Max Agency

About Max Agency

Welcome to Max Agency, a podcast about how the best AI agents are actually being built. Hosted by Harrison Chase, CEO of LangChain, each episode goes deep with the builders designing, deploying, and learning from real agent systems in the wild. From architecture decisions to evals, tooling, and failure modes, Max Agency is for people who want to understand what it really takes to build useful agents.

Publisher

LangChain

Category

technology

Language

en

Explicit

No

First episode

8 Apr 2026

Latest episode

13 Aug 2026

Latest episodes

3 of 11 episodes have a transcript.

1. 

   13 Aug 2026TRANSCRIPT

   How Unify cut its AI agent costs 95% in two weeks

   Unify Co-founder and CTO Connor Heggie shares how his team drastically cut AI agent costs by 95% through innovative engineering strategies.

2. 

   30 Jul 2026TRANSCRIPT

   The misaligned incentives behind AI coding agents | Russell Kaplan, Cognition

   Russell Kaplan, President of Cognition, discusses the misaligned incentives behind AI coding agents and how Devin Fusion optimizes cost and quality in this interview.

3. 

   16 Jul 2026TRANSCRIPT

   The best AI agents cost less than you think | Eno Reyes, Factory

   Eno Reyes is the co-founder and CTO at Factory, a $1.5 billion company turning signal into deployed code inside some of the world's biggest engineering orgs. Before founding Factory in 2023, he was an engineer at Microsoft and then Hugging Face. In this conversation, Eno unpacks why the harness matters more than the model running underneath it, how to build your own 24/7 software factory, and why he's "bullish on humans in the loop for a very long time.” – We also discuss: Why product management isn't going away The engineer who lint-checks Factory's own agents Why coding agents might become the best general agents The platonic representation hypothesis Why Factory might hide when "memory" is happening Building Factory's universal meta harness Tokenomics, and how routing cuts the bill – Timestamps: (00:00) Introduction (01:19) What a 24/7 autonomous software factory actually means (03:16) Why product management isn't going away (06:56) Alvin, the engineer who lint-checks Factory's own agents (10:16) "It makes me very bullish on humans in the loop for a very long time" (11:37) The Disney Epcot analogy for rolling out AI (16:47) Why coding agents might become the best general agents (20:54) The case against a model-independent harness, and Eno's counter (25:44) The platonic representation hypothesis explained (32:42) Why model quirks are like being left or right-handed (39:28) Why you could technically decompile Factory's entire harness (44:20) Why memory might be AI's most overused word (46:47) Inside AutoWiki and its Lore feature (55:32) Agent readiness: the deterministic feedback agents need (57:12) Missions: Factory's universal meta harness (1:01:12) "It's kind of turtles all the way down": validating the validators (1:04:37) Tokenomics: what missions cost, and how routing cuts the bill (1:11:08) Why Eno is bullish on open models (1:14:30) BenchBench, and why code review benchmarks might be broken – References: Aider (https://aider.chat/) Alvin Sng (https://www.linkedin.com/in/alvinsng/) Amp (https://ampcode.com/) Andrej Karpathy (https://x.com/karpathy) Anthropic (https://www.anthropic.com/) Anthropic: Emotion concepts and their function in a large language model (https://www.anthropic.com/research/emotion-concepts-function) Cursor (https://cursor.com/) Deep Agents (https://docs.langchain.com/oss/python/deepagents/overview) DeepWiki (https://deepwiki.com/) Epcot (https://en.wikipedia.org/wiki/Epcot) Factory (https://factory.ai/) GLM (https://chat.z.ai/) Harbor (https://www.harborframework.com/) Hugging Face (https://huggingface.co/) HuggingGPT (https://arxiv.org/abs/2303.17580) Kimi (https://www.kimi.com/en) LangGraph (https://www.langchain.com/langgraph) LangSmith (https://smith.langchain.com/) MiniMax (https://www.minimax.io/) Open Knowledge Format (OKF) (https://cloud.google.com/blog/products/data-analytics/how-the-open-knowledge-format-can-improve-data-sharing/) OpenAI (https://openai.com/) OpenRouter Model Fusion (https://openrouter.ai/fusion) Ramp (https://ramp.com/) Sakana Fugu (https://sakana.ai/fugu/) SWE-bench (https://www.swebench.com/) Terminal-Bench (https://www.tbench.ai/) – Where to find Eno: LinkedIn (https://www.linkedin.com/in/enoreyes) Twitter/X (https://x.com/EnoReyes) – Where to find Harrison: LinkedIn (https://www.linkedin.com/in/harrison-chase-961287118/) Twitter/X (https://x.com/hwchase17) – Where to find LangChain: Website (https://www.langchain.com/) Docs (https://docs.langchain.com/) – Send feedback or questions to maxagency@langchain.dev (mailto:maxagency@langchain.dev)

