Podcast
Chain of Thought | AI Agents, Infrastructure & Engineering
Hosted by Conor Bronsdon · EN
AI is reshaping infrastructure, strategy, and entire industries. Host Conor Bronsdon talks to the engineers, founders, and researchers building breakthrough AI systems about what it actually takes to ship AI in production, where the opportunities lie, and how leaders should think about the strategic bets ahead.
Chain of Thought translates technical depth into actionable insights for builders and decision-makers. New episodes weekly.
Conor Bronsdon is an angel investor in AI and dev tools, Technical Ecosystem Lead at Modular, and previously led growth at AI startups Galileo and LinearB.
Disclaimer: All views, opinions and statements expressed on this account are solely my own and are made in my personal capacity. They do not reflect, and should not be construed as reflecting, the views, positions, or policies of Modular. This account is not affiliated with, authorized by, or endorsed by Modular in any way.
19episodes
Episodes
Newest firstAll episodes
The AI Framework Era Is Over: Why Context Is the Moat | Jerry Liu
4d ago00:52:42Tap to summarizeJerry 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 survivesHow agent harnesses like Claude Code collapsed the old framework patterns into the modelWhy context quality is the durable moat, not the agent loopHow LlamaParse beats legacy OCR and frontier models on document accuracy and costWhy 95%+ accuracy is the real bar for legal, insurance, and financial document workHow LlamaIndex disrupted its own product and reinvented its ICP to stay aliveJerry'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 thoughtsConnect with Jerry Liu:LinkedIn: https://www.linkedin.com/in/jerry-liu-64390071/Twitter/X: https://x.com/jerryjliu0LlamaIndex: https://www.llamaindex.aiLlamaIndex careers: https://www.llamaindex.ai/careersConnect with Conor:Newsletter: https://newsletter.chainofthought.show/Twitter/X: https://x.com/ConorBronsdonLinkedIn: https://www.linkedin.com/in/conorbronsdon/YouTube: https://www.youtube.com/@ConorBronsdonMore episodes: https://chainofthought.show
Transcribe →
We Built Agents, Nobody Built HR | Tyler Akidau, Redpanda
2w ago00:50:50Tap to summarizeTyler 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 infrastructureThe four pillars of agent governance: identity, authorization, observability and explainability, accountability and controlWhy task-scoped, short-lived identity is the foundation everything else builds onAuthorization 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 responseHow Redpanda's Agentic Data Plane combines streaming topics, Oxla SQL, and Postgres under the hoodTyler's academic paper with a psychologist on the neurobiological systems humans have that AI agents are missingChapters:(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 governanceConnect 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/ConorBronsdonLinkedIn: https://www.linkedin.com/in/conorbronsdon/YouTube: https://www.youtube.com/@ConorBronsdonMore episodes: https://chainofthought.show
Transcribe →
How Superhuman Built AI Into a 100ms Product | Loïc Houssier
2w ago00:50:11Tap to summarizeLoïc 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 inferencePre-caching voice and tone context separately from dictation to keep the mobile voice feature feeling fastWhy 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 coverWhy "look foolish" is a P0 bug class, and where the boundary between agent agency and agent laziness actually sitsHow Superhuman's pod structure (PM, tech lead, designer) and a central AI platform team support aligned autonomyHiring for AI fluency: how interview questions are changing and what self-augmenting engineers look likePattern detection as the leadership skill that transfers from nuclear submarines to AI emailChapters:(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 hiringConnect with Loïc:LinkedIn: https://www.linkedin.com/in/houssier/Superhuman careers: https://superhuman.com/careersSuperhuman: https://superhuman.comConnect with Conor:Newsletter: https://newsletter.chainofthought.show/Twitter/X: https://x.com/ConorBronsdonLinkedIn: https://www.linkedin.com/in/conorbronsdon/YouTube: https://www.youtube.com/@ConorBronsdonMore episodes: https://chainofthought.showThanks to Galileo — download their free 165-page guide to mastering multi-agent systems at galileo.ai/mastering-multi-agent-systems
Transcribe →
