---
title: "Gemini"
category: "tools"
aliases: ["Gemini", "Gemini Live"]
sourceLabels: ["Official schedule", "Public YouTube metadata", "Transcript evidence", "Local slide OCR", "Topic synthesis"]
scheduleTracks: ["Vision & OCR", "Voice & Realtime AI", "AI Architects: Show my Workflow", "Autoresearch", "Workshops Day 2", "Context Engineering", "Workshops Day 3", "Memory & Continual Learning", "Agentic Commerce", "Generative Media", "Agentic Engineering"]
scheduleRooms: ["Track 6", "Expo Stage 3 SW", "Track 2", "Leadership 2", "Main Stage", "Track 4", "Track 8", "Track 3", "Track 1"]
---

# Gemini

## Why It Belongs
Gemini appears as a high-confidence tool, platform, model, protocol, product, or service in the AI Engineer World's Fair 2026 corpus.

This page records confirmed mentions and keeps them separate from broader inferred relevance.

## Confirmed Evidence

### Official Schedule
- [[2026-06-29-louis-fran-ois-bouchard-context-engineering-in-2026-compaction-memory-and-cost]] — Context Engineering in 2026: Compaction, Memory & Cost (track TBD / Track 6)
- [[2026-06-29-simran-arora-can-llms-write-fast-multi-gpu-kernels-we-built-a-benchmark-to-find-out]] — Can LLMs write fast multi-GPU kernels? We built a benchmark to find out. (track TBD / Expo Stage 3 SW)
- [[2026-06-29-andrew-dai-the-best-models-still-reason-like-toddlers]] — The Best Models Still Reason Like Toddlers (Vision & OCR / Track 2)
- [[2026-06-29-bohan-li-realtime-voice-agents-with-frontier-intelligence]] — Realtime Voice Agents with Frontier Intelligence (Voice & Realtime AI / Track 6)
- [[2026-06-29-niels-rogge-how-i-automate-my-own-job-at-hugging-face-using-agents]] — How I automate my own job at Hugging Face using agents (AI Architects: Show my Workflow / Leadership 2)
- [[2026-06-30-benoit-schillings-research-to-reality-with-google-deepmind]] — Research to Reality with Google DeepMind (Autoresearch / Main Stage)
- [[2026-06-30-thor-schaeff-build-realtime-multimodal-agents-with-gemini-live]] — Build realtime multimodal agents with Gemini Live (Workshops Day 2 / Track 4)
- [[2026-06-30-averi-kitsch-build-time-vs-run-time-why-your-dev-tools-will-fail-in-production]] — Build-Time vs. Run-Time: Why Your Dev Tools Will Fail in Production (Context Engineering / Track 8)
- [[2026-06-30-thor-schaeff-build-realtime-multimodal-agents-with-gemini-live-continued-2]] — Build realtime multimodal agents with Gemini Live (continued 2) (Workshops Day 2 / Track 4)
- [[2026-06-30-thor-schaeff-build-realtime-multimodal-agents-with-gemini-live-continued-3]] — Build realtime multimodal agents with Gemini Live (continued 3) (Workshops Day 2 / Track 4)

### Public YouTube Metadata
- [YouTube Bc6Ojl2XS1w](https://www.youtube.com/watch?v=Bc6Ojl2XS1w) — From Transcription to Live Music: Gemini's Audio Stack — Thor Schaeff, Google DeepMind
- [YouTube owH1f0N-keY](https://www.youtube.com/watch?v=owH1f0N-keY) — Gemini Nano on device — Florina Muntenescu & Oli Gaymond, Google DeepMind
- [YouTube zZsTVBXcbow](https://www.youtube.com/watch?v=zZsTVBXcbow) — How Google DeepMind is researching the next Frontier of AI for Gemini — Raia Hadsell, VP of Research
- [YouTube fgkXEIbZpGc](https://www.youtube.com/watch?v=fgkXEIbZpGc) — Building in the Gemini Era – Kat Kampf & Ammaar Reshi, Google DeepMind
- [YouTube LxQsQ3vZDqo](https://www.youtube.com/watch?v=LxQsQ3vZDqo) — Teaching Gemini to Speak YouTube: Adapting LLMs for Video Recommendations to 2B+DAU - Devansh Tandon
- [YouTube zK9lYrLbjSg](https://www.youtube.com/watch?v=zK9lYrLbjSg) — AI Engineering with the Google Gemini 2.5 Model Family - Philipp Schmid, Google DeepMind
- [YouTube 8EQo4J2BWKw](https://www.youtube.com/watch?v=8EQo4J2BWKw) — Thinking Deeper in Gemini — Jack Rae, Google DeepMind
- [YouTube wE1ZCmCLP5g](https://www.youtube.com/watch?v=wE1ZCmCLP5g) — A year of Gemini progress + what comes next — Logan Kilpatrick, Google DeepMind
- [YouTube fWY1FQwpWkY](https://www.youtube.com/watch?v=fWY1FQwpWkY) — Milliseconds to Magic: Real‑Time Workflows using the Gemini Live API and Pipecat
- [YouTube ySYLsoAhXmg](https://www.youtube.com/watch?v=ySYLsoAhXmg) — AI Engineers: The Next Generation — Stefania Druga, Google Gemini

### Resource Pages
- [[advanced-slide-logic-page-audit]]
- [[talk-video-transcript-map]]
- [[youtube-Bc6Ojl2XS1w]]
- [[youtube-LxQsQ3vZDqo]]

### Slide/OCR Pages
- [[youtube--TiET_K-E_g-slides]]
- [[youtube-4sX_He5c4sI-slides]]
- [[youtube-7Dtu2bilcFs-slides]]
- [[youtube-84Vtz2IL1Ug-slides]]
- [[youtube-Bc6Ojl2XS1w-dense-slides]]
- [[youtube-Bc6Ojl2XS1w-reconstructed-slides]]
- [[youtube-Bc6Ojl2XS1w-slides]]
- [[youtube-F_RyElT_gJk-slides]]
- [[youtube-G_bHFmEAarM-slides]]
- [[youtube-IddXPepIAS4-slides]]

### Topic Pages
- [[voice-agents]]

### Transcript Files
- `raw/sources/youtube-transcripts/QuuIywMG4s8.txt`
- `raw/sources/youtube-transcripts/SS-A8sE7hkw.txt`
- `raw/sources/youtube-transcripts/UM6sFg_jdlE.txt`
- `raw/sources/youtube-transcripts/UPwGaM2MKHY.txt`
- `raw/sources/youtube-transcripts/Xfl50508LZM.txt`
- `raw/sources/youtube-transcripts/_B4Pv9ttFgY.txt`
- `raw/sources/youtube-transcripts/dvft0Gp9sEE.txt`
- `raw/sources/youtube-transcripts/fWXJM-J0ZB8.txt`
- `raw/sources/youtube-transcripts/ghJmWQCIHRM.txt`
- `raw/sources/youtube-transcripts/hCMrEfPG2Yg.txt`

## Confidence
High confidence for presence in the corpus. Interpret broader importance through the linked schedule, transcript, slide, and topic evidence.