Chain of Thought | AI Agents, Infrastructure & Engineering

Most of the web will never get APIs for AI agents. School district sites, small business pages, government offices, and the long tail of e-commerce were built for humans, and they will keep working that way for years. So how do agents actually get things done across the web?
Dhruv Batra is co-founder and chief scientist of Yutori, the company building specialized browser and computer-use agents. He previously led embodied AI at Meta's FAIR lab, training robots in simulation and shipping the image question-answering model on Ray-Ban Meta glasses. His bet: the web is a shared roadway, much like roads split between human drivers and self-driving cars, and agents will be built to use it the way people already do.

Pixels in, clicks out. That is the API.
In this conversation:
Why the long tail of the web won't re-architect itself for agents
How Yutori's Navigator perceives pixels and writes JavaScript on the fly to shorten task trajectories
Why Navigator runs 2-3x faster and 4-5x cheaper than Opus 4.7 and GPT-5.5 on browser tasks
Learning from live websites, and using URL query parameters as privileged verifiers instead of cloning sites
What the shift from American to Chinese open-weight models means for startups
How smart glasses and robots share the same perception-action loop
Why demand for inference compute is pushing models smaller and onto devices
Chapters:
(00:00) Pixels in, clicks out
 (01:37) Why most of the web will never get APIs
 (08:47) Aggregation, specialization, and human friction
 (11:39) Digital niches and specialized models
 (16:41) The web's heavy tail and where browser agents win
 (20:40) Inside Yutori's Navigator and Scouts
 (24:08) N1.5: writing JavaScript to cut trajectory length
 (27:45) Training on live websites
 (33:29) Open source: FAIR's legacy and the Chinese frontier
 (37:22) Agent frameworks: OpenClaw, Hermes, heartbeats
 (40:57) How non-technical users adopt agents
 (44:25) Smart glasses, robotics, and embodied AI
 (50:57) Compute demand and smaller on-device models
 (53:12) Why the company is called Yutori
Connect with Dhruv Batra:
LinkedIn: https://www.linkedin.com/in/dhruv-batra-dbatra/
X/Twitter: https://x.com/DhruvBatra_
Yutori: https://yutori.com
Connect with Conor:
Newsletter: https://newsletter.chainofthought.show/
Twitter/X: https://x.com/ConorBronsdon
LinkedIn: https://www.linkedin.com/in/conorbronsdon/
YouTube: https://www.youtube.com/@ConorBronsdon
More episodes: https://chainofthought.show

Kristin "Kris" Lovejoy has spent her career inside the systems the global economy runs on: banks, hospitals, energy grids, governments. Today she is Global Head of Strategy at Kyndryl, the world's largest IT infrastructure services provider, working with mission-critical enterprises across more than 60 countries. Before that she ran security businesses at EY and IBM, founded the AI security company BluVector (acquired by Comcast), and now sits on the board of Dominion Energy.
Her prediction: the first fully autonomous AI attack, where an AI takes down an enterprise network with no human driving it, lands within 18 months.
Conor and Kris dig into why 62% of enterprise AI initiatives are still stuck in pilots even as spend climbs 33% year over year, why attackers chaining low-risk vulnerabilities changes the patching math, and why she has a fraught relationship with policy as code.
We cover:
The electricity analogy: we can build the models, but the transmission lines for industrial AI don't exist yet
Productivity AI vs mission-critical AI, and why banks and healthcare systems aren't running agentic AI at production scale
Why deterministic policy as code clashes with autonomous systems, and "human on top" vs human in the loop
The 18-month prediction: chaining low-risk vulnerabilities, outcome-oriented agents that take systems down by accident, and insiders armed with AI attack tools
The data center build-out from a Dominion Energy board member: PJM load forecasts that miss by double digits every year, water use, density, and rack optimization
Privacy as a double-edged sword: data combinations that suddenly become PII and the shift to continuous compliance
What's next: open source everywhere, sovereignty as control, autonomous robotics, and quantum
Chapters:
(00:00) Meet Kris Lovejoy: Kyndryl, EY, IBM, and Dominion Energy
 (02:09) Why 62% of AI initiatives are stuck in pilots
 (03:07) The electricity analogy: models without transmission lines
 (04:23) Productivity AI vs mission-critical AI
 (06:53) Vintage systems, hybrid data, and the risk gap
 (11:03) Policy as code and "human on top"
 (16:25) Data centers, energy, and the grid build-out
 (24:44) Data center design: density, cooling, rack optimization
 (26:54) Privacy, continuous compliance, and sovereignty as control
 (32:06) The first fully autonomous AI attack: 18 months away
 (38:06) Predictions: open source, robotics, and quantum
 (42:32) Control planes for agentic AI: closing thoughts
Connect with Kris Lovejoy:
LinkedIn: https://www.linkedin.com/in/klovejoy/
Kyndryl: https://www.kyndryl.com
Connect with Conor:
Newsletter: https://newsletter.chainofthought.show/
Twitter/X: https://x.com/ConorBronsdon
LinkedIn: https://www.linkedin.com/in/conorbronsdon/
YouTube: https://www.youtube.com/@ConorBronsdon
More episodes: https://chainofthought.show

