Scaling AI alphafinancial AIevaluations

What we do

We generate resumes for financial AI agents

Agents

Evaluated on vibes

Evaluated on actual performance

IQ: 160
Graduated from: Anthropic
Harness: Claude Code
Data: Cap IQ
Past achievements: 5-year track record running your fundamental LS strategy
Assessment: 1 personality test + 3 task-specific tests + 2-hour technical interview

Agentic components

Paying for general claims

Paying for true additivity

Information coefficient

Current data feedAI-ready data feed

We have developed a proprietary eval pipeline to quantify the performance of financial AI agents and the additivity of their components.

unlock potential

The same portfolio manager agent, before and after evals.

pre-eval agentpost-eval agent

We believe that AI alpha can be achieved through systematic evals. Witness our real-life demonstration here: live agent

Eval database
- –
  Access to our proprietary eval database across common models, harnesses, and datasets.
- –
  Go beyond headline metrics: agent outputs, behaviors, biases, and risks.
Proprietary research
- –
  Access to commentaries and guides from our proprietary evals and in-house alpha strategy.

For AI investors
- –
  Evals tailored to your agentic specification and vision — choose the model, harness, data, and strategy.
For AI product providers
- –
  Customized evals on your AI product — quantifying the additivity of your data, model, or harness to AI agent alpha.

In-house agents
- –
  Access to our in-house alpha agents, continuously evolved through our proprietary evals.
Investment signals
- –
  Leverage the alpha signals generated by our in-house agents, each developed and tested through our institutional-grade systematic research pipeline.

Evals done by industry practitioners and pioneers with skin in the game.

Our proprietary eval platform, built for any agent and any financial task.