Nov 10, 2025 · 43m · latent-space

⚡ Inside Google Labs: Building The Gemini Coding Agent — Jed Borovik, Jules + AIE CODE Preview

Jed Borovik · 20m spoken
0:00 / 0:00
▶ Watch on YouTube →

gold bands on the timeline = statements, start to end. Hover to read, click to jump. CC turns on captions

Google Labs engineer Jed Borovik discusses the architectural evolution, capabilities, and product vision of Jules, Google's autonomous coding agent, while exploring how AI is reshaping developer craft, software economics, and engineering communities.

How this conversation actually went

Every chapter scored 0–10 on four independent dynamics. Hover any point for the reasoning behind the score. How this is scored →

The hosts as informed peer 5.6 Guest teaching 3.7 Guest disagreement 1.3 The hosts pushing back 2.0
05100:0015:0030:002:19–6:41 · The hosts as informed peer 4/10 Jed's AI Journey and Joining Google Labs The conversation is genial as Jed explains his transition from Search to Google Labs following the release of Stable Diffusion. The host probes into Google Labs' org chart and internal precursors to Copilot.6:42–9:12 · The hosts as informed peer 4/10 Defining Jules: Autonomous and Ambient Coding Agents Jed details the product thesis behind Jules as an ambient and autonomous coding agent with its own dedicated compute environment. The host asks clarifying questions about CLI and API integrations.9:13–13:58 · The hosts as informed peer 7/10 Simplifying Agent Scaffolds and Moving Beyond RAG Jed explains how agent scaffolds have simplified over time as base models improve. The host actively pushes back on embedding-based RAG, arguing chunking is fundamentally flawed and that grep plus attention scales better.13:58–22:36 · The hosts as informed peer 7/10 Graduating Jules from Prototype to Production The dynamic shifts as the guest asks the host about the upcoming AI Engineer Code Summit. The host takes on an authoritative role, detailing conference dynamics, selective acceptance rates, and hallway tracks.22:36–35:40 · The hosts as informed peer 7/10 Long-Context Sessions and the Macroeconomics of Software The pair discuss long-context management in 30-day coding sessions and macroeconomic impacts on software engineering. The host invokes Jevons paradox and context compaction techniques, matching Jed's industry outlook.35:41–42:26 · The hosts as informed peer 7/10 Beyond Vibe Coding: Interactive Planning and Multimodality The discussion covers moving beyond 'vibe coding' towards spec-driven and interactive planning development. The host pitches Cognition's interactive planning philosophy and multimodal video inputs, while Jed discusses test-generation trade-offs.42:27–43:42 · The hosts as informed peer 3/10 Conference Connecting and Google Labs Recruitment A friendly wrap-up segment where Jed invites conference attendees to share their workflows, criticisms, and interest in joining Google Labs.2:19–6:41 · Guest teaching 5/10 Jed's AI Journey and Joining Google Labs The conversation is genial as Jed explains his transition from Search to Google Labs following the release of Stable Diffusion. The host probes into Google Labs' org chart and internal precursors to Copilot.6:42–9:12 · Guest teaching 5/10 Defining Jules: Autonomous and Ambient Coding Agents Jed details the product thesis behind Jules as an ambient and autonomous coding agent with its own dedicated compute environment. The host asks clarifying questions about CLI and API integrations.9:13–13:58 · Guest teaching 4/10 Simplifying Agent Scaffolds and Moving Beyond RAG Jed explains how agent scaffolds have simplified over time as base models improve. The host actively pushes back on embedding-based RAG, arguing chunking is fundamentally flawed and that grep plus attention scales better.13:58–22:36 · Guest teaching 2/10 Graduating Jules from Prototype to Production The dynamic shifts as the guest asks the host about the upcoming AI Engineer Code Summit. The host takes on an authoritative role, detailing conference dynamics, selective acceptance rates, and hallway tracks.22:36–35:40 · Guest teaching 4/10 Long-Context Sessions and the Macroeconomics of Software The pair discuss long-context management in 30-day coding sessions and macroeconomic impacts on software engineering. The host invokes Jevons paradox and context compaction techniques, matching Jed's industry outlook.35:41–42:26 · Guest teaching 4/10 Beyond Vibe Coding: Interactive Planning and Multimodality The discussion covers moving beyond 'vibe coding' towards spec-driven and interactive planning development. The host pitches Cognition's interactive planning philosophy and multimodal video inputs, while Jed discusses test-generation trade-offs.42:27–43:42 · Guest teaching 2/10 Conference Connecting and Google Labs Recruitment A friendly wrap-up segment where Jed invites conference attendees to share their workflows, criticisms, and interest in joining Google Labs.2:19–6:41 · Guest disagreement 1/10 Jed's AI Journey and Joining Google Labs The conversation is genial as Jed explains his transition from Search to Google Labs following the release of Stable Diffusion. The host probes into Google Labs' org chart and internal precursors to Copilot.6:42–9:12 · Guest disagreement 1/10 Defining Jules: Autonomous and Ambient Coding Agents Jed details the product thesis behind Jules as an ambient and autonomous coding agent with its own dedicated compute environment. The host asks clarifying questions about CLI and API integrations.9:13–13:58 · Guest disagreement 2/10 Simplifying Agent Scaffolds and Moving Beyond RAG Jed explains how agent scaffolds have simplified over time as base models improve. The host actively pushes back on embedding-based RAG, arguing chunking is fundamentally flawed and that grep plus attention scales better.13:58–22:36 · Guest disagreement 1/10 Graduating Jules from Prototype to Production The dynamic shifts as the guest asks the host about the upcoming AI Engineer Code Summit. The host takes on an authoritative role, detailing conference dynamics, selective acceptance rates, and hallway tracks.22:36–35:40 · Guest disagreement 2/10 Long-Context Sessions and the Macroeconomics of Software The pair discuss long-context management in 30-day coding sessions and macroeconomic impacts on software engineering. The host invokes Jevons paradox and context compaction techniques, matching Jed's industry outlook.35:41–42:26 · Guest disagreement 2/10 Beyond Vibe Coding: Interactive Planning and Multimodality The discussion covers moving beyond 'vibe coding' towards spec-driven and interactive planning development. The host pitches Cognition's interactive planning philosophy and multimodal video inputs, while Jed discusses test-generation trade-offs.42:27–43:42 · Guest disagreement 0/10 Conference Connecting and Google Labs Recruitment A friendly wrap-up segment where Jed invites conference attendees to share their workflows, criticisms, and interest in joining Google Labs.2:19–6:41 · The hosts pushing back 1/10 Jed's AI Journey and Joining Google Labs The conversation is genial as Jed explains his transition from Search to Google Labs following the release of Stable Diffusion. The host probes into Google Labs' org chart and internal precursors to Copilot.6:42–9:12 · The hosts pushing back 1/10 Defining Jules: Autonomous and Ambient Coding Agents Jed details the product thesis behind Jules as an ambient and autonomous coding agent with its own dedicated compute environment. The host asks clarifying questions about CLI and API integrations.9:13–13:58 · The hosts pushing back 5/10 Simplifying Agent Scaffolds and Moving Beyond RAG Jed explains how agent scaffolds have simplified over time as base models improve. The host actively pushes back on embedding-based RAG, arguing chunking is fundamentally flawed and that grep plus attention scales better.13:58–22:36 · The hosts pushing back 1/10 Graduating Jules from Prototype to Production The dynamic shifts as the guest asks the host about the upcoming AI Engineer Code Summit. The host takes on an authoritative role, detailing conference dynamics, selective acceptance rates, and hallway tracks.22:36–35:40 · The hosts pushing back 3/10 Long-Context Sessions and the Macroeconomics of Software The pair discuss long-context management in 30-day coding sessions and macroeconomic impacts on software engineering. The host invokes Jevons paradox and context compaction techniques, matching Jed's industry outlook.35:41–42:26 · The hosts pushing back 3/10 Beyond Vibe Coding: Interactive Planning and Multimodality The discussion covers moving beyond 'vibe coding' towards spec-driven and interactive planning development. The host pitches Cognition's interactive planning philosophy and multimodal video inputs, while Jed discusses test-generation trade-offs.42:27–43:42 · The hosts pushing back 0/10 Conference Connecting and Google Labs Recruitment A friendly wrap-up segment where Jed invites conference attendees to share their workflows, criticisms, and interest in joining Google Labs.