4. 

   2 Jul 2026

   The best AI agents are secretly teams | Ben Tannyhill, LangChain

   Ben Tannyhill is a product manager at LangChain, where he's building LangSmith Engine—an agent that finds and fixes your agent's failures. Engine continuously analyzes your production traces, clusters them into actionable issues, and opens pull requests to fix them. Engine's architecture is a lot like an org chart: a main model delegating to a team of cheaper, faster sub-agents. It launched in public beta at Interrupt 2026, and in this conversation, Ben unpacks why it uses a sandbox as a tool, how the team turned it into a self-improving agent that learns from its own traces, and the hard problem of testing a fix before it ships. – We also discuss: Why Engine is "the agent for agent engineers" Making LangSmith agent-native with condensed trace views Why the team keeps handing more control to the agent Inside Engine's four sub-agents: the screener, verifier, and more Giving Engine memory with an agent overview document How to keep an always-on agent from blowing the inference budget Where Insights, Polly, and Engine are converging – Timestamps: (00:00) Introduction (01:25) LangSmith 101 (02:22) Why Engine is "the agent for agent engineers" (03:49) Under the hood: Engine is a deep agent (06:08) Clustering millions of traces with condensed views (10:10) Why the team keeps handing more control to the agent (13:21) Why Engine uses a sandbox as a tool (14:11) Engine's four sub-agents and the org-chart analogy (16:51) Evals for Engine: IssueBench, Harbor, and synthetic environments (23:05) How Engine evolved: from noisy PRs to an issue inbox (25:56) Inside Engine's memory: the agent overview document (29:25) How to keep an always-on agent from blowing the inference budget (30:52) What models Engine uses (31:30) How Engine was rolled out: from Forge to public beta at Interrupt (34:18) Inside the two teams building Engine (35:53) Where Insights, Polly, and Engine are converging (40:06) The missing piece: testing a fix before it ships (42:22) Running a branched agent, and the write-access eval problem (46:35) Using Engine as long-term memory (47:39) Pointing Engine at coding-agent traces (48:49) Running Engine on Engine: the meta self-improvement loop – References: Anthropic (https://www.anthropic.com/) Chat LangChain (https://chat.langchain.com/) Claude Code (https://www.anthropic.com/claude-code) Claude Haiku (https://www.anthropic.com/claude/haiku) Claude Opus (https://www.anthropic.com/claude/opus) Codex (https://openai.com/codex/) Context Hub (https://docs.langchain.com/langsmith/use-the-context-hub) Credit Genie (https://www.creditgenie.com/) Deep Agents (https://docs.langchain.com/oss/python/deepagents/overview) Gemini (https://gemini.google.com/) GPT-5.5 (https://openai.com/index/introducing-gpt-5-5/) Harbor (https://www.harborframework.com/) Hex (https://hex.tech/) Insights (https://docs.langchain.com/langsmith/insights) Interrupt (https://interrupt.langchain.com/) LangGraph (https://www.langchain.com/langgraph) LangSmith (https://smith.langchain.com/) LangSmith Chat (formerly Polly) (https://docs.langchain.com/langsmith/chat) LangSmith Engine (https://www.langchain.com/langsmith/engine) LangSmith Observability (https://www.langchain.com/langsmith/observability) Mintlify (https://mintlify.com/) OpenAI (https://openai.com/) Palash Shah (https://www.linkedin.com/in/palash-sh/) Terminal-Bench (https://www.tbench.ai/) Unify (https://www.unifygtm.com/) – Where to find Ben: LinkedIn (https://www.linkedin.com/in/benjamintannyhill/) Twitter/X (https://x.com/bentannyhill) – Where to find Harrison: LinkedIn (https://www.linkedin.com/in/harrison-chase-961287118/) Twitter/X (https://x.com/hwchase17) – Where to find LangChain: Website (http://langchain.com) Docs (https://docs.langchain.com/) – Send feedback or questions to maxagency@langchain.dev (mailto:maxagency@langchain.dev)

