Markdown source

How Juries and Librarians Can Solve GTM's AI Trust Problem

Conference Context

Session Description

A couple of years ago, everyone worried about AI hallucinating. We rarely hear that word anymore, but it’s just because the problem grew up. Today, your AI still doesn’t know how to say “I’m not sure.” Instead, it hands you a revenue number that’s wrong in ways that look exactly like being right. The good news is we already solved this once, for people: you onboard a new hire so they understand your business; you put subjective, high-stakes calls in front of more than one set of eyes. This talk walks through patterns we run at Upside, including a librarian every agent consults before it acts, a jury-and-judge model for the questions a single pass can’t be trusted to answer, and knowing when the model itself is just too dumb for the job. Live demos and real failures included.

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.

Summary

Alex Bauer's AI in GTM session treats trust as an operational problem inside revenue systems, not as a generic model-behavior lecture. The official description says the dangerous failure mode is no longer a bizarre hallucination that is easy to spot, but a confident GTM answer, such as a revenue number, that is wrong in ways that look plausible. That framing makes the session especially relevant to teams applying agents to attribution, account intelligence, pipeline inspection, forecasting, and other GTM workflows where an answer can be formatted correctly while still being commercially misleading.

The connected people page sharpens why Bauer is a fitting speaker for this topic: he is co founder of Upside, described there as the data layer for GTM engineers, and previously spent 2016-2024 at Branch as a public voice on mobile attribution and deep linking. That background points toward a talk grounded in the messy edge cases of business data, identity, attribution, and source-of-truth disputes rather than abstract prompt engineering. The scheduled patterns are concrete: a shared “librarian” that agents consult before acting, a jury-and-judge model for subjective or high-stakes calls, and an explicit stop condition for cases where the model is simply not capable enough for the job.

Within the July 1 multi-track program, this session sits in the AI in GTM track during the conference's densest day at Moscone West. It complements the broader wiki theme of converting official schedule entries into evidence-backed intelligence: the current evidence is still schedule-grounded, and the transcript map notes that no exact AI Engineer YouTube recording match was found by normalized title during this run. Until a confirmed recording, transcript, slide OCR, or resource link is attached, the page should keep the librarian, jury, judge, and model-capability patterns as official-description claims rather than transcript-confirmed implementation details.

Transcript Status

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

People

Notes

Synthesis

Synthesized Breakdown

Well, hopefully this is the one talk that's different from all the others today. So, let's start with audience participation. Who here has kids? Oh.

Speaker And Company Context

Topics Covered

Derived Links And Source Material

Novel Concepts / Clever Methods

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.

Official YouTube Recording

Supporting Slides