The AI Hiring Doom Loop: Applications Up 239%, Hires Down 75%
May 600:57:07Tap to summarizeJob applications are up 239% since ChatGPT launched, tech layoffs show no signs of slowing down, and the market for technical talent is a topsy turvy mess. Greenhouse has a unique vantage point to understand all of this: they process 22 million job applications a month across 7,500+ companies including HubSpot, Anthropic, Coinbase, and the NFL. CEO Daniel Chait has had a front-row seat to the strangest hiring market in decades, and he's here to advise us all on how to navigate it.Daniel coined the term "AI doom loop" for what's happening: applications up 239% since ChatGPT launched, resume hacks like white-fonting and prompt injection up 500%, and 75% fewer applications reaching the hire stage. 91% of recruiters have spotted candidate deception. 38% of job seekers walk away from processes that include an AI interview.It's the worst job market for candidates and the hardest hiring market for recruiters.Daniel explains how technical talent can break the loop.We cover:Why software engineers, according to Greenhouse data, are the worst auto-appliers and what to do insteadThe North Korean infiltration problem: deepfakes, laptop farms, and why companies are flying candidates in for in-person interviews againHow AI screener interviews open up the funnel when companies are transparent about using them, and break it when they aren'tGreenhouse Dream Jobs: how a single high-signal application a month converts at 5x the rateWhy take-home assignments don't survive contact with AI and what Greenhouse uses insteadWhat a coding interview looks like when leetcode is dead and engineers run 10+ Claude Code sessions in parallelThe case for killing the resume entirely and rebuilding hiring around AI conversationsChapters: (00:00) Cold open: 239% more applications, 75% fewer hires (02:14) Galileo (03:05) The AI doom loop, defined (04:01) How we got here: remote work, ZIRP, and ChatGPT (07:51) Are software engineering jobs really in trouble? (12:46) The trust crisis: 91% of recruiters spot deception (15:52) North Korean spies, deepfakes, and laptop farms (19:34) Can AI fix the problem it created? (20:52) AI screener interviews and the uncanny valley (26:33) Greenhouse Dream Jobs: one signal, 5x conversion (28:31) Why auto-apply doesn't work (and what does) (30:18) Communities, building in public, and the early-mover advantage (37:08) Gen Z lost trust, and the bias problem (39:04) Kill the resume: rethinking hiring from scratch (43:34) How Greenhouse changed its own interview process (48:47) Coding interviews in the agent era: leetcode is dead (51:33) Predictions: more proof, more conversations, less noise (54:34) Where job seekers and hiring teams should startConnect with Daniel:Greenhouse: https://www.greenhouse.comMy Greenhouse (for job seekers): https://www.mygreenhouse.comLinkedIn: https://www.linkedin.com/in/dhchait/Connect with Conor:Newsletter: https://newsletter.chainofthought.show/Twitter/X: https://x.com/ConorBronsdonLinkedIn: https://www.linkedin.com/in/conorbronsdon/YouTube: https://www.youtube.com/@ConorBronsdonMore episodes: https://chainofthought.showThanks to Galileo — download their free 165-page guide to mastering multi-agent systems at galileo.ai/mastering-multi-agent-systems
Transcribe →
Every AI Agent Has an Evaluation Gap | Alex Ratner, Snorkel AI
Apr 2900:42:40Tap to summarizeAlex Ratner co-founded Snorkel AI out of Chris Ré's Stanford lab and helped establish data-centric AI as a field. Today, Snorkel is a $1.3B company shipping thousands of data sets and environments a week to frontier labs and vertical AI teams like Harvey.In this conversation, he argues our ability to build AI agents has outpaced our ability to measure them. That gap is what's keeping most enterprise agents stuck in demo purgatory.If you can't measure it, you can't improve it. And you can't deploy it.In this conversation:The three axes of the evaluation gap: input complexity, autonomy horizon, and output complexityBig Law Bench: how Snorkel and Harvey benchmarked legal agents on deep-research tasks that take lawyers 10-15 hoursWhat Snorkel's $3M Open Benchmarks Grant is funding, and why "benchmaxxing" critiques don't kill the case for public benchmarksWhy 40-50% of Snorkel's data work is still review and labeling, even with the best models in the loopThe "expert-agentic" era, where domain expertise (law, finance, coding, even