5. 

   18 Jun 2026

   The best AI agents are simpler than you think | Zack Reneau-Wedeen, Sierra

   Zack Reneau-Wedeen is the Head of Product at Sierra, the conversational AI platform behind customer-facing agents for most of the Fortune 20. Before Sierra, he spent seven years at Google as the founding PM for Google Lens and Google Podcasts, then led product at Robinhood and CoinTracker. Sierra is mostly known for customer support, but Zack reveals how and why the company is building agents that span the entire customer lifecycle, from browsing and booking to sales and loyalty. In this conversation, he argues agentic commerce will be bigger than e-commerce, explains why he's a "monolith loyalist", and unpacks why, when a model looks dumb, the problem is usually you. – We also discuss: How Sierra's no-code layer compiles down to agent code, and back again Why most multi-agent systems just ship your org chart Inside Sierra's modular voice architecture: thinking, listening, and talking in parallel Why Sierra built a PCI-certified stack for voice payments How outcome-based pricing aligns incentives Why there's no breakout memory company – Timestamps: 00:00 Introduction 03:39 Analyze, build, release: how you build on Sierra 07:54 Inside Ghostwriter 11:04 Meeting models on their turf “80% of the time 17:47 The one constraint Claude Code doesn't have 19:35 Agent-to-agent: when an API call still beats MCP 21:02 Why agentic commerce will be bigger than e-commerce 27:31 Running models in parallel and ensembling transcription 32:22 Inside the Agent Data Platform 40:00 Context engineering: everything it needs, nothing more 41:38 "Whenever you think the model's too dumb, the model's actually too smart" 46:13 Why multi-agent systems are a trap 48:44 Voice 101: latency, naturalism, and 60 languages 56:11 When voice-to-voice passes 50%: the over/under 57:03 Making memory a first-class primitive 1:02:47 Why there's no breakout memory company 1:08:02 Why the solution to all AI problems "is more AI" 1:09:20 Why Sierra open-sources the tau-bench universe 1:14:42 How outcome-based pricing aligns incentives 1:20:26 Who thrives as a forward-deployed agent builder 1:22:16 The Formula One analogy: why product is the bottleneck 1:25:47 How Sierra interviews for agency – References: Agent2Agent (A2A) Protocol (https://a2a-protocol.org/latest/) Anthropic (https://www.anthropic.com/) ChatGPT (https://chatgpt.com/) Claude (https://www.anthropic.com/claude) Claude Code (https://www.anthropic.com/claude-code) Claude Mythos (https://www.anthropic.com/claude/mythos) Claude Opus 4.5 (https://www.anthropic.com/news/claude-opus-4-5) Codex (https://openai.com/codex/) Deep Agents (https://docs.langchain.com/oss/python/deepagents/overview) Gemini (https://gemini.google.com/) Hawaiian Airlines (https://www.hawaiianairlines.com/) LangGraph (https://www.langchain.com/langgraph) Model Context Protocol (MCP) (https://modelcontextprotocol.io/) Not Another Workflow Builder (https://blog.langchain.com/not-another-workflow-builder/) Redfin (https://www.redfin.com/) Sentry (https://sentry.io/) Shopify (https://www.shopify.com/) Silero (https://github.com/snakers4/silero-vad) SiriusXM (https://www.siriusxm.com/) Stripe (https://stripe.com/) Tau-bench (https://github.com/sierra-research/tau-bench) Thinking Machines Lab (https://thinkingmachines.ai/) – Where to find Zack: LinkedIn (https://www.linkedin.com/in/zackrw/) Twitter/X (https://x.com/ZackRW) Sierra (https://sierra.ai/) – Where to find Harrison: LinkedIn (https://www.linkedin.com/in/harrison-chase-961287118/) Twitter/X (https://x.com/hwchase17) – Where to find LangChain: Website (http://langchain.com) Docs (https://docs.langchain.com/) – Send feedback or questions to maxagency@langchain.dev (mailto:maxagency@langchain.dev)

