SIGNAL//SYNTH
Ai

1030: Garbage In, Gospel Out: Why Agents Need Better Data, with Salesforce's Gaurav Pathak

aired Sep 25, 2026 · 22.0m
Signal
79.1/ 100
High signal
confidence 0.99
Orig61.3
Actn67.0
Dens100.0
Dpth100.0
Clty62.2
Summary

When humans get bad data, they argue about it in meetings. When AI agents get bad data, they pick a number and present it with total confidence.

Why listen

It goes beyond the title with direct discussion of data, right, like, including: When AI agents get bad data, they pick a number and present it with total confidence.

Key takeaways
  1. 01When AI agents get bad data, they pick a number and present it with total confidence
  2. 02Gaurav spent 13 years at Informatica building its metadata and AI products, including the Clare AI engine, before Salesforce acquired Informatica last year
  3. 03In this episode, filmed live at Dreamforce in San Francisco, Gaurav explains why context is 95% of the battle for enterprise agents, who the sin eaters are that pay for an agent's
Best for
AI engineers building production copilots