Markdown source

Advanced workshop: Mastering AI Observability

Conference Context

• Date/time: 2026-06-29 · 9:00am-11:00am
• Track/room: track TBD · Track 9
• Speaker(s): Doug Guthrie
• Session type/status: session · confirmed

• Track: track TBD
• Room: Track 9
• Session type: session
• Status: confirmed

Session Description

Your AI is in production, but is it actually good? In this hands-on workshop, you'll learn how to uncover patterns in your production traces using Braintrust Topics, build custom scorers to target real issues, and systematically improve your agent. By the end, you'll have a repeatable eval workflow and trace-backed evidence that your AI is actually doing what you think it is.

Media Evidence

Evals 101 — Doug Guthrie, Braintrust (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).

• youtube bk0TmxoZlUY transcript — full cached transcript markdown for the related YouTube source.

• Source video: youtube-bk0TmxoZlUY
• Slide deck: Dense Slides: Evals 101 — Doug Guthrie, Braintrust — 1 visible slide image(s); 1 HTML recreation(s).



• Additional slide evidence: Slides: Evals 101 — Doug Guthrie, Braintrust, Reconstructed Slides: Evals 101 — Doug Guthrie, Braintrust

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

• youtube-bk0TmxoZlUY — 9,125 transcript words
• Transcript signals for youtube-bk0TmxoZlUY: maybe, trust, brain, within, data, scores, eval, application.
• Evidence links for youtube-bk0TmxoZlUY: youtube bk0TmxoZlUY, youtube bk0TmxoZlUY transcript, youtube bk0TmxoZlUY slides, youtube bk0TmxoZlUY dense slides, youtube bk0TmxoZlUY reconstructed slides

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

Related video transcript availability: English auto-captions. Treat this as supporting context, not a recording of this exact scheduled session unless later confirmed. Cached at raw/sources/youtube-transcripts/bk0TmxoZlUY.txt (9,125 words).

People

• doug guthrie

Supporting Slides

• youtube bk0TmxoZlUY slides — extracted from the related public AI Engineer video.

Slide Evidence

• Slide-only cropped deck: youtube bk0TmxoZlUY dense slides (1 viable slide images).
• Related slide/OCR pages:
• youtube bk0TmxoZlUY dense slides
• youtube bk0TmxoZlUY reconstructed slides
• youtube bk0TmxoZlUY slides
• Slide-derived terms: evals, microsoft, prompt, braintrust, scorer, improve, eval, scorers, smol, code, zapier, model, quality, test, dataset, input, rome, datasets

Attendance Visibility

No high-confidence attendance icon signal is shown for this talk. The sampled video evidence was either low confidence, source-proxy-only, or did not expose a clear audience view.

Synthesis

Synthesized Breakdown

Hey everybody, my name is Doug Guthrie. Uh, I'm a solutions engineer at Brain Trust. Um, as you can see here, we're an endto-end developer platform for building AI products. We do evals.

Speaker And Company Context

• Doug Guthrie — Solutions Engineer at Braintrust.

Topics Covered

• agent security
• agentic search
• coding agents

Derived Links And Source Material

• youtube bk0TmxoZlUY transcript — transcript markdown; source cache raw/sources/youtube-transcripts/bk0TmxoZlUY.txt (9,125 words).
• youtube bk0TmxoZlUY — related YouTube source page.
• youtube bk0TmxoZlUY slides — slide evidence.
• youtube bk0TmxoZlUY reconstructed slides — slide evidence.
• youtube bk0TmxoZlUY dense slides — slide evidence.

Novel Concepts / Clever Methods

• No highlighted novel concept has been detected yet.

Evidence Boundary

This synthesis uses the official schedule plus cached video transcripts. Official AI Engineer World's Fair San Francisco 2026 livestreams and cut videos are primary event video sources for transcript/slide evidence; external, historical, or speaker-matched videos remain supporting context unless manually verified as exact official event recordings.