woodworking) is the new bottleneckWhy self-supervision is a dead end outside narrow cases like distillationThe false dichotomy between data and environments, and why pure-environment vendors miss how AI actually worksChapters(00:00) Intro: Alex Ratner and Snorkel AI (02:50) What the evaluation gap actually is (06:05) Moravec's paradox and the jagged frontier (08:46) Where AI agents fall down in enterprise work (10:40) Big Law Bench: benchmarking Harvey's legal agents (12:00) The three axes: input, autonomy horizon, output (18:31) Snorkel's $3M Open Benchmarks Grant (22:33) From "janitorial" to epicenter: 15 years of data-centric AI (29:26) The expert-agentic data era (34:54) The false dichotomy between data and environments (40:05) DoorDash Tasks and expert data at scaleConnect with Alex Ratner:X/Twitter: https://x.com/ajratnerSnorkel AI: https://snorkel.aiConnect with Conor:Newsletter: https://newsletter.chainofthought.show/Twitter/X: https://x.com/ConorBronsdonLinkedIn: https://www.linkedin.com/in/conorbronsdon/YouTube: https://www.youtube.com/@ConorBronsdonMore episodes: https://chainofthought.showThanks to Galileo — download their free 165-page guide to mastering multi-agent systems at galileo.ai/mastering-multi-agent-systems
Transcribe →
250,000 Lines of Code/Week: Inside an AMD VP's Agent-First Workflow | Anush Elangovan
Apr 2200:50:53Tap to summarizeWhat happens when a VP of AI Software at a major chip company goes all-in on AI coding agents for his own team's work?Anush Elangovan runs 10–12 Claude Code agents across three machines, burns 6.5 billion tokens a week, and rewrote a 25-year-old project (Slurm → Spur in Rust) in a single night.He does it all on dangerously-skip-permissions.About Anush Anush Elangovan is Corporate VP of AI Software at AMD. He founded Nod.ai, where his team built SHARK and was a primary contributor to Torch-MLIR and IREE. AMD acquired Nod.ai in 2023, and Anush now leads AI software strategy across AMD's full silicon portfolio. Before Nod.ai, he shipped the graphics stack on the first ARM Chromebook and led Chrome OS's migration to Gentoo.We cover:How Anush runs 10–12 parallel agents with a geo-distributed AMD hardware rigWhy the test harness is the new code review (and why agents are "sneaky and dumb")Rewriting a 25-year-old project in Rust overnight, without opening the editorWhy every new project is in Rust specifically because he refuses to learn itThe "HR partner fixing engineering bugs" moment and what it says about upskillingWhy normal SDLC is dead and speed is the only durable moatAMD's fully open-source software stack and how community contributions are accelerating ROCm"Software is just tokens" and what that means for AMD's bet against CUDA lock-inConnect with Anush LinkedIn: linkedin.com/in/anushelangovan Twitter/X: @AnushElangovan AMD AI blog: amd.com AMD AI Developer Program: amd.com/developerConnect with Conor Newsletter: newsletter.chainofthought.show Twitter/X: @ConorBronsdon LinkedIn: linkedin.com/in/conorbronsdon YouTube: @ConorBronsdonMore episodes: chainofthought.showChapters 0:00 Cold open 0:21 Welcome + guest intro 3:43 250K lines a week, 10–12 parallel agents 7:34 Agent architecture + geo-distributed test rig 9:57 When does AI-generated code become a liability? 14:12 80% tests first: the test harness philosophy 18:24 Dangerously-skip-permissions + testing as code review 19:52 "Normal SDLC is dead in the agentic world" 20:44 Advice for engineers and leaders who feel behind 24:51 Tokens, throughput, and what happens next 26:29 Block layoffs, uneven AI gains, the 25-year Slurm rewrite 32:55 Galileo sponsor break 34:24 When agents go off the rails: sneaky and dumb 37:52 Orchestrator agents vs. focused multi-threading 40:45 Open source, ROCm, AMD's software bet 44:19 "Software is just tokens" 45:24 AMD Developer Program + community contributions 47:09 Where to start with AMD 48:39 Heterogeneous compute 50:13 OutroThanks to Galileo. Download their free 165-page guide to mastering multi-agent systems at galileo.ai/mastering-multi-agent-systemsFull show notes: newsletter.chainofthought.showDisclaimer from our host: All views, opinions and statements expressed on this account are solely my own and are made in my personal capacity. They do not reflect, and should not be construed as reflecting, the views, positions, or policies of my employer. This account is not affiliated with, authorized by, or endorsed by my employer in any way.
