# Documentation

## Docs

- [Getting Started](https://docs.eigenai.com/index.md): EigenAI is a high-performance platform for model inference, fine-tuning, and deployment.
- [Deployments](https://docs.eigenai.com/platform/deployments.md): Deploy a model to a dedicated inference endpoint and call it via an OpenAI-compatible API.
- [Overview](https://docs.eigenai.com/platform/fine-tuning.md): Fine-tune a base model on your own dataset to adapt it for your use case.
- [RL](https://docs.eigenai.com/platform/fine-tuning/agent-rl.md): Train agents with reinforcement learning using verifiable reward functions and MCP tools.
- [Image Editing](https://docs.eigenai.com/platform/fine-tuning/image-editing.md): Fine-tune an image editing model on your own image pairs to learn specific styles, objects, or editing tasks.
- [SFT](https://docs.eigenai.com/platform/fine-tuning/sft.md): Supervised Fine-Tuning: train a model to follow instructions or adopt a new style using labeled conversation data.
- [Chatbot Interaction](https://docs.eigenai.com/products/eigendata-cli/core-concepts/chatbot-interaction.md): How you interact with EigenData-CLI through natural language to configure and run tasks.
- [Domain & Reference Document](https://docs.eigenai.com/products/eigendata-cli/core-concepts/domain.md): Learn about domains and reference documents in EigenData-CLI.
- [Function Schema](https://docs.eigenai.com/products/eigendata-cli/core-concepts/function-schema.md): Understand the function schema format used in EigenData-CLI for defining tool capabilities.
- [MCP Server](https://docs.eigenai.com/products/eigendata-cli/core-concepts/mcp-server.md): Understand how MCP (Model Context Protocol) servers integrate with EigenData-CLI.
- [Data Audit](https://docs.eigenai.com/products/eigendata-cli/core-features/data-audit.md): Inspect data against the schema and business rules, analyze function coverage, and produce a structured report highlighting issues, anomalies, coverage gaps, and quality metrics.
- [Data Generate](https://docs.eigenai.com/products/eigendata-cli/core-features/data-generate.md): Generates synthetic or sample data from scratch based on a provided MCP (schema/config), producing records that conform to the defined structure and constraints.
- [Data Repair](https://docs.eigenai.com/products/eigendata-cli/core-features/data-repair.md): Detects and resolves minor errors, inconsistencies, or malformed values in existing data, keeping changes minimal and targeted.
- [Schema Polish](https://docs.eigenai.com/products/eigendata-cli/core-features/schema-polish.md): Refines and improves an existing schema — cleaning up naming conventions, structure, types, and consistency without changing its core definition.
- [Schema-Triggered Patch](https://docs.eigenai.com/products/eigendata-cli/core-features/schema-triggered-patch.md): Automatically patches existing data when the MCP/schema is updated — reconciling records to align with the new schema without a full regeneration.
- [Demo Samples](https://docs.eigenai.com/products/eigendata-cli/datasets/apex-agent/demo.md): A free 10-task sample of the APEX Agent dataset — management consulting cases across Project Terrace (Floor & Decor) and Project Roku (CTV platform analysis).
- [Full Dataset](https://docs.eigenai.com/products/eigendata-cli/datasets/apex-agent/overview.md): The full APEX Agent corpus — long-horizon, tool-using tasks across investment banking, management consulting, and law, synthesized from scratch by EigenData-CLI.
- [Demo Samples](https://docs.eigenai.com/products/eigendata-cli/datasets/enterprise-bench/demo.md): A free, individually-audited 20-sample slice of Enterprise Bench — 10 multi-system operations trajectories and 10 read-only investigation QA tasks, organized in the tau-bench four-folder layout with a self-contained reward verifier per sample.
- [Full Dataset](https://docs.eigenai.com/products/eigendata-cli/datasets/enterprise-bench/overview.md): The full Enterprise Bench corpus — long-horizon, tool-using agent tasks set inside realistic simulated companies, spanning 27 enterprise environments and two task families, synthesized by EigenData-CLI.
- [Google Workspace](https://docs.eigenai.com/products/eigendata-cli/datasets/google-workspace.md): Everyday Google Workspace tasks — managing emails, calendars, sheets, and contacts in single-turn and multi-turn formats.
- [Datasets](https://docs.eigenai.com/products/eigendata-cli/datasets/index.md): Off-the-shelf datasets generated by EigenData-CLI for agent evaluation and training, spanning diverse domains and task complexities.
- [Demo Samples](https://docs.eigenai.com/products/eigendata-cli/datasets/mcp-atlas/demo.md): A free, individually-verified slice of MCP-Atlas Synthesis — both-ready bundles that pair a real agent trajectory (SFT) with a fully-restorable environment + claims-based reward (RL), one self-contained folder per task, with zero machine-specific paths.
- [Full Dataset](https://docs.eigenai.com/products/eigendata-cli/datasets/mcp-atlas/overview.md): The full MCP-Atlas corpus — multi-step, multi-server tool-use tasks over a ~40-server MCP graph, each frozen with a claims-based reward and a replayable environment snapshot. Built on the MCP-Atlas benchmark; data generated and verified by EigenData-CLI.
- [Demo Samples](https://docs.eigenai.com/products/eigendata-cli/datasets/mcp-mark/demo.md): A free 20-task sample of the MCPMark agentic dataset — 10 Filesystem tasks (Sorrentino Bespoke Travel) and 10 GitHub tasks (google/gif-for-cli), each with its environment, task spec, and a full agent trajectory.
