v0.9.0 — public beta

synthpanel

Run synthetic focus groups with any LLM.

Define personas in YAML. Define your research instrument in YAML. Run against Claude, GPT, Gemini, Grok, or any OpenAI-compatible model — from your terminal, a pipeline, or an AI agent's MCP tool call.

$ pip install synthpanel

Add [mcp] for Claude Code / Cursor / Windsurf agent integration.

GitHub repo → PyPI package

MCP Server

Give your AI coding assistant access to synthetic focus groups. Drop this config into your editor and start running panels from chat. 

// Claude Code · Cursor · Windsurf · Zed
{
  "mcpServers": {
    "synth_panel": {
      "command": "synthpanel",
      "args": ["mcp-serve"],
      "env": { "ANTHROPIC_API_KEY": "sk-..." }
    }
  }
}
Claude Code Cursor Windsurf Zed Claude Desktop Full MCP docs →

Requires pip install synthpanel[mcp]. 12 tools: run prompts, run panels, manage persona & instrument packs, and more.

Quick start 

# 1. install
pip install synthpanel

# 2. set a key for any provider you have
export ANTHROPIC_API_KEY="sk-..."

# 3. one-shot prompt against the default model
synthpanel prompt "What do you think of the name Traitprint?"

# 4. run a full panel
synthpanel panel run \
  --personas examples/personas.yaml \
  --instrument examples/survey.yaml

MCP server

→

Drop-in config for Claude Code, Cursor, Windsurf, Zed, and Claude Desktop. 12 tools.

PyPI

→

Pip-installable package. pip install synthpanel.

GitHub

→

Source, issues, and roadmap. MIT-licensed.

SynthBench

→

Open benchmark for synthetic survey quality. See the leaderboard at synthbench.org.

Powered the SynthBench public benchmark — independent, open evaluation of synthetic-respondent quality. Ensemble blending of 3 models hits SPS 0.90 (90% human parity) on the current leaderboard.

Further reading