Transcribe →Hallucinations Are a Data Architecture Problem | Sudhir Hasbe, Neo4j
Apr 1600:52:24Tap to summarizeSudhir Hasbe is President and Chief Product Officer at Neo4j, the graph database company powering 84 of the Fortune 100 (Walmart, Uber, Airbus) at $200M+ ARR and a $2B+ valuation. Before Neo4j, he ran product for all of Google Cloud's data analytics services: BigQuery, Looker, Dataflow, and led the Looker acquisition.His thesis: the hallucinations we blame on AI models are really a data architecture problem. LLMs weren't trained on your enterprise knowledge, so handing them a data lake with 10,000 disconnected tables and asking them to reason is the wrong design. The fix is knowledge graphs: feeding the model a structured map of relationships, entities, and context so it can reason over meaning, not just vector similarity.Sudhir breaks down the five capabilities knowledge graphs unlock for enterprise AI: GraphRAG (moving accuracy from 60% to 97%), semantic mapping across siloed systems, context graphs, agent memory, and multi-hop reasoning. He explains three architecture patterns customers are actually shipping, why giving an LLM hundreds of tools makes it worse, and what Uber, EA Sports, Klarna, and Novo Nordisk are doing differently.This is the case for treating knowledge as infrastructure.We cover:Why enterprise AI needs a different playbook than consumer AIThe five data asset types every agentic system needs: system of record, historical, memory, context, and referenceHow GraphRAG combines vector search and graph traversal to move from 60% accuracy to 95%+Three architecture patterns: semantic layer only, semantic map plus domain data, full consolidation (the Klarna/Kiki model)What context graphs capture that Salesforce doesn't: the Slack and email negotiation behind every dealWhy giving an LLM hundreds of tools drops accuracy, and how Uber uses knowledge graphs as a business validation layerWhat Neo4j's Aura Agent, MCP server, and A2A support mean for developers starting todayChapters:(0:00) Why building a self-driving car is hard(0:22) Intro(2:03) Hallucinations as a data architecture problem(4:31) From models-as-core to systems-of-knowledge(6:13) Why data lakes fail AI agents(9:15) The five data asset types enterprise agents need(11:46) Where basic RAG breaks down: the Spotify metadata lesson(16:00) GraphRAG: 3x accuracy, easier development, explainability(18:47) Semantic mapping across the enterprise estate(19:23) Three knowledge-graph architecture patterns(22:42) Context graphs: capturing the "why" behind decisions(25:33) Individual vs. organizational agent memory(28:40) Multi-hop reasoning for fraud rings and AML(31:52) Why there are no shortcuts in enterprise AI(36:38) What happens when you give an LLM 100 tools(39:19) The Uber example: knowledge graph as business validation(44:42) First mile of a 26-mile marathon(48:32) Aura Agent, MCP server, and the A2A protocol(50:43) Where developers should startConnect with Sudhir Hasbe:LinkedIn: https://www.linkedin.com/in/shasbe/Neo4j: https://neo4j.com/Neo4j Aura: https://neo4j.com/product/auradb/Connect with Conor:Newsletter: https://newsletter.chainofthought.show/Twitter/X: https://x.com/ConorBronsdonLinkedIn: https://www.linkedin.com/in/conorbronsdon/YouTube: https://www.youtube.com/@ConorBronsdonMore episodes: https://chainofthought.showThanks to Galileo — download their free 165-page guide to mastering multi-agent systems at: galileo.ai/mastering-multi-agent-systems
Transcribe →Why LLMs Are Plausibility Engines, Not Truth Engines | Dan Klein