Jerry Liu built one of the most installed pieces of AI plumbing of the last three years. LlamaIndex became the indexing and retrieval layer a whole generation of RAG apps were stitched together with. Then he started arguing that the framework era he helped create is over.
Jerry is co-founder and CEO of LlamaIndex. In this conversation he walks through the company's pivot from open-source framework to managed document infrastructure with LlamaCloud and LlamaParse, and why he is betting that context quality is the one moat that compounds as agent loops get good enough to absorb the scaffolding.
If you are a founder worried a frontier lab or a coding agent is about to eat your product, this is the playbook for reinventing your ICP without losing the thread.
In this conversation:
Why Jerry says the AI framework era is over, and what actually survives
How agent harnesses like Claude Code collapsed the old framework patterns into the model
Why context quality is the durable moat, not the agent loop
How LlamaParse beats legacy OCR and frontier models on document accuracy and cost
Why 95%+ accuracy is the real bar for legal, insurance, and financial document work
How LlamaIndex disrupted its own product and reinvented its ICP to stay alive
Jerry's take on agent memory, model personalities, and why LLMs are still bad writers
(0:00) Is the AI framework era over?
 (1:56) What died and what survived
 (6:31) Why context quality is the moat
 (8:12) Defining the context layer
 (13:18) Coding and vision as the abstraction layer
 (18:13) The bet that context compounds
 (23:59) Which verticals are adopting
 (25:14) Why 95%+ accuracy is the real bar
 (29:49) The file system as an agent primitive
 (34:33) Surviving your own pivot
 (37:15) Reinventing strategy and hiring
 (42:00) Agent memory as persistent context
 (44:41) Model personalities and cultural memory
 (47:51) Writing with AI
 (50:19) Closing thoughts
Connect with Jerry Liu:
LinkedIn: https://www.linkedin.com/in/jerry-liu-64390071/
Twitter/X: https://x.com/jerryjliu0
LlamaIndex: https://www.llamaindex.ai
LlamaIndex careers: https://www.llamaindex.ai/careers
Connect with Conor:
Newsletter: https://newsletter.chainofthought.show/
Twitter/X: https://x.com/ConorBronsdon
LinkedIn: https://www.linkedin.com/in/conorbronsdon/
YouTube: https://www.youtube.com/@ConorBronsdon
More episodes: https://chainofthought.show

Tyler Akidau spent 12 years on streaming systems at Google and five years at Snowflake before joining Redpanda as CTO. He wrote the O'Reilly Streaming Systems book most of the field has on its shelf. His new piece on O'Reilly Radar (Post-Human: We All Built Agents, Nobody Built HR) argues that enterprises are stuck in the prototype-to-production gap because they're applying human-era identity, auth, and observability tools to a workforce that's unpredictable in structurally novel ways, runs at machine speed, and follows bad instructions to a fault. Inline guardrails like CLAUDE.md work until they don't. Governance has to be enforced through channels the agent can't see, modify, or override.
We cover:
Why AI agents are a new kind of co-worker (unpredictable, machine-speed, directable to a fault) and what that means for enterprise infrastructure
The four pillars of agent governance: identity, authorization, observability and explainability, accountability and control
Why task-scoped, short-lived identity is the foundation everything else builds on
Authorization that's deny-capable and intersection-aware (Tyler's "guest badge" model)
Why OpenTelemetry is the right starting point for recording every prompt, tool call, and response
How Redpanda's Agentic Data Plane combines streaming topics, Oxla SQL, and Postgres under the hood
Tyler's academic paper with a psychologist on the neurobiological systems humans have that AI agents are missing
Chapters:
(00:00) Why nobody built HR for AI agents
(02:12) Three ways agents differ from human employees
(07:53) The four pillars of out-of-band governance
(10:29) Identity: task-scoped, short-lived, chained to humans
(14:40) Authorization: deny-capable and intersection-aware
(18:57) Observability: record everything via OpenTelemetry
(24:24) Redpanda's agents and the $1,000 trade limit example
(30:10) Accountability and the kill switch
(34:02) The Agentic Data Plane: streaming, Oxla SQL, Postgres
(41:20) Should we stop chasing model alignment?
(44:04) Building human-like value systems into agents
(47:25) Tyler's 12-24 month outlook for agent governance
Connect with Tyler:
LinkedIn: https://www.linkedin.com/in/takidau/
Redpanda: https://www.redpanda.com/
Post-Human article: https://www.oreilly.com/radar/posthuman-we-all-built-agents-nobody-built-hr/ 
Connect with Conor:
Newsletter: https://newsletter.chainofthought.show/
Twitter/X: https://x.com/ConorBronsdon
LinkedIn: https://www.linkedin.com/in/conorbronsdon/
YouTube: https://www.youtube.com/@ConorBronsdon
More episodes: https://chainofthought.show

