• From a $20 Contract to Browser Automation at Scale
    Nov 17 2026

    Suchintan Singh is a founder of Skyvern, which uses AI agents and computer vision to automate browser workflows. He previously built machine learning platforms at Faire and Gopuff.

    Dan and Suchintan discuss Skyvern's early customer pilots, open source launch, and efforts to make browser automation accessible to people who know the work but do not write code. Suchintan explains why the team keeps rewriting its agent as models change, how caching shaped its latest architecture, and where Rustwright fits into its browser infrastructure.

    They also examine AI code review, the limits of browser-agent benchmarks, and the opportunities and risks of putting agents in more people's hands. Suchintan shares concerns about cybersecurity and the representation of minority histories in AI, alongside his optimism about what agents can make possible.

    Full episode notes

    Transcript

    Chapters

    • (00:00) - Skyvern's origins and early pilots
    • (06:34) - The $20 insurance automation customer
    • (09:49) - LLMs, open source, and anti-bot tradeoffs
    • (13:06) - RuneScape bots and machine learning roots
    • (22:57) - Browser agents for non-programmers
    • (25:23) - Rewriting agents as models change
    • (27:28) - Page context, caching, and agent speed
    • (31:18) - Rustwright and browser infrastructure
    • (34:09) - Agent feedback and code review
    • (39:21) - WebBench and benchmark skepticism
    • (44:50) - Agents for the rest of the company
    • (49:45) - Training and deploying specialized models
    • (52:47) - Building in Toronto and working remotely
    • (57:31) - Minority histories, trust, and AI risks
    • (01:03:39) - Hope for agents and cybersecurity concerns

    ⠀

    Links from the show

    --------------------

    • Skyvern
    • Rustwright
    • WebBench
    • WebVoyager
    • Pi

    ⠀

    Guests

    -------

    Suchintan Singh, Co-Founder, Skyvern

    • LinkedIn
    • X

    ⠀

    Follow the podcast

    -------------------

    • LinkedIn
    • Threads
    • Instagram
    • TikTok

    ⠀

    Follow Dan Gerlanc

    -------------------

    • X
    • LinkedIn
    • Threads
    • Bluesky
    Show More Show Less
    1 hr and 9 mins
  • Delegation, Agent Router, and AI Traffic
    Nov 10 2026

    Erica Hughberg is a software engineering leader, speaker, and community advocate at Tetrate. She maintains Agent Router, formerly Envoy AI Gateway, working on documentation, the website, and community.

    Dan and Erica compare coding agents with engineering management, from delegating work and taking responsibility to planning and reviewing the result. They discuss missing system context, authentication mistakes, and how subject matter experts can use agents to build and learn, including a researcher's move from SPSS to R.

    Erica explains why she uses a scheduled Claude task for project triage and when a separately deployed agent might make sense. She also introduces Agent Router and its Envoy foundation, tracing the demands of inference and MCP traffic through provider failover, large payloads, long-running requests, and the hardware that moves and processes them.

    Full episode notes

    Transcript

    Chapters

    • (00:00) - Engineering management as preparation for agents
    • (06:38) - What agents miss about teams and systems
    • (14:16) - Planning more and testing uncertainty
    • (20:11) - Authentication mistakes and checking data work
    • (23:16) - Helping a researcher move from SPSS to R
    • (28:35) - A seven-year-old builds a game
    • (31:14) - Learning engineering with agents
    • (40:53) - Who needs to build and deploy an agent?
    • (51:09) - Choosing among open source projects
    • (53:51) - Agent Router and the engineers of arrows
    • (58:16) - Inference costs, failover, and proxy foundations
    • (01:04:23) - Large payloads and encryption hardware
    • (01:10:51) - Long requests, event loops, and proxy history
    • (01:18:54) - MCP multiplexing and session management
    • (01:23:46) - Payload limits and planning proxy capacity

    ⠀

    Links from the show

    --------------------

    • Agent Router
    • Envoy Proxy
    • OAuth
    • SPSS
    • R
    • Lovable
    • Cloud Run
    • Kubernetes
    • NGINX
    • C10K problem
    • NVIDIA BlueField DPUs
    • eBPF
    • MCP

    ⠀

    Guests

    -------

    Erica Hughberg, Maintainer of Agent Router and Manager at Tetrate

    • LinkedIn
    • GitHub

    ⠀

    Follow the podcast

    -------------------

    • LinkedIn
    • Threads
    • Instagram
    • TikTok

    ⠀

    Follow Dan Gerlanc

    -------------------

    • X
    • LinkedIn
    • Threads
    • Bluesky
    Show More Show Less
    1 hr and 30 mins
  • From Python Core to Personal Apps: Working with AI Agents
    Nov 3 2026

    Mariatta Wijaya is a multi-award-winning open source maintainer and contributor with over 20 years of software engineering experience. A Python core developer focused on workflow and documentation, she advises and administers Global PyLadies, co-founded PyCascades, and formerly chaired PyCon US, PyCascades, and PyLadiesCon.