Apr 801:18:13Tap to summarizeEvery few weeks at Microsoft, someone would build an AI prototype that blew everyone's minds. Three months later? Dead. "We can never ship that." Dan Klein watched this happen for five years before he decided to do something about it.Dan is co-founder and CTO of Scaled Cognition, a professor of computer science at UC Berkeley, and winner of the ACM Grace Murray Hopper Award. His previous startups include adap.tv (acquired by AOL for $405M) and Semantic Machines (acquired by Microsoft in 2018), where he spent five years integrating conversational AI. His PhD students now run AI teams at Google, Stanford, MIT, and OpenAI.At Scaled Cognition, Dan's team built APT1 (the Agentic Pre-trained Transformer) for under $11 million. It's a model designed for actions, not tokens, with structural guarantees that go beyond prompt-and-pray.Dan makes the case that current LLMs are plausibility engines, not truth engines, and that the gap between demo and production is where most AI projects die.Why prompting is a fundamentally unreliable control surface for production AIHow APT1's architecture gives actions and information first-class status instead of treating everything as tokensThe specific failure modes that kill enterprise AI prototypes within three monthsWhy stacking multiple models to check each other produces correlated errors, not reliabilityHow Scaled Cognition applied RL to conversational AI when there's no zero-sum winnerWhy every S-curve in AI gets mistaken for an exponential — and what comes after the current plateauThe societal risk of systems that produce output indistinguishable from truthChapters (0:00) Cold open: RL is about doubling down on what works (0:28) Introducing Dan Klein and Scaled Cognition (2:53) The demo-to-production gap: why AI prototypes die (5:40) Why prompting is not a real control surface (8:06) Modular decomposition vs. end-to-end optimization (10:55) Are LLMs fundamentally mismatched with how we use them? (14:26) What's wrong with benchmarks today (20:27) APT1: building a model for actions, not tokens (24:14) What makes data truly agentic (28:02) Hallucinations as an iceberg — visible vs. undetectable (34:16) Building a prototype model for under $11 million (39:57) Applying RL to conversations without a zero-sum winner (43:31) LLMs as a condensation of the web — and what happens when it runs out (50:07) Reasoning models: where they work and where they don't (53:04) Early deployments in regulated industries (57:14) Why multi-model checking fails (1:00:34) The minimum bar for trustworthy agentic systems (1:04:07) Societal risk: when AI output is indistinguishable from truth (1:13:33) Where Dan is inspired in AI research todayConnect with Dan Klein:Scaled Cognition: https://scaledcognition.comLinkedIn: https://www.linkedin.com/in/dan-klein/UC Berkeley NLP Group: https://nlp.cs.berkeley.eduConnect with Conor:Newsletter: https://newsletter.chainofthought.show/Twitter/X: https://x.com/ConorBronsdonLinkedIn: https://www.linkedin.com/in/conorbronsdon/YouTube: https://www.youtube.com/@ConorBronsdonMore episodes: https://chainofthought.showThanks to Galileo — download their free 165-page guide to mastering multi-agent systems at galileo.ai/mastering-multi-agent-systems
Transcribe →
Agent Memory: The Last Battleground in the AI Stack | Richmond Alake, Oracle
Apr 200:59:24Tap to summarizeRichmond Alake is Director of AI Developer Experience at Oracle and one of the most concrete voices on agent memory right now. His AI Engineer World's Fair talk on architecting agent memory crossed 100,000 views, he built the open-source MemoRIS library, and he co-created a course with Andrew Ng.In this conversation, Richmond walks through memory engineering as a distinct discipline from prompt engineering and context engineering, demos a memory-aware financial services agent that runs vector, graph, spatial, and relational search in a single query, and explains the principle that separates production-grade memory systems from prototypes: don't delete, forget. If you're building agents that need to remember anything across sessions, this is the episode.We cover:- Why memory engineering deserves its own name, separate from prompt and context engineering- The two failure modes Richmond sees most: wrong mental model and deleting instead of forgetting- Four human memory types mapped to agent architecture: working, episodic, semantic, and procedural- Demo: AFSA, a memory-aware financial services agent with converged search across data types- How the Generative Agents paper's decay formula (relevance + recency + importance) enables controlled forgetting- Where context engineering ends and memory engineering begins - Why files work for prototypes but databases win in productionChapters:(0:00) Memory is the last battleground in AI(0:28) Meet Richmond Alake, Oracle's AI DevEx lead(2:23) Why memory engineering is its own discipline(7:57) The failure modes nobody talks about(12:49) Demo: a memory-aware financial services agent(18:30) Segmenting context windows by memory type(19:22) Four human memory types mapped to agent architecture(23:51) Procedural memory in production systems(27:11) Don't delete, forget: implementing controlled decay (33:32) Sponsor: Galileo(35:46) Where context engineering ends and memory engineering begins(38:50) Is agent memory fundamentally a database problem?(44:13) Files vs. databases: what production actually needs(51:09) Picking your lane in the AI noise(55:44) Richmond's courses with Andrew Ng, O'Reilly classes, and where to followConnect with Richmond Alake: LinkedIn: https://www.linkedin.com/in/richmondalake/Check out his Youtube: https://www.youtube.com/@richmond_aO'Reilly courses: https://www.oreilly.com/live-events/ai-memory-management-in-agentic-systems/0642572179274/Diagrams from the episode: https://imgur.com/a/mMtcAtkConnect with Conor:Newsletter: https://newsletter.chainofthought.show/Twitter/X: https://x.com/ConorBronsdonLinkedIn: https://www.linkedin.com/in/conorbronsdon/YouTube: https://www.youtube.com/@ConorBronsdonMore episodes: https://chainofthought.showThanks to Galileo — download their free 165-page guide to mastering multi-agent systems at http://www.galileo.ai/mastering-multi-agent-systems
Transcribe →Context Poisoning Is Killing Your AI Agents: How to Stop It
Mar 2500:44:18Tap to summarizeMichel Tricot co-founded Airbyte, the open source data integration platform with 600+ free connectors that hit a $1.5 billion valuation. Now he's building the company's next product: an agent engine, currently in public beta. His thesis is that agents don't fail because models are bad. They fail because the data feeding them is wrong: context poisoning is killing them.Michel demos this live. A simple Gong query through raw API calls burned 30,000 extra tokens and took three minutes. The same query through Airbyte's context store ran in one minute and used a fraction of the context window. Conor and Michel dig into why RAG alone won't cut it, what a "context engineer" actually does, how Airbyte tracks entities across Salesforce, Zendesk, and Gong without embeddings, and whether the SaaS apocalypse playing out in public markets is overblown.Chapters:0:00 Intro0:20 Meet Michel Tricot, CEO of Airbyte2:27 Data Got Us to the Information Age. Context Gets Us to Intelligence.4:48 How Context Poisoning Breaks Agents7:49 Why Airbyte Customers Stopped Loading Into Warehouses10:12 Live Demo: Context Store vs Raw API Calls10:38 What Does a Context Engineer Actually Do?14:14 RAG Isn't Dead, But How We Build It Will Die16:41 30K Wasted Tokens Without Proper Context22:22 Cross-System Joins: Zendesk, Gong, and Salesforce26:12 The Open Source Agent Connector SDK29:45 The SaaS Apocalypse Is Overblown36:09 From Data Pipes to Agent Infrastructure38:51 What Agents Need to Get Right by Summer40:48 Memory Is Just Another Form of Context43:07 OutroAbout the Guest:Michel Tricot is the CEO and co-founder of Airbyte, the open source data integration platform used by thousands of companies to move data between systems. Before Airbyte, he led data ingestion and distribution engineering at LiveRamp. Airbyte raised at a $1.5 billion valuation and offers 600+ free connectors. The company recently launched the public beta of its agent engine, which includes a context store, agent connector SDK, and MCP integration.Guest Links:AirbyteMichel on LinkedInAgent Blueprint (Substack)Agent Connector SDK (GitHub)Show Links:Chain of Thought PodcastNewsletterConor on LinkedInConor on X/TwitterThanks to our presenting sponsor Galileo. Download their free 165-page guide to mastering multi-agent systems at galileo.ai.
Transcribe →