> ## Documentation Index
> Fetch the complete documentation index at: https://levers9.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Every feature

> A map of the platform, one line per feature, with where to read more

## Run code

| feature | what it does | read |
| - | - | - |
| `@job` | run a Python function in a container: `.remote()` once, `.map()` one container per item | [CPU job](https://levers9.mintlify.site/demos/cpu_job.md) |
| `@endpoint`, `@asgi`, `@realtime` | a function, an ASGI app or a WebSocket app behind an HTTP URL with keep-warm and autoscaling | [Endpoint](https://levers9.mintlify.site/demos/endpoint.md) |
| `@queue` | background work with retries, fed from Python or HTTP | [Queue](https://levers9.mintlify.site/demos/queue.md) |
| `@cron` | a function on a cron expression (UTC) | [Cron](https://levers9.mintlify.site/demos/cron.md) |
| `Box` | any long-running process with ports: servers, databases, notebooks | [Box, shell and run](https://levers9.mintlify.site/demos/box.md) |
| `Sandbox` | an isolated container you drive from Python: run code, manage files, expose ports, snapshot memory | [Sandbox](https://levers9.mintlify.site/sdk/sandbox.md) |
| `Blueprint` | Python version, pip and apt packages, shell commands, Docker-in-Docker; built once, content-addressed | [Blueprint](https://levers9.mintlify.site/demos/blueprint.md) |
| `Volume`, `CloudBucket` | persistent files shared between containers; S3 or GCS buckets mounted directly | [Volumes](https://levers9.mintlify.site/demos/volumes.md) |
| secrets | API keys injected as environment variables | [Secrets](https://levers9.mintlify.site/demos/secrets.md) |
| GPUs | `gpu="L40S"` or a preference list; T4 to H200 and RTX PRO 6000 | [GPU](https://levers9.mintlify.site/demos/gpu.md) |
| pipelines | chain functions on a volume: prep, train in parallel, evaluate, package | [Pipeline](https://levers9.mintlify.site/demos/pipeline.md), [GPU pipeline](https://levers9.mintlify.site/demos/gpu_pipeline.md) |
| `VLLM` | serve an open-weights model behind an OpenAI-compatible URL | [LLM serving](https://levers9.mintlify.site/sdk/llm-serving.md) |
| `MCPServer` | deploy a FastMCP server as a URL tools can call | [MCP server](https://levers9.mintlify.site/sdk/mcp-server.md) |
| `Output` | save a file from inside a container and get a download URL | [Parameters](https://levers9.mintlify.site/sdk/parameters.md#outputs) |
| `levers9 serve` | a temporary URL with hot reload while you develop | [CLI](https://levers9.mintlify.site/guides/cli.md) |
| `levers9 shell`, `run`, `dev` | an interactive shell, a one-off container, a remote dev box | [CLI](https://levers9.mintlify.site/guides/cli.md) |

## Watch and operate

| feature | what it does | read |
| - | - | - |
| Apps | every function and deployment with its description (from the docstring), its calls in order, each labelled with its arguments, containers, logs and an execution timeline per call | [Apps](https://levers9.mintlify.site/dashboard/apps.md) |
| Containers | what is running now, with live output and a stop button | [Containers and workers](https://levers9.mintlify.site/dashboard/containers-and-workers.md) |
| Workers and pools | the worker processes per node, pool, CPU, memory and GPU in use; workspace metrics | [Containers and workers](https://levers9.mintlify.site/dashboard/containers-and-workers.md) |
| Storage | a file browser per volume with upload, download, previews, and where each volume is mounted | [Storage and secrets](https://levers9.mintlify.site/dashboard/storage-and-secrets.md) |
| Secrets | create from integration templates, rotate, delete | [Storage and secrets](https://levers9.mintlify.site/dashboard/storage-and-secrets.md) |
| Notebooks | JupyterLab boxes with a native notebook editor, file browser, live CPU/memory/GPU meters, attached volumes and secrets | [Notebooks](https://levers9.mintlify.site/guides/notebooks.md) |
| Endpoints | a curated open-weights model catalog with GPU fit, deployed with vLLM in one click | [Endpoints](https://levers9.mintlify.site/dashboard/endpoints.md) |
| Workspaces | one per email domain or per team; invite members by email | [Workspaces and environments](https://levers9.mintlify.site/dashboard/workspaces.md) |
| Environments | `main`, `staging`, a branch, a client: each a separate controlplane workspace; `levers9 login --env NAME` | [Workspaces and environments](https://levers9.mintlify.site/dashboard/workspaces.md) |
| Sign-in | Google sign-in for the dashboard and the CLI, or a plain token when self-hosting | [Sign-in](https://levers9.mintlify.site/guides/sign-in.md) |
| Empty states | every page that can be empty says what it is for with a drawn animation: a recording cut into labelled clips, a notebook cell running, files stacking on a volume, a secret masked into an environment variable, a request and its reply, a worker taking a container | |
| Insights | interactive analytics over datasets, the Arena and tasks: build a chart or a number, click to filter everything, pin to a board, drill to rows, SQL and questions in words | [Insights](https://levers9.mintlify.site/lab/insights.md) |
| Anonymization | one scan per dataset finds phones (written or said out loud), IDs, IBANs, cards, emails and names and writes a masked copy; a policy per dataset (Off, Flag, Mask) decides whether share links, published files, draft models and Insights read that copy; a review of a random sample of rows measures the scan (precision and recall per type, each with its range) and fixes the masking of every row reviewed | [Personal data](https://levers9.mintlify.site/lab/personal-data.md) |
| Agent skills | a SKILL.md per feature for Claude Code, Cursor and Codex; `levers9 skills install` | [Skills and MCP for AI agents](https://levers9.mintlify.site/guides/agent-skills.md) |
| MCP servers | the docs as an MCP server, and the workspace as one: deployments, tasks, logs, GPU capacity, invoke (`levers9 mcp` or the dashboard API's `/mcp`), and deploy from the local one | [Skills and MCP for AI agents](https://levers9.mintlify.site/guides/agent-skills.md) |

