
Lakshya A Agrawal
Lakshya A Agrawal is a computer science PhD student at UC Berkeley and creator of GEPA. His research explores AI systems that improve through experience by optimizing prompts, agent harnesses and model weights.
- Videos
- 1
- Channels
- 1
- Topics
- 3
0 comments · 0 votes
Video topic coverage
Based on 1 reviewed video for Lakshya A Agrawal; compared with all 3137 public reviewed videos. Catalogue coverage, not expertise or speaking time.
Unmapped topics: 0 for this person; 23 in all videos. Scores cover mapped topics only.
- Lakshya A Agrawal (1 video; normalised to 100%)
- All videos (3137; normalised to 90%)
Both plots connect neighbouring topic values in the same ten-axis order, including zeros at the centre. The blue person plot is proportionally normalised to a 100% maximum and the white baseline to 90%. Each plot uses its own scale, showing relative topic emphasis; the values below show actual coverage.
- Agents & workflows100%55.7%
- Coding & tools0%39%
- Models & learning0%36.9%
- Infrastructure & compute0%21.2%
- Research & evaluation100%38.6%
- Safety & security0%28.2%
- Business & productivity0%25.6%
- Creative & media0%6.4%
- Robotics & perception0%5.1%
- Society & policy0%16.6%
Topic attribution
Both datasets use the same explicit fractional topic memberships. For each video, only the strongest membership in each group counts. We average those values across distinct public reviewed videos, including untagged videos. The all-video baseline includes this person's videos. Both datasets come from the same active catalogue snapshot and are independent of filters and viewing history. Groups overlap, so percentages do not need to total 100. Weights describe topic membership, not measured speaking time or relationship confidence.
Topics associated with this person:
- AI Agents: Agents & workflows: 100%
- AI Evaluation: Research & evaluation: 100%
- AI Research: Research & evaluation: 100%
Videos with Lakshya A Agrawal
Share Lakshya A Agrawal's AI video profile
Lakshya A Agrawal is a computer science PhD student at UC Berkeley and creator of GEPA. His research explores AI systems that improve through experience by optimizing prompts, agent harnesses and model weights.