    Dan and Mariatta discuss why unreviewed AI-generated contributions burden CPython maintainers, even as Mariatta uses AI to write code. She shares how she reviews plans and results, records decisions, and builds Claude skills to prevent agents from repeating mistakes.

    They also discuss her self-hosted personal apps, the limits she places on AI advice, and how she uses AI to help promote community events while keeping time for speaker mentorship. Mariatta explains why agent instructions should be useful to humans and why she packages recurring work as reusable scripts.

    Full episode notes

    Transcript

    Chapters

    • (00:00) - Introduction
    • (01:35) - AI contributions and CPython maintainers
    • (05:45) - Experience, review, and learning to code
    • (09:16) - Migrating off Heroku with AI
    • (12:17) - Documenting decisions and iterating on plans
    • (19:26) - Claude skills and repeated Django mistakes
    • (23:19) - Reviewing software as product owner and tester
    • (28:01) - Where Mariatta prefers human judgment
    • (34:24) - Personal apps and alternatives to subscriptions
    • (43:43) - AI for community organizing
    • (50:44) - Respecting project guidelines and reviewing output
    • (53:27) - Documentation for humans and agents
    • (55:36) - Git skills and reusable automation scripts
    • (59:46) - Speaker management and spreadsheet parsing

    ⠀

    Links from the show

    --------------------

    • CPython
    • Claude skills
    • Django
    • Heroku
    • Claude
    • Calendly
    • Doodle
    • Sessionize
    • architectural decision record

    ⠀

    Guests

    -------

    Mariatta Wijaya, Python Core Developer

    • Website
    • Mastodon
    • Bluesky
    • LinkedIn

    ⠀

    Follow the podcast

    -------------------

    • LinkedIn
    • Threads
    • Instagram
    • TikTok

    ⠀

    Follow Dan Gerlanc

    -------------------

    • X
    • LinkedIn
    • Threads
    • Bluesky
    Show More Show Less
    1 hr and 3 mins
  • The AI Sandwich, Agent Primitives, and Designing with AI
    Oct 27 2026
    Trevin Chow is has more than 25 years of experience in product and design, held product leadership roles at Axon, Sketchy, Nike, and Microsoft, and co-founded Chewsy. He is a core maintainer of Compound Engineering, a plugin for Claude Code, Codex, and other agent harnesses. Dan and Trevin discuss how AI changes the work of building software, especially design and product judgment. Trevin describes starting with a value proposition before generating designs, using visual references to guide exploration, and keeping humans involved in critique. His “AI sandwich” puts human attention on defining the work and polishing the result while agents handle implementation. Concrete examples include illo's character packs for consistent illustrations and Compound Engineering's reviews across model families. Trevin explains why newer models call for clearer goals and fewer prescribed steps, while extensive evaluations, changing model behavior, and outdated plugins make maintenance costly. The conversation also covers the supervised Hermes Agent setup Trevin built for his daughter, including boundaries around companionship and homework help. It closes with Jev-powered prototypes and Energon, his open source service for sharing documents and files across agents without losing control of the underlying context. Full episode notes Transcript Chapters (00:00) - Product optimism and the changing craft of software(09:53) - Design exploration with AI agents(14:24) - Start with the value proposition, then explore designs(21:21) - Agent primitives and the problem of sharing context(24:54) - Cross-model review and the AI sandwich(32:19) - illo and consistent character illustrations(40:08) - Writing skills for changing models(43:03) - Evaluations, model regressions, and maintenance costs(47:36) - Future skills and the plugin update problem(52:13) - A supervised Hermes Agent for a child(01:02:41) - Jev experiments in document analysis and book discovery(01:06:54) - Energon and context that travels between agents ⠀ Links from the show -------------------- Compound EngineeringilloEnergonHermes AgentImpeccableJevGrok botMuseClaude CodeCodexCursorCloudflare WorkersCleanShot XFigmaDaniel Lemiresimdjsondesign systemrisograph ⠀ Guests ------- Trevin Chow, Product Leader and Builder WebsiteLinkedInX ⠀ Follow the podcast ------------------- LinkedInThreadsInstagramTikTok ⠀ Follow Dan Gerlanc ------------------- XLinkedInThreadsBluesky
    Show More Show Less
    1 hr and 14 mins
  • Design Docs, Nightly Audits, and Vycari's Agent Development Loop
    Oct 20 2026
    Allen Hutchison is the co-founder and CTO of Vycari, building AI agents for everyday tasks with Chris Perry. He spent 21 years at Google, most recently as a Distinguished Engineer at Google DeepMind, helped found Gemini CLI, and built the Antigravity SDK. His earlier leadership work included Google's mapping products, Core ML, and the AI Developer organization. He writes Letters from Silicon Valley.Dan and Allen discuss why consumer agents need familiar interfaces. Vycari embeds agents in mini apps, including a calendar booking tool that works with meeting preferences and buffer time. Allen wants users to think about the assistant's usefulness rather than the technology behind it.Vycari's two founders have landed well over a thousand PRs in roughly a month. Planning documents guide implementation, nightly jobs keep those documents aligned with code, and review follow-ups become issues that agents can implement. Independent reviews and reflection on user trajectories help identify problems, while Allen retains the final merge decision.Their engineering choices favor quick feedback and manageable costs. Vycari is separating microservices into their own repositories and runs Python and Postgres on VPSs. Allen explains how inexpensive models, stronger models writing their procedures, and deterministic integrations support the goal of a $5 monthly subscription.Full episode notesTranscriptChapters(00:00) - Allen's path to Gemini CLI(06:46) - Open-source contributions and approval fatigue(11:08) - XLA and the infrastructure behind machine learning(13:52) - Vycari and agents inside familiar apps(21:02) - A calendar booking tool that knows your preferences(22:34) - Two founders, a thousand PRs, and startup economics(29:29) - Planning documents and the automated development loop(37:55) - Reflection agents and nightly codebase audits(39:57) - Product context and tiers of coding agents(42:24) - CI, test coverage, and smaller repositories(48:06) - Python, Postgres, and conventional infrastructure(51:53) - Refactoring at a scale that used to be impractical(54:18) - Unexpected agent behavior and database migrations(59:19) - Inexpensive models and a $5 subscription goal(01:06:02) - The invisible work in a reliable agent harness⠀Links from the show--------------------VycariGemini CLIClaude CodeGreptileGitHubObsidianAntigravity SDKRoborevHostingerPythonPostgresXLATheanoJAXCUDAGemini Flash LiteClaude HaikuGPT LunaGemmaGLMDeepSeekSupabaseNeonModalmicroservicescontinuous integrationfine-tuningyou ain't gonna need it⠀Guests-------Allen Hutchison, Co-Founder & CTO, VycariWebsiteVycariLinkedInGitHubX⠀Follow the podcast-------------------LinkedInThreadsInstagramTikTok⠀Follow Dan Gerlanc-------------------XLinkedInThreadsBluesky
    Show More Show Less
    1 hr and 8 mins
  • Why AI Can Generate a Song but Struggles with Music Theory
    Oct 13 2026

