Build domain-expert AI from messy historical data

Lightning Rod turns raw documents and public sources into verified training sets and compact domain experts — without hand-labeling.

Trusted by enterprise, government, and startups

Generate verified training data from real-world outcomes.

Prompt to AI

Describe what you want. Our agent handles the rest.

Lightning Rod Agent
No install required
I want to predict the likelihood of geopolitical events using news data.
Got it. I'll pull from Reuters and AP News — about 18 months of coverage. Does that work?
Yes, go ahead.
Gathering sources now. You can track progress on the right.
Reply to agent...
Gather sources
2
Generate questions
3
Resolve outcomes
4
Add context
5
Train model

Used to train frontier-beating models.

Feb 2026 UChicago Leaderboard

#1 on ProphetArena Sports

Foresight-32B ranked #1, ahead of GPT-5.2 and Gemini 3 Pro.

Jan 2026 Benchmark

Top 5 on ForecastBench

Outperformed Gemini 3 Pro, Claude Sonnet 4.5, and o3 on the Forecasting Research Institute benchmark.

2025–2026 Peer Reviewed

Cutting Edge Research

Beating frontier models using our novel Future-as-Label methodology.

See Research & Benchmarks

Simple, powerful API

Generate verified datasets in a few lines of code. Our SDK handles the complexity.

  • Grounded in real outcomes and source documents
  • Bootstrap with public feeds: news, SEC filings, Wikipedia
  • Full provenance with citations and source docs
GitHub Examples on HuggingFace
build_dataset.py
from lightningrod import Pipeline

pipeline = Pipeline([
    NewsSeedGenerator(query="AI regulation"),
    ForwardLookingQuestionGenerator(
        instructions="Generate questions about future AI regulations and rulings"
    ),
    WebSearchLabeler()
])

dataset = pipeline.run(n_samples=100)

Trusted by enterprise, government, and startups.

We got back 10,000 high-quality, citable QA pairs in hours — we were fine-tuning the next day.

Joe Phongpreecha
Joe Phongpreecha
Co-founder & CEO, Takeoff 41

Lightning Rod is the only solution that turns messy sources into high-quality, verified training data.

Ross Koenig
Ross Koenig
Chief Data Officer, Shore Capital Partners

Thousands of high-confidence Q&A pairs in an incredibly short time — something that would have taken our team weeks manually.

BB Chen
BB Chen
Co-founder, CareTie

We went from idea to deployment in a single sprint. Without this, we would have been stuck in a proof-of-concept loop for months.

Paul Alexander
Paul Alexander
CTO, Caremaze

10,000 labeled examples that we immediately put to work in our eval pipeline, teleporting us weeks ahead.

Andrew Becker
Andrew Becker
CEO, InPolicy.ai

Incredibly easy way to generate high-quality datasets from public sources.

Adam Goldenberg
Adam Goldenberg
CEO, Fabletics

Train AI experts for any domain.

See how Lightning Rod turns your sources into verified training data in minutes.

Get Started Book a Demo