> ## Documentation Index
> Fetch the complete documentation index at: https://arizeai-433a7140.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# PXI Advanced

> Skills, the permission model, the terminal client, slash commands, model providers, and configuration.

Everything beyond the [PXI](/docs/phoenix/pxi) quickstart: what each skill does, conversations, the terminal client, and how to configure and lock down the agent.

## What it can do

| You can ask PXI to | Try asking |
| - | - |
| Optimize a prompt | *Tighten this prompt so it stops apologizing* |
| Write an evaluator | *Write an evaluator that flags answers with no citation* |
| Build a dataset from failures | *Add today's failing traces to a dataset called regressions* |
| Run and compare experiments | *Rerun the last experiment and compare the scores* |
| Query your data | *Which projects had the most errors this week?* |

Each row is backed by a **skill**, a reusable procedure for one Phoenix workflow that PXI loads on demand.

**File GitHub issues.** When PXI finds a real defect it can file an issue linking the relevant traces, through [GitHub's MCP server](https://github.com/github/github-mcp-server). Add a [fine-grained token](https://docs.github.com/en/authentication/keeping-your-account-and-data-secure/managing-your-personal-access-tokens) with **Issues read/write** under **Settings → Assistant → Tools → GitHub**, or set `githubPersonalAccessToken` in `~/.px/settings.json` for the terminal. Issues are filed as you, after approval.

## Conversations

Chats are saved on the server, so a conversation survives a reload and is the same session in the panel or the `pxi` client. The panel header lists past chats to continue, rename, or delete; a **temporary** chat is never saved. On any message, **Rewind** drops it and everything after, and **Branch** forks a new chat from that point.

Retention is set under **Settings → Assistant → Chats & data**; see [agent session retention](/docs/phoenix/settings/data-retention#agent-session-retention). Sessions are also exposed under `/v1/agent_sessions`; see the [Agent Sessions API](/docs/phoenix/sdk-api-reference/rest-api/api-reference/agent-sessions/list-sessions).

## The terminal client

The same server-side agent in your terminal, shipped with the Phoenix CLI. Credentials, skills, and permissions come from the server.

```bash theme={"theme":{"light":"github-light-default","dark":"github-dark-default"}}
# run without installing
npx -y -p @arizeai/phoenix-cli pxi

# or install it globally
npm install -g @arizeai/phoenix-cli

# point it at your instance, and pick a model (defaults to claude-opus-5)
export PHOENIX_ENDPOINT=http://localhost:6006   # and PHOENIX_API_KEY if auth is on
pxi --provider OPENAI --model gpt-5.4
```

Requires Phoenix **20.0.0 or newer** and a configured model provider. Lines beginning with `/` are handled locally: `/help` lists them, `/compact` summarizes earlier turns. See the [CLI reference](/docs/phoenix/sdk-api-reference/typescript/arizeai-phoenix-cli#pxi) for every flag and command.

## Configuration

### Bring your own model

PXI runs on your model provider and your API key. Set credentials for Anthropic, OpenAI, Google, or AWS Bedrock through environment variables or Phoenix secrets, or add a custom provider under **Settings → AI Providers**.

### Permissions and approval

Agent assistance is opt-in.

* **Turn it off** per deployment (`PHOENIX_DISABLE_AGENT_ASSISTANT=true`), per instance (**Settings → Assistant → Permissions**), or per browser (**Settings → Assistant → General**).
* **State-changing actions wait for you.** Saving a prompt, writing dataset examples, or submitting an evaluator arrives as a diff or card you accept. Read-only actions run freely. **Bypass Approval** applies edits without asking and shows a warning while active.
* **Web access is per session**, through the globe button in the chat input, and only when an administrator allows it.

### Privacy and tracing

PXI runs inside your Phoenix process, on your data, with your model key. Arize is not in the request path.

* **Bash** runs in a sandboxed shell on the server with no network. `PHOENIX_AGENTS_DISABLE_BASH=true` removes it.
* **PXI sees whatever you can see**, so be deliberate on sensitive data.
* **Chats can be recorded as traces** in the `assistant_agent` project. Off by default; administrators turn it on under **Settings → Assistant**.
* **PXI makes mistakes.** Treat its output as suggestions.

### Configuration reference

The `DISABLE` and `FORCE` variables take `true`. The others take a URL, token, or name.

| Variable | Effect |
| - | - |
| `PHOENIX_DISABLE_AGENT_ASSISTANT` | Turn PXI off for the deployment. |
| `PHOENIX_ALLOW_EXTERNAL_RESOURCES` | `false` blocks all external access: docs lookups, web search and fetch, and GitHub tools. |
| `PHOENIX_AGENTS_DISABLE_WEB_ACCESS` | No web search or fetch. |
| `PHOENIX_AGENTS_DISABLE_BASH` | No server-side bash, subagents, or terminal agent. |
| `PHOENIX_AGENTS_DISABLE_GITHUB` | No GitHub issue tools. |
| `PHOENIX_AGENTS_ENABLE_MCP_CODE_MODE` | `false` gives PXI one tool per read-only REST endpoint instead of `search` and sandboxed `execute`. Independent of the `/mcp` server's `PHOENIX_ENABLE_MCP_CODE_MODE`. |
| `PHOENIX_AGENTS_GITHUB_MCP_URL` | Self-hosted GitHub MCP server URL. |
| `GITHUB_PERSONAL_ACCESS_TOKEN` | Fallback GitHub token for all users. |
| `PHOENIX_AGENTS_FORCE_TRACING` | Record and export every user's chats. |
| `PHOENIX_AGENTS_COLLECTOR_ENDPOINT` | Where exported chat traces go. |
| `PHOENIX_AGENTS_COLLECTOR_API_KEY` | Key for that collector. |
| `PHOENIX_AGENTS_ASSISTANT_PROJECT_NAME` | Project for recorded chats (default `assistant_agent`). |

## Feedback

PXI is in beta. Open an issue or start a discussion on [GitHub](https://github.com/Arize-ai/phoenix).