6. 

   4 Jun 2026

   The tool design tricks behind Benchling's AI agents

   Nick Larus-Stone is the Head of AI at Benchling, the R&D data platform that life science companies use to store and manage their experiments, samples, instruments, and analysis. Benchling has been around for since 2012. In October 2025, it launched Benchling AI, an intelligence layer with a chat interface, backed by an agent, that helps scientists find data, design experiments, and write reports. Nick came to Benchling through its acquisition of Sphinx Bio, the analysis startup he founded. In this conversation, Nick walks through what it takes to build agents for scientific work, and where the playbook from coding agents holds up and where it breaks down. – We also discuss: Why Benchling invests so heavily in getting clean data upfront How they cross-check answers between models to get more out of each one Why and how Benchling leans on production traces Where AI actually helps science today, and where it still gets stuck Why understanding LLMs is closer to biology than software engineering – Timestamps: 00:00 Intro 01:22 What Benchling AI is, and the 14-year data platform underneath it 04:36 Why a decade of structured data is a core advantage 05:57 The architecture under the hood 08:28 Similarities and differences compared to a coding harness 11:14 Benchling’s multi-agent architectures 14:36 Dealing with verifiable vs non-verifiable tasks 16:19 Doing evals when clean benchmarks aren’t possible 18:13 Context engineering: SQL vs. file-based harnesses 22:11 Memory: agents that create and update their own skills 25:30 What user education for scientists looks like 30:33 Why understanding LLMs is closer to biology than software 33:28 When will agents discover a novel cure for disease? 44:58 The future of harnesses in science 48:13 Why fine-tuning on biology hasn't beaten frontier models – References: Agent Skills (Claude Docs) (https://docs.claude.com/en/docs/agents-and-tools/agent-skills/overview) Benchling’s Deep Research Agent (https://www.benchling.com/blog/complex-questions-fast-answers-benchling-deep-research) Claude (Anthropic) (https://www.anthropic.com/claude) Design of experiments (DOE) (https://en.wikipedia.org/wiki/Design_of_experiments) FDA Investigational New Drug (IND) application (https://www.fda.gov/drugs/types-applications/investigational-new-drug-ind-application) Gemini (Google) (https://gemini.google.com/) Google AI co-scientist (https://research.google/blog/accelerating-scientific-breakthroughs-with-an-ai-co-scientist/) LangSmith (https://www.langchain.com/langsmith) Model Context Protocol (MCP) (https://modelcontextprotocol.io/) The Ralph (Wiggum) Loop (Geoffrey Huntley) (https://ghuntley.com/ralph/) Sphinx Bio (https://www.benchling.com/blog/resync-bio-and-sphinx-bio-join-benchling) – Where to find Nick: Benchling (https://www.benchling.com/) LinkedIn (https://www.linkedin.com/in/nlarusstone/) Twitter/X (https://x.com/nlarusstone) – Where to find Harrison: LinkedIn (https://www.linkedin.com/in/harrison-chase-961287118/) Twitter/X (https://x.com/hwchase17) – Where to find LangChain: Website (https://www.langchain.com/) Docs (https://docs.langchain.com/) – Send feedback or questions to maxagency@langchain.dev (mailto:maxagency@langchain.dev)

7. 

