---
title: "Hill-climbing Skills: How to Improve Agents Without Touching the Model"
category: "talks"
date: "2026-06-29"
time: "4:30pm-5:30pm"
track: "Workshops Day 1"
room: "Track 4"
speakers: ["Shubhankar Srivastava"]
sourceLabels: ["Official conference schedule", "Public YouTube metadata"]
scheduleTrack: "Workshops Day 1"
scheduleRoom: "Track 4"
scheduleLabels: ["Workshops Day 1", "Track 4", "workshop", "confirmed"]
---
# Hill-climbing Skills: How to Improve Agents Without Touching the Model

## Conference Context
- Date/time: 2026-06-29 · 4:30pm-5:30pm
- Track/room: Workshops Day 1 · Track 4
- Speaker(s): Shubhankar Srivastava
- Session type/status: workshop · confirmed

- Track: Workshops Day 1
- Room: Track 4
- Session type: workshop
- Status: confirmed

## Session Description
Agent Capability is now highly dependent on the markdown files read at runtime -- skills.This workshop treats skills as a first-class optimization surface. We borrow the concept of autoresearch (from Karpathy) and apply it to the skills your agents already read. You'll see how we at Browserbase did the same for browser agents, enabling our customers to scale the coverage of their browser agents while improving performance(2x faster runs) and optimizing for token spend(upto 10x cheaper).You'll leave with a working http://SKILL.md you generated through an auto-research loop, and a mental model for when skill optimization beats fine-tuning or prompt engineering.

## Media Evidence
No related AI Engineer channel video found yet.

## Evidence Graph
This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.

### Media Signals
No linked video, transcript, or slide source has been attached yet.

### Agent Reading Notes
Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.

## Transcript Status
No official session recording transcript was found by exact title match on the AI Engineer YouTube channel during this run.

## People
- [[shubhankar-srivastava]]

## Notes
- Pending transcript synthesis when an official recording or confirmed matching video is available.

## Synthesis
### Synthesized Breakdown
# Hill-climbing Skills: How to Improve Agents Without Touching the Model ## Conference Context - Date/time: 2026-06-29 · 4:30pm-5:30pm - Track/room: Workshops Day 1 · Track 4 - Speaker(s): Shubhankar Srivastava - Session type/status: workshop · confirmed - Track: Workshops Day 1 - Room: Track 4 - Session type: workshop - Status: confirmed ## Session Description Agent Capability is now highly dependent on the markdown files read at runtime -- skills.This workshop treats skills as a first-class optimization surface. We borrow the concept of autoresearch (from Karpathy) and apply it to the skills your agents already read. You'll see how we at Browserbase did the same for browser agents, enabling our customers to scale the coverage of their browser agents while improving performance(2x faster runs) and optimizing for token spend(upto 10x cheaper).You'll leave with a working http://SKILL.md you generated through an auto-research loop, and a mental model for when skill optimization beats fine-tuning or prompt engineering. ## Media Evidence No related AI Engineer channel video found yet.

### Speaker And Company Context
- [[shubhankar-srivastava|Shubhankar Srivastava]] — Founding Sales Engineer at [[browserbase|Browserbase]].

### Topics Covered
- [[agentic-search]]
- [[agentic-web]]
- [[ai-sandboxes]]

### Derived Links And Source Material

### Novel Concepts / Clever Methods
- No highlighted novel concept has been detected yet.

### Evidence Boundary
This synthesis is based on the official schedule and linked source pages. It should be revisited when exact session recordings or transcript-backed secondary sources are available.