AI & ML interests
Private evals, RL environments and training data for AI agents on real creative jobs. First up, video editing.
Recent Activity
Papers
View all Papers
AI training data, evals, and RL environments
Training data, evals, and RL environments for AI labs, robotics companies, and enterprises. Custom datasets, production traces, and domain-expert staffing.
VIDEO EDITING · TIMELINEBENCH
Agents say they’re done. Most aren’t.
TimelineBench gave 16 agent setups 56 real editing jobs. Each is a whole job: raw footage, audio and a brief in, a finished cut out. A run resolves only if it passes hard checks on delivery, content and the brief, and a quality test calibrated on blind judgments by 43 professional editors.
What we build
Private evals
Available nowWe run your unreleased checkpoint or agent on our jobs and send a failure report. Results stay private.
RL environments
Scoped with your teamOur jobs, packaged for your sandbox, with our checks exposed as the reward.
Training and eval data
CommissionedPre-training and post-training data, custom datasets, and production traces scoped to your workflows.
Domain-expert staffing
We staff domain experts onto your team for data and evaluation work.
Tell us what you need. Terms are scoped per engagement.
The three founders wrote TimelineBench.
Two of us were Research Fellows at Microsoft Research India. Papers at NeurIPS, ACL Findings, EACL, Interspeech and CSCW.
- Pavan Kalyan Tankala CEO
- Nirmit Arora CTO
- Gunin Gupta CBO
- Y Combinator W26