   22 May 2026

   How Cogent builds AI agents that have to be right every single time | Geng Sng (Co-founder & CTO - Cogent)

   Geng Sng is co-founder and CTO of Cogent, which builds autonomous agents that remediate vulnerabilities for enterprise security teams. Today, Cogent's agents process billions of security events per day, maintaining a live context graph of every asset and vulnerability across customer environments. In this conversation, Geng walks through Cogent's hot vs cold context split, the sub-agents that handle side quests, and the two graphs they run in parallel. – We also discuss: Why defensive security is harder for AI than offensive Under the hood of Cogent's three agents Inside Cogent's “read only” by-default sandboxes Why graph databases don't scale for security data Cogent Research and the move into formal verification Why interactive agents need a deeper planning phase to one-shot – Referenced: Abnormal AI (https://abnormal.ai/) Amazon S3 (https://aws.amazon.com/s3/) Anthropic (https://www.anthropic.com/) Bash (https://www.gnu.org/software/bash/) ChatGPT (https://chatgpt.com/) Claude Code (https://www.anthropic.com/claude-code) Claude Mythos (https://red.anthropic.com/2026/mythos-preview/) CodeMender (https://deepmind.google/blog/introducing-codemender-an-ai-agent-for-code-security/) Codex (https://openai.com/codex/) Cogent (https://www.cogent.com/) Cursor (https://cursor.com/) Google DeepMind (https://deepmind.google/) GPT-5.5-Cyber (https://openai.com/index/gpt-5-5-with-trusted-access-for-cyber/) Jupyter (https://jupyter.org/) Letta (https://www.letta.com/) Mozilla (https://www.mozilla.org/) OpenAI (https://openai.com/) Opus 4.6 (https://www.anthropic.com/news/claude-opus-4-6) Opus 4.7 (https://www.anthropic.com/news/claude-opus-4-7) Vercel (https://vercel.com/) – Where to find Geng: LinkedIn (https://www.linkedin.com/in/geng-sng/) – Where to find Harrison: LinkedIn (https://www.linkedin.com/in/harrison-chase-961287118/) Twitter/X (https://x.com/hwchase17) – Where to find LangChain: Website (https://www.langchain.com/) Docs (https://docs.langchain.com/) – Send feedback or questions to maxagency@langchain.dev (mailto:maxagency@langchain.dev) – Timestamps: 00:00 Why mean time to exploit collapsed from years to minutes 02:08 Inside Cogent's Agent Lake architecture 05:11 Why Cogent rejected graph databases 10:48 The trust ladder before agents touch production 15:13 The three types of agents inside Cogent 17:07 How Cogent sandboxes its agents 19:16 Short-circuiting interactive agents with a deeper planning phase 24:31 What to do when users believe agents too much 31:21 Why sub-agents let agents go on side quests 34:59 Two-tiered evals and the metric that catches bad prompts 40:00 Cogent’s unique approach to context 48:39 Cogent Research and the move into formal verification 51:33 The single trait Cogent hires for 54:00 Open-sourcing models within six months 57:07 Why defensive security won’t be commoditized anytime soon 1:00:51 The founding insight behind Cogent

8. 

