Discover
Max Agency
Max Agency
Author: LangChain
Subscribed: 31Played: 245Subscribe
Share
© LangChain
Description
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.
12 Episodes
Reverse
Jeff Barg is Head of AI at Clay, the go-to-market platform for list building, data enrichment and orchestration, with a dataset of 900 million contacts and 40 million companies. Clay recently launched a new global agent, built around a coding agent that runs on the same CLI external agents use. In this conversation, Jeff explains why Clay got more out of harness engineering than post-training, how the agent asks for approval on 100+ line Bash commands, and why he’d rather charge for tokens than outcomes. –We also discuss:Where a first-party agent beats a plugin on latency and costMaking a SQL-like query language for Clay’s search platformThe case for picking an off-the-shelf harnessWhy Codex is “really bad” at debugging long tracesWhy memory came before the agent –Timestamps:(00:00) Introduction(01:11) From Sculptor to the global agent: tasks vs outcomes(07:32) Making Clay agent-friendly, and the CLI RevOps teams love(11:50) How Clay’s evals moved from capabilities to user journeys(15:54) First-party agent vs plugin: when to build your own(20:05) Why Clay built around a coding agent(21:53) What post-training taught Clay, and a SQL-like search language(26:49) The case for an off-the-shelf harness(30:14) Do lab-built harnesses really work best?(33:10) Running the agent outside the sandbox(37:51) Why Codex is bad at debugging long traces(41:16) Knowledge Hub: building memory before the agent(46:25) Multiplayer agents, and what the agent looks like in Slack(48:24) How close the agent is to an AI head of growth(53:44) Where the harness ends and infrastructure begins(56:57) Why Clay would rather charge for tokens than outcomes(59:14) Fine-tuning, and a post-trained model router for Claygent(01:02:37) Approvals for 100-line Bash commands(01:06:36) Eval environments and simulated users –References:Account Agents (Clay)BullMQChristina CacioppoClaude CodeClaude FableClaude HaikuClaude OpusClaude SonnetClayClay AgentClay CLIClaygentClaygent auto-modeClaygent BuilderCodexDeep AgentsDots (OpenAI)HarveyInstinctKnowledge Hub (Clay)LangSmithLangSmith Chat (formerly Polly)LangSmith EngineMuse (Meta)OpenClawParker ConradPiQuickJS –Where to find Jeff:LinkedInTwitter/X –Where to find Harrison:LinkedInTwitter/X –Where to find LangChain:WebsiteDocs –Send feedback or questions to [email protected]
Connor Heggie spent his early career on a fifteen-person self-driving startup run like a research lab, then moved to Scale AI's mapping team, before becoming the co-founder and CTO at Unify. Unify builds agents for go-to-market teams, and for the last two years, one of AI's big mainstream narratives has been automating away the sales rep entirely. Connor and his team built the opposite: an agent that gives every sales rep "an engineer in their back pocket." He walks through how Unify's harness evolved from million-agent batch jobs to a chat product, and unpacks the engineering that makes it cost-effective to run at scale.–We also discuss:How Unify cut 90-95% of costs two weeks before launchThe 15-requests-per-second ceiling inside OpenAI's prompt cacheWhy your LLM judge must be a different model familyThe Speed Audit: why one at a time beats a table of 1,000Why Unify's subagents are just a function callWhat working on self-driving taught Connor about running evals–Timestamps:00:00 Introduction01:30 "Go-to-market is a search problem"06:10 The old workflow: drag-and-drop nodes over a million-row table09:40 Why the harness is similar to a coding agent's10:50 Running durable agents in the cloud without a full VM13:15 Giving models pandas-like superpowers over a live table15:50 Why Unify's subagents are just a function call18:25 The 15-requests-per-second limit hiding inside OpenAI's cache24:20 Optimizing for prompt caching hit rates28:20 Fork versus child subagents32:35 The Speed Audit: why one at a time beats a table of 1,00037:50 Locking memory to keys instead of letting the agent freestyle44:15 Why AI isn’t taking over sales49:00 What working on self-driving taught Connor about running evals52:46 Why your LLM judge must be a different model family54:45 Ditching full VMs for Monty, a Python REPL that suspends58:55 Semantic merge sort: why Connor is obsessed with RLMs59:53 How Unify cut 90-95% of costs two weeks before launch1:01:15 The case for "semantic linters" over skill files1:04:55 Why Unify runs mostly on OpenAI, their first investor1:06:12 Why 10x cheaper tokens still lose on tool efficiency1:07:24 Why open-source models don’t make economic sense (yet)–Referenced:AnthropicChatGPTClaudeClaude Fable 5Claude Sonnet 5Context HubDeep AgentsGLM-5.2GPT-5.4Helm.aiLangSmithOpenAIQuickJSRecursive Language Models (RLM)SalesforceScale AIScaling Managed AgentsUnify–Where to find Connor:Twitter/XLinkedIn–Where to find Harrison:Twitter/XLinkedIn–Where to find LangChain:Twitter/XLinkedIn–Send feedback or questions to [email protected]