speaking balance: gold is the hosts, purple is the guest (3 minute bins)

0:00 · the hosts 0% · guest 100%0:00 · the hosts 0% · guest 100%3:00 · the hosts 0% · guest 100%3:00 · the hosts 0% · guest 100%6:00 · the hosts 0% · guest 100%6:00 · the hosts 0% · guest 100%9:00 · the hosts 0% · guest 100%9:00 · the hosts 0% · guest 100%12:00 · the hosts 0% · guest 100%12:00 · the hosts 0% · guest 100%15:00 · the hosts 0% · guest 100%15:00 · the hosts 0% · guest 100%18:00 · the hosts 0% · guest 100%18:00 · the hosts 0% · guest 100%21:00 · the hosts 0% · guest 100%21:00 · the hosts 0% · guest 100%24:00 · the hosts 0% · guest 100%24:00 · the hosts 0% · guest 100%27:00 · the hosts 0% · guest 100%27:00 · the hosts 0% · guest 100%30:00 · the hosts 0% · guest 100%30:00 · the hosts 0% · guest 100%33:00 · the hosts 0% · guest 100%33:00 · the hosts 0% · guest 100%36:00 · the hosts 0% · guest 100%36:00 · the hosts 0% · guest 100%39:00 · the hosts 0% · guest 100%39:00 · the hosts 0% · guest 100%42:00 · the hosts 0% · guest 100%42:00 · the hosts 0% · guest 100%
Sharpest disagreement ▶ 39:56 Pushing back against mandatory automated tests

Jed politely resists the host's framing around enforcing matching tests for generated code, asserting that developers should retain full discretion over their repo conventions.