   7 May 2026

   How Ramp built an AI agent that can think outside of tokens | Alex Shevchenko

   Alexander Shevchenko is the head of applied research at Ramp, where he leads Ramp Labs – the team behind Ramp Sheets and a steady stream of public AI engineering experiments. Ramp Sheets started as an internal process mining tool that turned Loom videos of accountants into Markov diagrams, before evolving into the agentic spreadsheet editor that shipped in November. In this conversation, Alex walks through the architecture under the hood, why Ramp biases the agent toward Excel formulas over Python code gen, and two recent Labs experiments: Latent Briefing and a user-steerable revival of Golden Gate Claude. We also discuss: Under the hood of Ramp Sheets Inspect, Ramp's internal coding agent, and the self-improving monitor loop it powers Why finance professionals rejected code gen as too "black box" Why Anthropic models tend to excel at agentic spreadsheet manipulation The case for putting the agent outside the sandbox, not inside it The Loom-to-Markov-diagram process mining pipeline RLMs and how subagents can share memory in latent space Latent Briefing and KV-cache communication between subagents Reviving Golden Gate Claude with steering vectors on Gemma Referenced: Alex Levinson (https://www.linkedin.com/in/alex-levinson/) Anthropic (https://www.anthropic.com/) Ben Geist (https://www.linkedin.com/in/benjamin-geist/) Claude (https://www.anthropic.com/claude) Efficient Memory Sharing for Multi-Agent Systems via KV Cache Compaction (Ben Geist) (https://x.com/RampLabs/status/2042660310851449223) Gemma (https://ai.google.dev/gemma) Golden Gate Claude (https://www.anthropic.com/news/golden-gate-claude) Graphviz (https://graphviz.org/) Inspect (https://builders.ramp.com/post/why-we-built-our-background-agent) Latent Briefing (https://x.com/RampLabs/status/2042672773747589588) Loom (https://www.loom.com/) Modal (https://modal.com/) OpenAI (https://openai.com/) Opus (https://www.anthropic.com/claude/opus) Qwen (https://qwen.ai/) Ramp (https://ramp.com/) Ramp Labs (https://ramplabs.substack.com/) Ramp Sheets (https://labs.ramp.com/sheets) Recursive Language Models (Alex Zhang) (https://alexzhang13.github.io/blog/2025/rlm/) Retool (https://retool.com/) Self-maintaining Ramp Sheets (https://ramplabs.substack.com/p/self-maintaining) Steer AI (https://labs.ramp.com/steer-ai) Where to find Alex: LinkedIn (https://www.linkedin.com/in/shevalex) Twitter/X (https://x.com/shevchenkoaalex) Website (https://www.alshevchenko.com/) Where to find Harrison: LinkedIn (https://www.linkedin.com/in/harrison-chase-961287118/) Twitter/X (https://x.com/hwchase17) Where to find LangChain: Website (http://langchain.com) Docs (https://docs.langchain.com/) Send feedback or questions to maxagency@langchain.dev (mailto:maxagency@langchain.dev) Timestamps: 00:00 Introduction 01:13 The origin of Ramp Sheets 02:27 The Loom-to-Markov-diagram process mining pipeline 04:28 Why code gen approaches felt too "black box" to finance 06:13 Meeting finance where they already are: inside the spreadsheet 09:08 How far process mining got them 10:31 Text descriptions and Graphviz DAGs as output 12:41 Under the hood of Ramp Sheets 14:52 Why the agent uses Python only as an escape hatch 15:47 Why Anthropic models excel at agentic spreadsheet manipulation 17:12 Frankensteining the OpenAI Agents SDK 17:43 The Ramp Sheets UX and fast vs. expert mode 19:58 Agent in a sandbox vs. agent with a sandbox 21:55 Vibe evals with expert humans 23:40 Inspect, the internal coding agent 24:13 The self-monitoring loop and auto-PRs 28:01 Other wacky experiments on Sheets 28:43 Memory experiments that didn't pan out 31:16 Latent Briefing and KV-cache subagent communication 35:13 Reviving Golden Gate Claude 37:47 Contrastive pairs and steering vectors 39:47 Picking the right layers in Gemma 41:37 What Ramp Labs looks for when hiring

9. 

