A profile about the people, projects and experiences behind their work. Discover their career, contributions and connections.
Backed byDetails being loaded
Cosigned byDetails being loaded
Team on CosignDetails being loaded
Team
Team
5
Profile nameProfile nameProfile name
Team
5
Profile nameProfile nameProfile name
Cosigns Received
Cosigner name
A thoughtful collaborator who builds great products and supports the people around them.
Profile name
Cosigner name
A thoughtful collaborator who builds great products and supports the people around them.
Profile name
Loading organization
Organization name
A profile about the people, projects and experiences behind their work. Discover their career, contributions and connections.
Backed byDetails being loaded
Cosigned byDetails being loaded
Team on CosignDetails being loaded
Team
Team
5
Profile nameProfile nameProfile name
Team
5
Profile nameProfile nameProfile name
Cosigns Received
Cosigner name
A thoughtful collaborator who builds great products and supports the people around them.
Profile name
Cosigner name
A thoughtful collaborator who builds great products and supports the people around them.
Profile name
Loading organization
Organization name
A profile about the people, projects and experiences behind their work. Discover their career, contributions and connections.
Backed byDetails being loaded
Cosigned byDetails being loaded
Team on CosignDetails being loaded
Team
Team
5
Profile nameProfile nameProfile name
Team
5
Profile nameProfile nameProfile name
Cosigns Received
Cosigner name
A thoughtful collaborator who builds great products and supports the people around them.
Profile name
Cosigner name
A thoughtful collaborator who builds great products and supports the people around them.
Profile name
CIMO Labs
CIMO Labs There's an interesting tension in how AI systems get evaluated today.
For traditional product changes—ranking algorithms, pricing models, core features—teams at scale use A/B tests. Randomization, statistical significance, confidence intervals. The infrastructure is mature and the discipline is established.
But A/B tests are slow. Weeks of production traffic. Real users exposed to potentially worse variants. Infrastructure overhead to serve multiple models in parallel. For teams iterating on prompts or evaluating new models, that cycle time is prohibitive.
So teams use offline evaluations: generate responses, score with an LLM judge, compare averages. Fast, cheap, enables rapid iteration. The challenge is calibration.
This creates a tradeoff: rigorous but slow (A/B tests) versus fast but uncertain (uncalibrated offline evals).
We think there's a third option: offline evaluations with the statistical rigor of A/B tests. That requires making the causal assumptions explicit, calibrating judge scores to outcomes that matter, and quantifying uncertainty honestly.
Backed by
Loading investors
Founders
Loading founders
Cosigned by
Loading cosigns
Featured roles
Loading featured roles
Team
Loading company relationships
Team
5
Profile nameProfile nameProfile name
Team
5
Profile nameProfile nameProfile name
Loading company cosigns
Cosigner name
A thoughtful collaborator who builds great products and supports the people around them.
Profile name
Cosigner name
A thoughtful collaborator who builds great products and supports the people around them.