or help context
* opening exact app pages from a project-oriented terminal session

Do not parse terminal UI output in automation. Use explicit commands with `--format json` instead.

<Frame caption="The reports tab keeps architecture, cost, unit test, and shareable report status visible without leaving the terminal.">
  <img src="https://mintcdn.com/ganakailabs-db727e50/9uUc6pZVXStvEpYp/assets/images/cli/reports.png?fit=max&auto=format&n=9uUc6pZVXStvEpYp&q=85&s=40db57c3af9beebdf3ebe8cde590d6e7" alt="CloudEval terminal UI reports tab showing report status, score, attention count, run commands, and project report shortcuts" width="2448" height="1818" data-path="assets/images/cli/reports.png" />
</Frame>

<Frame caption="The billing tab shows plan, credits, subscriptions, and customer portal actions for local account checks.">
  <img src="https://mintcdn.com/ganakailabs-db727e50/9uUc6pZVXStvEpYp/assets/images/cli/billing.png?fit=max&auto=format&n=9uUc6pZVXStvEpYp&q=85&s=dbdc9bc68aefe776e39caca9368f6072" alt="CloudEval terminal UI billing tab showing plan, credits, billing status, subscription controls, and customer portal actions" width="2412" height="1808" data-path="assets/images/cli/billing.png" />
</Frame>

## When to use explicit commands

Use explicit commands when another tool needs predictable output.

```bash theme={null}
cloudeval status --profile codex --format json
cloudeval projects list --profile codex --format json
cloudeval reports run --project <project-id> --type all --wait --profile codex --format json
cloudeval ask "Summarize the highest-risk findings" --project <project-id> --profile codex --format json --non-interactive
```

<Frame caption="JSON mode keeps CLI output predictable for scripts, agents, and CI jobs.">
  <img src="https://mintcdn.com/ganakailabs-db727e50/431cYuJMCQHimeRQ/assets/images/cli/cli-json-output.png?fit=max&auto=format&n=431cYuJMCQHimeRQ&q=85&s=1efedb2f62f940e8f6f99e0b7dbc1014" alt="CloudEval CLI terminal output showing version, MCP doctor JSON, toolsets, tools, resources, prompts, and project report status JSON" width="1440" height="980" data-path="assets/images/cli/cli-json-output.png" />
</Frame>

This mode is better for:

* CI jobs
* MCP-adjacent automation
* shell scripts
* local agents
* repeatable report generation
* saving output to files

## Output rules

For machine-readable commands:

* stdout is the data channel
* stderr is for prompts, progress, warnings, and browser-open messages
* `--output <file>` writes durable artifacts when supported
* `--profile <name>` keeps defaults scoped to one agent or workspace

## Good defaults for automation

```bash theme={null}
cloudeval doctor --profile codex --format json
cloudeval capabilities --profile codex --format json
cloudeval config show --profile codex --format json
```

Use those checks before relying on a local CLI install in automation.

## Next step

Use [CLI command reference](/reference/cli-command-reference) for the full command surface, or [MCP client setup](/reference/mcp-client-setup) when an agent should call CloudEval through MCP instead of shell commands.