   23 Apr 2026

   How Listen is building a system of AI Agents & subagents for specialized tasks | Florian Juengermann, CTO

   Florian Juengermann is the co-founder and CTO of Listen, an AI startup that turns qualitative research across hundreds of interviews, surveys, and focus groups into structured, traceable insights. Listen's agents analyze responses at scale, and Florian has rearchitected the system multiple times to get there. In this conversation, he walks through the virtual table architecture at the core of their Research Agent, how small models run map-reduce classification across thousands of open-ended responses, and the self-reviewing feedback subagent that catches errors during long async runs. We also discuss: The three agents inside Listen's platform How Listen rearchitected from a simple RAG bot to a multi-agent system multiple times Why the PowerPoint subagent was completely rebuilt using Claude's code SDK Contextual prompt engineering as an alternative to skills How Listen keeps report numbers live as new interview responses come in When to trigger the long-running agent vs. showing early results What Florian looks for when hiring agent engineers References: Anthropic (https://www.anthropic.com/) ChatGPT (https://chatgpt.com/) Claude (https://claude.ai/) Claude Code SDK (https://docs.anthropic.com/en/docs/claude-code/sdk) E2B (https://e2b.dev/) Emotional Intelligence (https://listenlabs.ai/features/emotional-intelligence) GPT Mini (https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/) Haiku (https://www.anthropic.com/claude/haiku) Listen (https://listenlabs.ai/) OpenAI (https://openai.com/) Pandas (https://pandas.pydata.org/) Postgres (https://www.postgresql.org/) Python (https://www.python.org/) Research Agent (https://listenlabs.ai/features/research-agent) Render (https://render.com/) Zoom (https://zoom.us/) Where to find Florian: LinkedIn (https://www.linkedin.com/in/juengermann/) Twitter/X (https://x.com/florian_jue) Where to find Harrison: LinkedIn (https://www.linkedin.com/in/harrison-chase-961287118/) Twitter/X (https://x.com/hwchase17) Where to find LangChain: Website (http://langchain.com) Docs (https://docs.langchain.com/) Send feedback or questions to maxagency@langchain.dev Timestamps 00:00 Introduction 01:25 The three agents inside Listen's platform 03:15 Live chat vs. long async runs, and how Listen tunes for each 05:33 Under the hood of the Research Agent 06:37 Listen's virtual table architecture 07:34 How small models classify thousands of open-ended responses 10:05 Running code in a sandbox: how E2B fits in 11:52 Why Listen rebuilt the PowerPoint subagent from scratch 14:11 Contextual prompt engineering instead of skills 16:32 The feedback subagent that reviews its own reports 18:14 How Listen runs evals in production 19:47 Unexpected ways users push the agent to its limits 21:42 How many times Listen has rearchitected, and why 24:59 Trace observability: depth over breadth 26:10 Lessons from running Claude Code SDK inside E2B 27:42 Memory: what's solved and what isn't 29:10 The Composer agent UX: co-editing a document with AI 35:50 How Listen keeps report numbers live as new responses come in 43:47 What Listen looks for when hiring agent engineers

10. 

    9 Apr 2026

    How Hex builds AI agents that reason like human data analysts | Izzy Miller, AI Engineer