Loïc Houssier leads engineering at Superhuman, the email client Grammarly acquired for ~$825 million in July 2025. Before Superhuman he was CTO of OpenTrust (acquired by DocuSign), ran engineering at ProductBoard, and started his career in applied cryptography for France's defense industry, including work on nuclear submarine systems. Loïc joined Superhuman in early 2024 and within 30 days was leading a six-week sprint to ship AI Inbox.
Superhuman's brand is built on speed: every interaction under 100 milliseconds. LLMs do not run in 100 milliseconds. So Loïc walks Conor through how his team retrofitted AI into a product that was already winning without it: pre-caching context for the mobile voice feature, starting every feature on the smartest available model and only then fine-tuning down to cheap dedicated infrastructure, treating "look foolish" as a P0 bug class, and refusing to auto-send any email even when their agents could.
This is a practitioner's tour of what it actually takes to put AI on top of a product that has to stay fast, stay quiet, and never embarrass the user.
We cover:
The model-routing strategy: Opus and frontier models to prove a feature, then fine-tuned BERT classifiers on dedicated inference
Pre-caching voice and tone context separately from dictation to keep the mobile voice feature feeling fast
Why eval engineering at Superhuman is owned by PMs, and how a single "how much time did I spend in Waymo last month" query exposes the eigenvectors a feature has to cover
Why "look foolish" is a P0 bug class, and where the boundary between agent agency and agent laziness actually sits
How Superhuman's pod structure (PM, tech lead, designer) and a central AI platform team support aligned autonomy
Hiring for AI fluency: how interview questions are changing and what self-augmenting engineers look like
Pattern detection as the leadership skill that transfers from nuclear submarines to AI email
Chapters:
(00:00) Cold open: pattern detection beats new tools
 (00:18) Loïc's path: cryptography, OpenTrust, ProductBoard, Superhuman
 (02:13) Retrofitting AI into a 100ms product
 (04:08) Voice on mobile: pre-caching LLM context to keep the feel fast
 (07:46) Frontier first, then fine-tune: model strategy across features
 (11:04) The "double-dipping" trick that worked on GPT-4 and stopped working
 (12:25) Cognitive load and staying current as a leader
 (16:59) Balancing YC founder urgency with peer CTO grounding
 (19:28) Pods, AI Guild, and aligned autonomy
 (23:15) Managing models vs. managing people: delegation in reverse
 (28:27) The Waymo example: eigenvectors of evaluation
 (32:15) Day 30 onboarding: leading the AI Inbox sprint
 (35:04) Why email is the killer agent use case
 (38:51) Auto-draft, never auto-send
 (39:57) Agent agency vs. agent laziness
 (43:07) Hiring for AI fluency
 (45:55) Pattern detection is the leadership skill
 (47:21) Nuclear submarines as engineering reference points
 (48:37) Closing thoughts
 (49:38) Superhuman is hiring
Connect with Loïc:
LinkedIn: https://www.linkedin.com/in/houssier/
Superhuman careers: https://superhuman.com/careers
Superhuman: https://superhuman.com
Connect with Conor:
Newsletter: https://newsletter.chainofthought.show/
Twitter/X: https://x.com/ConorBronsdon
LinkedIn: https://www.linkedin.com/in/conorbronsdon/
YouTube: https://www.youtube.com/@ConorBronsdon
More episodes: https://chainofthought.show
Thanks to Galileo — download their free 165-page guide to mastering multi-agent systems at galileo.ai/mastering-multi-agent-systems