> ## Documentation Index
> Fetch the complete documentation index at: https://docs.eigenai.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Data Generate
> 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 Generate generates synthetic or sample data from scratch based on a provided MCP (schema/config), producing records that conform to the defined structure and constraints. You describe what kind of data you need, and the system generates realistic conversations tailored to your specifications.
## Two-Phase Generation Strategy
Generation uses a two-phase workflow to ensure quality:
1. **Phase 1: Pilot Optimization**: Runs several iterations, generating small batches for validation and refinement. You can provide feedback to improve or customize your personalized generation agentic system.
2. **Phase 2: Large-Scale Generation with Online Monitoring**: Uses the optimized generation agentic system from Phase 1 to generate your complete dataset at scale.
## Parameters
| Parameter | Required | Description |
| ---------------- | -------- | --------------------------------------------------------------------------------------------- |
| `domain` | Yes | The problem space or topic area (see [Domain](/products/eigendata-cli/core-concepts/domain)) |
| `request` | Yes | Description of data to generate |
| `final_samples` | Yes | Number of samples to generate |
| `schema_file` | One of | Path to a local [schema file](/products/eigendata-cli/core-concepts/function-schema) |
| `mcp_server_url` | One of | URL of an [MCP server](/products/eigendata-cli/core-concepts/mcp-server) providing the schema |
| `data_language` | No | Language mix specification |
| `reference_doc` | No | Path to reference documentation |
You must provide either `schema_file` or `mcp_server_url` as the function schema source.
This feature uses the standard [chatbot interaction flow](/products/eigendata-cli/core-concepts/chatbot-interaction). Describe what data you want to generate in natural language, and the CLI guides you through parameter collection and confirmation.
## Phase 1: Pilot Optimization
After you confirm the configuration, Phase 1 begins. The system runs several iterations, each producing a small batch of samples for validation.
The CLI displays a live progress tracker showing the current iteration, elapsed time, and workflow pipeline status.
### Provide Feedback
During each Phase 1 iteration, the CLI opens a browser-based review interface displaying the generated samples. You can:
* Review each generated conversation
* Add per-sample feedback in the provided text areas
* Submit with no feedback if the samples look good
Your feedback is summarized and used to refine the generation strategy for subsequent iterations, progressively improving output quality.
## Phase 2: Large-Scale Generation with Online Monitoring
Phase 2 starts automatically once Phase 1 completes. The system uses the optimized generation strategy to produce your full dataset at the target scale, processing in batches.
The CLI continues showing progress until the run finishes.
## Completion
Upon completion:
The sampling config file can be reused for future resample operations to skip Phase 1.
## Resample: Quick Generation with Saved Config
If you are satisfied with a previous generation, use resample to skip Phase 1:
## Output
After a run completes, results are saved under `outputs/` as a new run directory, for example:
* `outputs/generated_data_/`
Inside the run directory:
* `generated_data.jsonl` - The generated dataset in JSONL format
* `datapoints/` - One JSON file per sample (expanded view of `generated_data.jsonl`)
* `metadata.json` - Run metadata (task type, parameters, primary files, timestamps)
The [viewer](../utility-commands/view) can browse and render these outputs.
## Example Output: Tau2-Bench Airline Domain
Below is an example of 20 multi-turn function-calling dialogs generated for the [Tau2-Bench](https://github.com/sierra-research/tau2-bench) airline customer service domain. Each sample is a realistic conversation involving booking, modification, cancellation, refunds, and baggage handling — with tool calls to airline backend APIs.
**User:**
> Hi, this is Emma Smith, user id emma\_smith\_9363. I have three things I need handled across my bookings: 1) Please cancel reservation E9TZTU with a full refund. 2) Change the flights for reservation 1YVFB9 to travel on 2024-05-28 instead of 2024-05-27 AND upgrade to business class. 3) Add 2 checked bags to reservation ...
**Assistant** → `get_user_details({"user_id": "emma_smith_9363"})`
**Tool response:**
```json theme={null}
{"user_id": "emma_smith_9363", "name": {"first_name": "Emma", "last_name": "Smith"}, "membership": "silver", ...}
```
**Assistant** → `get_reservation_details({"reservation_id": "E9TZTU"})`
**Tool response:**
```json theme={null}
{"reservation_id": "E9TZTU", "origin": "PHL", "destination": "DTW", "cabin": "basic_economy", ...}
```
**Assistant:**
> I've pulled up your details. Let me walk through each request. For reservation E9TZTU — this is a basic economy round-trip flight from PHL to DTW. I need to let you know that basic economy reservations can only receive a refund as travel certificates, not a full cash refund ...
**Dataset statistics:**
* **20 samples**, averaging **37 messages** per dialog
* **4–20 tool calls** per conversation across functions like `get_user_details`, `get_reservation_details`, `cancel_reservation`, `update_reservation_flights`, `book_reservation`, and more
* Covers diverse scenarios: cancellation, flight modification, baggage updates, refunds, payment handling, insurance, and membership-related requests
20-sample JSONL file (OpenAI format)
Interactive HTML dialog viewer
## Using /execute
You can also run data-generate non-interactively via [`/execute`](../utility-commands/execute) with a YAML config.
**Prerequisites**
* You have a YAML configuration file available.
* You provide a schema source (`schema_file` or `mcp_server_url`).
```yaml theme={null}
task: data-generate
domain: airline customer service
request: Generate 10 multi-turn function-calling dialogs with diverse tool usage.
final_samples: 10
mcp_server_url: http://127.0.0.1:8009
```