https://www.brgr.one/blog Notes on AI agents in production — how they get built, coded, operated, and governed. Reading the research and incident reports for what survives contact with production. en-us mail@brgr.one (Patrick Burger) mail@brgr.one (Patrick Burger) Thu, 11 Dec 2025 00:00:00 GMT https://www.brgr.one/blog/ai-code-generation-quality-gap https://www.brgr.one/blog/ai-code-generation-quality-gap Notes on Itamar Friedman's talk about Qodo's research into what happens to code quality when AI triples output. Thu, 11 Dec 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) ai-code-generationsoftware-qualityagentic-aitalk-notes https://www.brgr.one/blog/beyond-scaling-next-ai-breakthroughs https://www.brgr.one/blog/beyond-scaling-next-ai-breakthroughs Notes on Ilya Sutskever's interview with Dwarkesh Patel about why the next breakthroughs will come from generalization, not scale. Sat, 29 Nov 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) ai-researchgeneralizationcontinual-learningtalk-notes https://www.brgr.one/blog/ai-platform-strategy-infrastructure-over-integrations https://www.brgr.one/blog/ai-platform-strategy-infrastructure-over-integrations Notes on Dane Knecht's talk about Cloudflare's AI infrastructure: opinionated primitives, edge scheduling and 75%+ GPU utilization. Fri, 31 Oct 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) ai-platform-strategyenterprise-aiplatform-engineeringinfrastructure-strategydeveloper-experiencetalk-notes https://www.brgr.one/blog/startups-vs-enterprise-ai https://www.brgr.one/blog/startups-vs-enterprise-ai Notes on a Y Combinator discussion about why enterprise AI projects stall and where startups fit. Thu, 30 Oct 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) aienterprisestartupsproductstrategytalk-notes https://www.brgr.one/blog/ai-agents-cognitive-core https://www.brgr.one/blog/ai-agents-cognitive-core Notes on Andrej Karpathy's interview with Dwarkesh Patel about why AI agents still lack a robust cognitive core. Fri, 24 Oct 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) ai-agentsmachine-learningstartup-strategytalk-notes https://www.brgr.one/blog/data-streaming-ai-real-time https://www.brgr.one/blog/data-streaming-ai-real-time Notes on Andrew Sellers' (Confluent) talk about governed, real-time data streams as the foundation for scaling AI. Tue, 21 Oct 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) data-streamingai-infrastructurereal-time-systemsai-agentstalk-notes https://www.brgr.one/blog/ai-agents-enterprise-security https://www.brgr.one/blog/ai-agents-enterprise-security Notes on Abnormal Security CISO Mike Britton's talk about AI agents and enterprise security. Fri, 17 Oct 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) ai-securityenterprise-itbusiness-strategyzero-trustagentic-aitalk-notes https://www.brgr.one/blog/operationalizing-ai-agents https://www.brgr.one/blog/operationalizing-ai-agents Notes on Sokratis Kartakis's Google Cloud Tech talk about operationalizing AI agents from prototype to production. Wed, 08 Oct 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) ai-agentsmlopsgenaiopstalk-notes https://www.brgr.one/blog/iam-for-ai-agents https://www.brgr.one/blog/iam-for-ai-agents Notes on Michael Grinich's (WorkOS) talk about authentication, authorization and audit for AI agents. Fri, 03 Oct 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) ai-agentsidentity-managemententerprise-securitytalk-notes https://www.brgr.one/blog/beyond-llms-adaptive-ai-agents https://www.brgr.one/blog/beyond-llms-adaptive-ai-agents Notes on Richard Sutton's interview with Dwarkesh Patel about why static LLMs fall short and agents must learn from experience. Sun, 28 Sep 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) aireinforcement-learningmachine-learningtalk-notes https://www.brgr.one/blog/ai-coding-agents-tdd-enforcement https://www.brgr.one/blog/ai-coding-agents-tdd-enforcement Notes on Jo Van Eyck's demonstration of enforcement layers that keep AI coding agents in red-green-refactor cycles. Sat, 20 Sep 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) ai-codingtddsoftware-qualitytalk-notes https://www.brgr.one/blog/building-reliable-ai-agents https://www.brgr.one/blog/building-reliable-ai-agents Notes on Rafal Wilinski's Software Huddle conversation about balancing deterministic guardrails and agent flexibility. Tue, 16 Sep 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) ai-agentsmachine-learningproduct-developmenttalk-notes https://www.brgr.one/blog/optimizing-llm-inference-for-scale https://www.brgr.one/blog/optimizing-llm-inference-for-scale Notes on Philip Kiely's conversation about cutting latency and cost in production LLM inference. Fri, 12 Sep 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) llminferenceai-infrastructuretalk-notes https://www.brgr.one/blog/startups-edge-ai-enterprise-shift https://www.brgr.one/blog/startups-edge-ai-enterprise-shift Notes on Aaron Levie's Y Combinator conversation about why AI opens enterprise software to startups. Mon, 08 Sep 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) aistartupsenterprise-softwaretalk-notes https://www.brgr.one/blog/ai-agents-end-of-saas https://www.brgr.one/blog/ai-agents-end-of-saas Notes on Replit CEO Amjad Masad's conversation about AI agents reshaping software creation and SaaS. Sun, 31 Aug 