- [Full Dataset](https://docs.eigenai.com/products/eigendata-cli/datasets/mcp-mark/overview.md): The full MCPMark corpus — synthetic, agentic filesystem + GitHub tasks with deterministic Python verifiers, 1,233 tasks across 95 self-contained worlds, runnable fully offline. Generated and verified by EigenData-CLI.
- [Demo Samples](https://docs.eigenai.com/products/eigendata-cli/datasets/personal-agent-bench/demo.md): A free, runnable 12-task sample of Personal Agent Bench — four task families (tax packet, tax return filing, reimbursement packet, subscription audit) across three seeds, with a worked example and frontier-model grading.
- [Full Dataset](https://docs.eigenai.com/products/eigendata-cli/datasets/personal-agent-bench/overview.md): The full Personal Agent Bench corpus — long-horizon, tool-using tasks set in synthetic personal-laptop environments (tax, finance ops, personal admin), synthesized from scratch by EigenData-CLI.
- [Demo Samples](https://docs.eigenai.com/products/eigendata-cli/datasets/tau2-bench/demo.md): A free sample of the Tau2-Bench dataset — multi-turn customer-service dialogs across airline, telecom, and retail, each grounded in a stateful backend and a written agent policy.
- [Full Dataset](https://docs.eigenai.com/products/eigendata-cli/datasets/tau2-bench/overview.md): The full Tau2-Bench corpus — multi-turn, policy-grounded customer-service dialogs across airline, telecom, and retail, generated by EigenData-CLI.
- [Demo Samples](https://docs.eigenai.com/products/eigendata-cli/datasets/tau3-bench/demo.md): A free 10-task sample of the Tau3-Bench dataset — hard banking dialogs with discoverable tools, identity verification, and executable per-task evaluators.
- [Full Dataset](https://docs.eigenai.com/products/eigendata-cli/datasets/tau3-bench/overview.md): The full Tau3-Bench corpus — hard, single-domain banking dialogs with dynamically discoverable tools, knowledge-base-grounded policy, and executable per-task evaluators, generated by EigenData-CLI.
- [Demo Samples](https://docs.eigenai.com/products/eigendata-cli/datasets/toolathlon/demo.md): A free sample of the Toolathlon dataset — single-turn, multi-app agent tasks over 32 MCP tool servers, with deterministic grading, SFT trajectories, and self-contained RL environments.
- [Full Dataset](https://docs.eigenai.com/products/eigendata-cli/datasets/toolathlon/overview.md): The full Toolathlon corpus — single-turn, tool-using agent tasks over a multi-application MCP workspace with 32 tool servers, 102 task families, and 4,300 RL environments with deterministic grading, generated and verified by EigenData-CLI.
- [Demo Samples](https://docs.eigenai.com/products/eigendata-cli/datasets/wildclaw-bench/demo.md): A free, fully-verified 30-task sample of WildClawBench — agentic tool-use tasks across five categories, organized in the tau-bench four-folder layout with a runnable reward verifier per sample.
- [Full Dataset](https://docs.eigenai.com/products/eigendata-cli/datasets/wildclaw-bench/overview.md): The full WildClawBench corpus — long-horizon, tool-using agent tasks across six capability categories, from PDF parsing to code debugging to safety alignment. Built on InternLM's WildClawBench benchmark; data generated and verified by EigenData-CLI.
- [Getting Started](https://docs.eigenai.com/products/eigendata-cli/getting-started.md): Install, configure, and start using EigenData-CLI in minutes.
- [What is EigenData-CLI](https://docs.eigenai.com/products/eigendata-cli/intro.md): EigenData-CLI is a natural language-driven command-line tool for generating, refining, auditing, and repairing high-quality function-calling agent data.
- [Troubleshooting](https://docs.eigenai.com/products/eigendata-cli/reference/troubleshooting.md): Common issues and solutions when using EigenData-CLI.
- [/configure](https://docs.eigenai.com/products/eigendata-cli/utility-commands/configure.md): Update EigenData-CLI settings including API key, MCP server URL, and schema file.
- [/execute](https://docs.eigenai.com/products/eigendata-cli/utility-commands/execute.md): Run tasks from a YAML configuration file for reproducible experiments and batch processing.
- [/tutorial](https://docs.eigenai.com/products/eigendata-cli/utility-commands/tutorial.md): Toggle tutorial hints on or off during your EigenData-CLI session.
- [/version](https://docs.eigenai.com/products/eigendata-cli/utility-commands/version.md): Display the current version of EigenData-CLI.
- [/view](https://docs.eigenai.com/products/eigendata-cli/utility-commands/view.md): Launch the web-based data viewer to browse and inspect generated datasets.
- [Base URL](https://docs.eigenai.com/products/model-api/api-reference/base-url.md): Production base URLs for all API requests.
- [Create Chat Completions](https://docs.eigenai.com/products/model-api/api-reference/chat-completions.md): Create a chat completion from a list of messages.
- [Generate Audio](https://docs.eigenai.com/products/model-api/api-reference/generate-audio.md): Transcribe audio to text (ASR) or synthesize speech from text (TTS).
- [Generate Image](https://docs.eigenai.com/products/model-api/api-reference/generate-image.md): Generate or edit images depending on the selected model.
- [Generate Video](https://docs.eigenai.com/products/model-api/api-reference/generate-video.md): Submit an image-to-video generation job and retrieve the result asynchronously.
- [Stream Audio (WebSocket)](https://docs.eigenai.com/products/model-api/api-reference/stream-audio.md): Stream real-time audio generation over a WebSocket connection.
- [Upload Voice Reference](https://docs.eigenai.com/products/model-api/api-reference/upload-voice.md): Upload a voice reference audio file to get a voice_id for use in TTS requests.

## OpenAPI Specs

- [openapi](https://docs.eigenai.com/api-reference/openapi.json)