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

ℹ️ 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

What does AI actually know about you?

Can you trust what AI tells you?

How Ramp engineers work with AI agents at every step

What happens when you talk to AI?

How auto mode works with Claude Code

Building AI-native across industries with NTT, Mizuho and Mercari