## Data Lab

| feature | what it does | read |
| - | - | - |
| Datasets | import audio or text from volumes, S3, GCS, BigQuery, Hugging Face or URL lists; chunk audio into clips | [Datasets](https://levers9.mintlify.site/lab/datasets.md) |
| Decision gold sets | a human gold set for a decision model: reviewers answer typed questions about a lead, mark the events that caused each answer, say how it would change without an event and review the logged decision; exported as JSON lines with twin records, and the questions as a schema | [Decision gold sets](https://levers9.mintlify.site/lab/decision-gold-sets.md) |
| Pre-labelling | optional drafts from Whisper, Azure, Google, ElevenLabs, Kokoro, vLLM, Anthropic or OpenAI, and from a Decision API for a decision dataset | [Datasets](https://levers9.mintlify.site/lab/datasets.md#pre-labelling) |
| Annotation | a keyboard-driven editor for transcripts, roles, replies and clip quality, with statuses and filters | [Annotation](https://levers9.mintlify.site/lab/annotation.md) |
| Spreadsheet round-trip | export TSV, edit anywhere, import back | [Annotation](https://levers9.mintlify.site/lab/annotation.md#spreadsheets) |
| Sharing | named links per annotator, an anyone-with-the-link option, viewer or annotator roles | [Sharing](https://levers9.mintlify.site/lab/sharing.md) |
| NDA gate | an agreement annotators sign before they see a row; versioned wording | [Sharing](https://levers9.mintlify.site/lab/sharing.md#nda) |

## RL Arena

| feature | what it does | read |
| - | - | - |
| Call logs | real calls in through a webhook, a dataset or paste; every reply scored on the rubric | [Call logs](https://levers9.mintlify.site/lab/call-logs.md) |
| Scenarios | thousands of moments grouped automatically into a few dozen situations, on a map you can pan, zoom and select | [Scenarios](https://levers9.mintlify.site/lab/scenarios.md) |
| Arena | simulated customers with personas and moods talk to a policy; fork any conversation at any turn | [RL Arena](https://levers9.mintlify.site/guides/rl-arena.md) |
| Compare | two replies for one moment; pick the better one and tick why | [Train and evaluate](https://levers9.mintlify.site/lab/train-and-evaluate.md) |
| Train | preferences become a new policy version instantly; DPO with LoRA on a GPU for weights | [Train and evaluate](https://levers9.mintlify.site/lab/train-and-evaluate.md#train) |
| Evaluate | two versions on the same customers and seeds: win rate, mean reward, per-dimension radar, regressions | [Train and evaluate](https://levers9.mintlify.site/lab/train-and-evaluate.md#evaluate) |
| Policies | versions with lineage; make one live | [Train and evaluate](https://levers9.mintlify.site/lab/train-and-evaluate.md#policies) |
| Culture pack | the market's rubric, guardrails and personas; draft one from your playbooks | [Culture pack](https://levers9.mintlify.site/guides/culture-pack.md) |
| Tenants | one client per tenant, each with its own pack, webhook key and filters | [Call logs](https://levers9.mintlify.site/lab/call-logs.md#tenants) |


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