    Izzy Miller is an AI engineer at Hex, an AI analytics platform that was one of the first companies to ship data agents to real paying users. Today, Hex runs a multi-agent system with nearly 100K tokens of tools, and Izzy is building a 90-day simulation to evaluate whether those agents actually get smarter over time. In this conversation, he walks through the harness decisions that shaped their architecture, the failure modes Hex is seeing at scale, and what it takes to build an eval that no current model can pass. We also discuss: Why data agents are harder to verify than coding agents Under the hood of Hex’s agents How Hex is unifying separate agents Why most eval sets are bad The 90-day simulation for long-horizon evals How Izzy went from marketing to AI engineer References: Andon Labs (https://andonlabs.com/) Anthropic (https://www.anthropic.com/) Barry McCardel (linkedin.com/in/barrymccardel) ChatGPT (http://chatgpt.com) Claude Code (https://code.claude.com/docs/en/overview) Claude Sonnet 4.6 (https://www.anthropic.com/news/claude-sonnet-4-6) DBT (https://www.getdbt.com/) GPT-3.5 Turbo (https://developers.openai.com/api/docs/models/gpt-3.5-turbo) GPT-5.3 Codex Spark (https://openai.com/index/introducing-gpt-5-3-codex-spark/) GPT-5.4 (https://openai.com/index/introducing-gpt-5-4/) Hex (https://hex.tech/) LangChain (https://www.langchain.com/) LangSmith (https://www.smith.langchain.com/) Looker (https://lookerstudio.google.com/) OpenAI (https://openai.com/) Opus 4.6 (https://www.anthropic.com/news/claude-opus-4-6) Satya Nadella (https://www.linkedin.com/in/satyanadella) Snowflake (https://www.snowflake.com/en/) Vending Machine (https://andonlabs.com/vending) Where to find Izzy: LinkedIn (https://www.linkedin.com/in/izzy-miller/) Twitter/X (https://x.com/isidoremiller) Where to find Harrison: LinkedIn (https://www.linkedin.com/in/harrison-chase-961287118/) Twitter/X (https://x.com/hwchase17) Where to find LangChain: Website (http://langchain.com) Docs (https://docs.langchain.com/) Send feedback or questions to maxagency@langchain.dev Timestamps: 01:35 Where Hex's notebook agent started 03:46 The moment Hex knew it was time for agents 07:36 Why data agents are harder to verify than coding agents 09:30 How Hex is unifying separate agents 13:28 Under the hood of the notebook agent 15:41 The harness features that are now holding the agent back 17:41 Why Hex built their own orchestrator 18:59 Managing nearly 100K tokens of tools 20:49 Ephemeral queries and agent behavior trade-offs 24:46 The UX problem with showing agents' thinking 27:28 Why verification is harder than transparency for data agents 31:00 Memory, context conflicts, and collapse modes 34:38 How Hex built their internal eval system 39:29 Why most eval sets are bad 44:30 The 900% quota eval that every model fails 46:55 Model upgrades and the "in distribution" debate 51:34 How Izzy went from marketer to AI engineer 59:59 The 90-day simulation for long-horizon evals

11. 

    8 Apr 2026

    Welcome to Max Agency

    Welcome to Max Agency, the podcast that goes deep into how the best agents are being built by builders like you. I'm Harrison Chase, CEO of LangChain, the agent engineering company, and I'll be your host.

Inside a recent episode

How Unify cut its AI agent costs 95% in two weeks

Published 13 Aug 2026 · Transcript excerpt

[…] Are models good at operating over tabular data? No, but they're really good at writing pandas-like code, which is really good at operating over tabular data. So yes, we had a whole thing around how you would basically make it accessible to the model. We ended up with this sort of class that wraps a data store that we basically implement. It's like, imagine we virtualize the tabular data. It's actually just in the database for us. Then we re-implemented a bunch of pandas-like functions on top of that class. In TypeScript. In TypeScript, though, to let it do things like filters and fetch rows, ag rows, re-sort columns, change data types, map rows. […]

Reach and audience

Public platform figures. Ratings count people who left a rating, not total listeners.

Apple Podcasts (US)

5.0 / 5

12 ratings

Spotify

5.0 / 5

25 ratings

Contact Max Agency

Guest appearances

Books guests

Based on episode analysis; this does not confirm that the show is currently accepting guests.

Shows with a similar audience

• 

  No Priors: Artificial Intelligence | Machine Learning | Technology | Startups

• 

  Training Data

• 

  AI + a16z

• 

  Y Combinator

• 

  a16z Podcast

• 

  Practical AI: Machine Learning, Data Science

Questions about Max Agency