Russell Kaplan is the President of Cognition, the $26 billion company behind Devin, the AI software engineer. He started his career in machine learning at Tesla's Autopilot team, then led the ML org at Scale AI, which had acquired his computer vision startup Helia. In this conversation, Russell unpacks why more and more engineering work is becoming "intelligence saturated," how the sidekick architecture inside Devin Fusion cuts cost without cutting quality, and why Cognition is underwriting a $10 million productivity guarantee.–We also discuss:Why mergeability is the next eval barWhen to use Fable vs GPT modelsHow smarter routing unlocked 35% better price performanceWhy letting users pick their own model is a UX bugWiring agents to be proactive instead of reactiveHow Cognition scores a session productive or unproductive–Timestamps:(00:00) Introduction(01:21) Launching Devin at 13% on SWE-bench(02:47) When Devin became the number one committer to Devin(05:56) Intelligence saturation: when speed and cost start to matter more(07:05) When to use Fable vs GPT models(08:41) Why mergeability is the next eval bar(10:51) How open source maintainers shaped FrontierCode(14:56) The telltale sign of agent-written code(17:56) When per-person token spend starts to eclipse salaries(20:26) Why letting users pick their own model is a UX bug(21:46) How smarter routing unlocked 35% better price performance(23:50) Why Cognition still trains its own models(27:13) Deploying Cerebras at scale at 950 tokens per second(28:21) The Tesla chip debate: does an inference chip need division?(30:06) Wiring agents to be proactive instead of reactive(32:19) Why "software factory" is the wrong term(35:16) Why everyone is now a new grad(41:10) Forward deployed engineering, and why ex-founders thrive(43:16) The industry's incentive to get you tokenmaxxing(45:11) How Cognition scores a session productive or unproductive(46:51) Underwriting a $10 million productivity guarantee(48:11) Using productivity dashboards to coach, not police–References:AnthropicCerebrasClaude FableClaude OpusCognitionCognition's AI Productivity GuaranteeDevinDevin DesktopDevin FusionDevin ReviewDevin Security SwarmEstimating the Productivity of an Autonomous AI Software EngineerFrontierCodeGPT-5.5GPT-5.5-CyberHarborLangSmithOpenAIOpenRouter Model FusionSWE-1.6SWE-benchTesla–Where to find Russell:LinkedInTwitter/X–Where to find Harrison:LinkedInTwitter/X–Where to find LangChain:WebsiteDocs–Send feedback or questions to [email protected]
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 awayThe engineer who lint-checks Factory's own agentsWhy coding agents might become the best general agentsThe platonic representation hypothesisWhy Factory might hide when "memory" is happeningBuilding Factory's universal meta harnessTokenomics, 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:AiderAlvin SngAmpAndrej KarpathyAnthropicAnthropic: Emotion concepts and their function in a large language modelCursorDeep AgentsDeepWikiEpcotFactoryGLMHarborHugging FaceHuggingGPTKimiLangGraphLangSmithMiniMaxOpen Knowledge Format (OKF)OpenAIOpenRouter Model FusionRampSakana FuguSWE-benchTerminal-Bench–Where to find Eno:LinkedInTwitter/X–Where to find Harrison:LinkedInTwitter/X–Where to find LangChain:WebsiteDocs–Send feedback or questions to [email protected]
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 viewsWhy the team keeps handing more control to the agentInside Engine's four sub-agents: the screener, verifier, and moreGiving Engine memory with an agent overview documentHow to keep an always-on agent from blowing the inference budgetWhere 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:AnthropicChat LangChainClaude CodeClaude HaikuClaude OpusCodexContext HubCredit GenieDeep AgentsGeminiGPT-5.5HarborHexInsightsInterruptLangGraphLangSmithLangSmith Chat (formerly Polly)LangSmith EngineLangSmith ObservabilityMintlifyOpenAIPalash ShahTerminal-BenchUnify–Where to find Ben:LinkedInTwitter/X–Where to find Harrison:LinkedInTwitter/X–Where to find LangChain:WebsiteDocs–Send feedback or questions to [email protected]