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) ai-agentssoftware-engineeringfuture-of-worktalk-notes https://www.brgr.one/blog/forward-deployed-engineer-ai-playbook https://www.brgr.one/blog/forward-deployed-engineer-ai-playbook Notes on Bob McGrew's Y Combinator interview about the forward deployed engineer model for AI products. Wed, 27 Aug 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) ai-startupsproduct-strategyengineering-leadershiptalk-notes https://www.brgr.one/blog/advanced-context-engineering-ai-agents https://www.brgr.one/blog/advanced-context-engineering-ai-agents Notes on Dexter Horthy's talk about context engineering that makes coding agents work in large, messy codebases. Mon, 25 Aug 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) ai-agentscontext-engineeringsoftware-developmenttalk-notes https://www.brgr.one/blog/cursor-100m-arr-strategy https://www.brgr.one/blog/cursor-100m-arr-strategy Notes on Michael Truell's conversation about how Cursor grew to $100M ARR in a year. Tue, 19 Aug 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) aideveloper-toolsstartup-strategytalk-notes https://www.brgr.one/blog/scaling-legal-ai-in-conservative-markets https://www.brgr.one/blog/scaling-legal-ai-in-conservative-markets Notes on Max Junestrand's conversation about growing Legora in a conservative legal market. Fri, 15 Aug 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) ailegaltechstartup-growthtalk-notes https://www.brgr.one/blog/agentic-ai-enterprise-scale-box https://www.brgr.one/blog/agentic-ai-enterprise-scale-box Notes on Box CTO Ben Kus's talk about moving from simple LLM calls to an agentic platform for enterprise content. Thu, 07 Aug 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) ai-architectureenterprise-aiagentic-systemstalk-notes https://www.brgr.one/blog/scaling-ai-knowledge-apps-blackrock https://www.brgr.one/blog/scaling-ai-knowledge-apps-blackrock Notes on the BlackRock talk by Vaibhav Page and Infant Vasanth about a sandbox and app-factory framework for shipping LLM apps in a regulated environment. Sun, 03 Aug 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) aillmenterprise-softwareautomationfinancial-servicestalk-notes https://www.brgr.one/blog/multi-agent-ai-network-knowledge-graphs https://www.brgr.one/blog/multi-agent-ai-network-knowledge-graphs Notes on Ola Mabadeje's (Cisco Outshift) talk about AI agents and a network knowledge graph for safer change management. Wed, 30 Jul 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) ai-agentsknowledge-graphnetwork-operationstalk-notes https://www.brgr.one/blog/anthropic-llm-architecture-strategy https://www.brgr.one/blog/anthropic-llm-architecture-strategy Notes on Tom Brown's Y Combinator conversation about scaling, infrastructure and building Claude Code. Sat, 26 Jul 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) aillminfrastructurestartupsproduct-strategytalk-notes https://www.brgr.one/blog/ai-model-interpretability-anthropic https://www.brgr.one/blog/ai-model-interpretability-anthropic Notes on Anthropic's discussion of interpretability research and what it reveals about how models think. Tue, 22 Jul 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) aiinterpretabilityllmtalk-notes https://www.brgr.one/blog/2025-ai-evaluation-boardroom https://www.brgr.one/blog/2025-ai-evaluation-boardroom Notes on John Dickerson's conversation about AI evaluation and monitoring moving from technical teams to the boardroom. Fri, 18 Jul 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) ai-evaluationenterprise-aiai-governancetalk-notes https://www.brgr.one/blog/agentic-ai-finance-automation https://www.brgr.one/blog/agentic-ai-finance-automation Notes on a Y Combinator conversation with Model ML about bringing agentic AI to finance workflows. Mon, 14 Jul 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) aifinanceautomationenterpriseyctalk-notes https://www.brgr.one/blog/demis-hassabis-ai-simulation-agi https://www.brgr.one/blog/demis-hassabis-ai-simulation-agi Notes on Demis Hassabis's conversation with Lex Fridman about AI as a scientific instrument and the path to AGI. Thu, 10 Jul 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) aiagisimulationdeepmindmachine-learningtalk-notes https://www.brgr.one/blog/ai-agents-24-month-job-shakeup https://www.brgr.one/blog/ai-agents-24-month-job-shakeup Notes on a debate between Amjad Masad, Bret Weinstein and Daniel Priestley about how AI agents will reshape work in the next 24 months. Sat, 10 May 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) ai-agentsfuture-of-workbusiness-strategytalk-notes https://www.brgr.one/blog/building-evaluating-reliable-ai-agents https://www.brgr.one/blog/building-evaluating-reliable-ai-agents Notes on Sayash Kapoor's AI Engineer talk about why agent evaluations fail and how to measure reliability. Tue, 15 Apr 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) ai-agentsevaluationreliabilitytalk-notes https://www.brgr.one/blog/enterprise-ai-revolution-outcomes-over-algorithms https://www.brgr.one/blog/enterprise-ai-revolution-outcomes-over-algorithms Notes on a Y Combinator conversation with Aaron Levie about why enterprises buy workflow outcomes, not model access. Sat, 08 Feb 2025 00:00:00 GMT mail@brgr.one (Patrick Burger) ai-enterprise-transformationoutcome-driven-solutionsvertical-aiai-securitycloud-to-ai-transitionstartups-in-aiai-commoditizationtalk-notes