About
We build custom evals for product teams, as a service. To build these eval sets, we source domain experts and have them turn their work into original, real world evals. For example, our research engineering experts have create tasks involving optimizing an algorithm, deploying a model, or running experiments to solve a novel problem. A grader scores the agent’s performance, and these scores serve as signals during evaluations.
Founders
Perbhat Kumar· Founderceo at Glue. prev engineer at Amazon and Microsoft. worked on a home launcher redesign for Kindle Fire, and built enterprise-scale rag agents at Microsoft Copilot Studio. now focused on building interface design tools for ai agents.
Tejas Priyadarshi· FounderCo-founder & CTO of Glue. Building a design interface that natively operates on code. Prev. engineer at Microsoft and Meta.
Change history · 14 recorded
- September 11, 2026
- Description rewritten07:00 PM
- Website updated07:00 PM
- August 29, 2026
- Description rewritten07:00 PM
- Pitch updated07:00 PM
- Team reduced from 2 to 107:00 PM
- Industry reclassified to B2B07:00 PM
- Industries updated07:00 PM
- Tags updated07:00 PM
- July 22, 2026
- Industry reclassified to Industrials07:00 PM
- Industries updated07:00 PM
- Tags updated07:00 PM
- Former names updated07:00 PM
- Description rewritten07:00 PM
- Pitch updated07:00 PM