Skip to content
ClaudeClaude

Evals for taste: Hill-climbing a slide-generation agent

Built rubric-driven replayable eval system from real user projects giving quality, cost, latency, error, token signals in under 6 hours per model change. Evolved into dev flywheel powered by real user dissatisfaction signals.

May 23, 202639mWatch on YouTube ↗

Episode Details

EPISODE INFO

Released
May 23, 2026
Duration
39m
Channel
Claude
Watch on YouTube
▶ Open ↗

EPISODE DESCRIPTION

Built rubric-driven replayable eval system from real user projects giving quality, cost, latency, error, token signals in under 6 hours per model change. Evolved into dev flywheel powered by real user dissatisfaction signals.

EPISODE SUMMARY

In this episode of Claude, Evals for taste: Hill-climbing a slide-generation agent explores building actionable evals to iteratively improve slide-generation agents fast Evals are positioned as the actionable bridge between subjective “vibes” and measurable signals for improving AI agents before issues hit production.

RELATED EPISODES

DoorDash gave every employee Claude Code

DoorDash gave every employee Claude Code

Photographing the stars with Claude

Photographing the stars with Claude

Claude Fable 5: working at the frontier

Claude Fable 5: working at the frontier

How Squidsoup makes art installations with Claude

How Squidsoup makes art installations with Claude

The future of work with @Claude

The future of work with @Claude

The Explore → Plan → Code → Commit workflow in Claude Code

The Explore → Plan → Code → Commit workflow in Claude Code

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.