---
title: "Your company brain will leak secrets. Here's how we stopped it for big banks and ourselves."
category: "talks"
date: "2026-06-29"
time: "2:50pm-3:10pm"
track: "Claws & Personal Agents"
room: "Track 1"
speakers: ["Tanmai Gopal"]
sourceLabels: ["Official conference schedule", "Public YouTube metadata"]
scheduleTrack: "Claws & Personal Agents"
scheduleRoom: "Track 1"
scheduleLabels: ["Claws & Personal Agents", "Track 1", "session", "confirmed"]
---
# Your company brain will leak secrets. Here's how we stopped it for big banks and ourselves.

## Conference Context
- Date/time: 2026-06-29 · 2:50pm-3:10pm
- Track/room: Claws & Personal Agents · Track 1
- Speaker(s): Tanmai Gopal
- Session type/status: session · confirmed

- Track: Claws & Personal Agents
- Room: Track 1
- Session type: session
- Status: confirmed

## Session Description
Everyone wants a shared "company brain", one single AI that knows everything the org knows. But it's nearly impossible to build one, because the moment AI scrapes everyone's data into one place, a single wrong answer to the wrong person is a breach. The downside of modifying a above-my-pay-grade shared skill, or leaking confidential information to the wrong colleague is catastrophic. Ergo, company brain projects can only ever ship to the few people who already had access to everything, or stay hobbled with strictly public information (eg: River at Shopify). We've been building one for the last year and have successfully deployed for Fortune 100 banks, for distributed-operations orgs with global scale, and for ourselves as a 70-person AI-native startup. I'll leave you with a blueprint covering how we solved the following problems: 1. Permissions for shared data and tools 2. A shared context layer (skills, knowledge, semantic layer) with its own access control 3. Scoping the blast radius of wrong context 4. Auto-learning without auto-leaking If your company brain effort has been blocked by security, compliance, or just a healthy fear of the intern asking the AI a question and getting back the exec comp table, this is the talk.

## Media Evidence
[Realtime Data Connectivity for AI: Tanmai Gopal](https://www.youtube.com/watch?v=himhGiWJXjo) (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).

- Source video: `youtube-himhGiWJXjo`
- Slide deck: [[youtube-himhGiWJXjo-reconstructed-slides|Reconstructed Slides: Realtime Data Connectivity for AI: Tanmai Gopal]] — 9 visible slide image(s); 9 HTML recreation(s).
![[assets/reconstructed-slides/himhGiWJXjo/slide-002.jpg]]
![[assets/reconstructed-slides/himhGiWJXjo/slide-004.jpg]]
![[assets/reconstructed-slides/himhGiWJXjo/slide-005.jpg]]
- Additional slide evidence: [[youtube-himhGiWJXjo-slides|Slides: Realtime Data Connectivity for AI: Tanmai Gopal]]
- Slide-derived themes for `youtube-himhGiWJXjo`: data, embrace, overlords, give, deal, acme, stuck, stage.

## 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-himhGiWJXjo` — 6 slide-derived text signals
- Slide-derived themes for `youtube-himhGiWJXjo`: data, embrace, overlords, give, deal, acme, stuck, stage.
- Evidence links for `youtube-himhGiWJXjo`: [[youtube-himhGiWJXjo]], [[youtube-himhGiWJXjo-slides]], [[youtube-himhGiWJXjo-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. Not fetched yet.

## People
- [[tanmai-gopal]]

## Supporting Slides
- [[youtube-himhGiWJXjo-slides]] — extracted from the related public AI Engineer video.

## Synthesis
### Synthesized Breakdown
# Your company brain will leak secrets. Here's how we stopped it for big banks and ourselves. ## Conference Context - Date/time: 2026-06-29 · 2:50pm-3:10pm - Track/room: Claws & Personal Agents · Track 1 - Speaker(s): Tanmai Gopal - Session type/status: session · confirmed - Track: Claws & Personal Agents - Room: Track 1 - Session type: session - Status: confirmed ## Session Description Everyone wants a shared "company brain", one single AI that knows everything the org knows. But it's nearly impossible to build one, because the moment AI scrapes everyone's data into one place, a single wrong answer to the wrong person is a breach.

### Speaker And Company Context
- [[tanmai-gopal|Tanmai Gopal]] — CEO/cofounder at [[promptql|PromptQL]].

### Topics Covered
- [[agent-security]]

### Derived Links And Source Material
- [[youtube-himhGiWJXjo]] — related YouTube source page.
- [[youtube-himhGiWJXjo-slides]] — slide evidence.
- [[youtube-himhGiWJXjo-reconstructed-slides]] — slide evidence.

### Novel Concepts / Clever Methods
- No highlighted novel concept has been detected yet.

### Evidence Boundary
This synthesis is based on the official schedule and linked source pages. It should be revisited when exact session recordings or transcript-backed secondary sources are available.