Hardest push from the hosts ▶ 11:56 Declaring embedding chunking fundamentally broken

The host directly disputes Jed's framing of RAG being just 'hard', asserting that semantic chunking will never be adequate compared to attention and grep.

Biggest teaching moment ▶ 9:41 Explaining the decline of complex agent harnesses

Jed educates the host on Google Labs' findings that multi-agent personas and complex harnesses act as crutches that become obsolete as foundation models improve.

The host holds their own ▶ 12:05 Demonstrating deep retrieval systems knowledge

The host articulates the architectural limitations of arbitrary semantic chunking boundaries and cites Cognition's tool-based grep approach.

the scores for every segment, with the reasoning behind each
ChapterTopicThe hosts as informed peerGuest teachingGuest disagreementThe hosts pushing backWhy
Jed's AI Journey and Joining Google Labs 4511 The conversation is genial as Jed explains his transition from Search to Google Labs following the release of Stable Diffusion. The host probes into Google Labs' org chart and internal precursors to Copilot.
Defining Jules: Autonomous and Ambient Coding Agents 4511 Jed details the product thesis behind Jules as an ambient and autonomous coding agent with its own dedicated compute environment. The host asks clarifying questions about CLI and API integrations.
Simplifying Agent Scaffolds and Moving Beyond RAG 7425 Jed explains how agent scaffolds have simplified over time as base models improve. The host actively pushes back on embedding-based RAG, arguing chunking is fundamentally flawed and that grep plus attention scales better.
Graduating Jules from Prototype to Production 7211 The dynamic shifts as the guest asks the host about the upcoming AI Engineer Code Summit. The host takes on an authoritative role, detailing conference dynamics, selective acceptance rates, and hallway tracks.
Long-Context Sessions and the Macroeconomics of Software 7423 The pair discuss long-context management in 30-day coding sessions and macroeconomic impacts on software engineering. The host invokes Jevons paradox and context compaction techniques, matching Jed's industry outlook.
Beyond Vibe Coding: Interactive Planning and Multimodality 7423 The discussion covers moving beyond 'vibe coding' towards spec-driven and interactive planning development. The host pitches Cognition's interactive planning philosophy and multimodal video inputs, while Jed discusses test-generation trade-offs.
Conference Connecting and Google Labs Recruitment 3200 A friendly wrap-up segment where Jed invites conference attendees to share their workflows, criticisms, and interest in joining Google Labs.

Statements from this episode (9)

Assertion Supported
Google Labs' Jules Partners with GitHub for Agent HQ
“Jules is, yeah, partnering with GitHub for the new agent HQ stuff, which we're excited about.”
Jed Borovik Nov 10, 2025 ▶ 0:23
Assertion Supported
Borovik: Google built internal AI coding tools in Cider IDE for years
“Being Google, we built a lot of our own tools and, you know, cider, which, you know, folks maybe have heard of is our, you know, our internal IDE and we've had all kinds of, you know, capabilities and tools there for a while. So yes, you know, we certainly hav…”
Jed Borovik Nov 10, 2025 ▶ 5:42
Insight
Autonomous coding agents require dedicated computing environments over local workspaces
“Autonomous, you know, means, like, it has its own computer, right? So for Jules, it's, you know, the end. Yeah, exactly. So tons of agents that run, you know, locally or in your workspace with you while you're coding but if you want something that's going to r…”
Jed Borovik Nov 10, 2025 ▶ 7:20
Disclosure
Google Labs launched Jules CLI, plans integration with Gemini CLI
“So we have the dual CLI we launched a couple of weeks ago, which lets you interact with it. By the time this podcast comes out, we'll be in the integrated with the Gemini CLI.”
Jed Borovik Nov 10, 2025 ▶ 8:41
Insight
Borovik: Agent scaffolding gets simpler as underlying models improve
“I think one of the things we've seen is the scaffolds get simpler and simpler over time as the models get better. And in some ways, this, the scaffolding is almost a crutch for things the model struggles with. For example, like, you know, really complicated su…”
Jed Borovik Nov 10, 2025 ▶ 10:03
Disclosure
Borovik: Jules locks sessions after a 30-day data retention window
“We store some data for a session, but it only lasts. We only store it for 30 days. And so after 30 days your session becomes locked. And when the first user starts first started hitting that, they were upset. We're like, there's no way anyone's gonna be using …”
Jed Borovik Nov 10, 2025 ▶ 25:09
Opinion
Jed Borovik: AI coding tools will not reduce software engineer hiring
“I don't really Buy this, like, you know, that we're not gonna hire more software engineers story. I think, like, for a few reasons I mean, this is an example that, that often comes up, but is it, like, kind of the elasticity of the demand for software?”
Jed Borovik Nov 10, 2025 ▶ 33:43
Insight
Borovik: The two core AI agent challenges are specification and verification
“They're kind of like two problems as these things get better. One is like, how do you specify what you want? And the other one is how do you verify that what you got is what you're.”
Jed Borovik Nov 10, 2025 ▶ 38:59
Disclosure
Borovik: Google's Jules coding agent now supports image uploads
“With Jules, you can upload images now.”
Jed Borovik Nov 10, 2025 ▶ 40:44
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.