    Ben Morss is a Developer Advocate at Mistral. He previously spent 9.5 years at Google as a Product Manager for advanced APIs in Chrome and a Developer Advocate for the web. He earned a bachelor's degree in Computer Science and Music from Harvard University and a doctorate in Music Composition from the University of California at Davis. He continues to make music and write about music theory.

    Dan and Ben discuss how LLMs help people learn while still missing context and intent. Their discussion of information theory and training data leads into a debate about software craft when agents make code much cheaper to produce. Ben describes Chat Invaders, a cat-themed demo game, and a reunion sing-along app that broke with forty people present. He had not load-tested the app and did not determine what caused the failure.

    They explore why working output does not guarantee value for a business or an audience. Ben wants musical assistance that can develop ideas and handle arranging work, but finds music theory explanations unreliable. The conversation ends with the human experience behind fiction and songs, and open questions about whether models could be conscious.

    Full episode notes

    Transcript

    Chapters

    • (00:00) - Learning with LLMs and the limits of explanation
    • (05:24) - Model progress and conversational regressions
    • (09:02) - Keeping up with AI and understanding the mechanics
    • (11:10) - Information theory, entropy, and model compression
    • (19:19) - Computing, music, and understanding structure
    • (23:35) - Software craft versus speed of iteration
    • (30:55) - Vibe coding and educational sample code
    • (34:22) - The sing-along app that broke live
    • (37:38) - Software demand and the power of verification
    • (40:58) - Human judgment and useful business adoption
    • (48:47) - AI composition and the missing musical assistant
    • (52:38) - Music theory and gaps in training data
    • (59:31) - Fiction, music, and the human behind the work
    • (01:05:14) - Thinking, consciousness, and continuity

    ⠀

    Links from the show

    --------------------

    • Mistral
    • Genius
    • information theory
    • entropy
    • lossy compression
    • Claude Shannon
    • Magenta
    • Suno
    • Markov chains
    • WebSockets
    • music theory
    • augmented sixth chord
    • stems

    ⠀

    Guests

    -------

    Ben Morss, Developer Advocate, Mistral

    • Website
    • LinkedIn

    ⠀

    Follow the podcast

    -------------------

    • LinkedIn
    • Threads
    • Instagram
    • TikTok

    ⠀

    Follow Dan Gerlanc

    -------------------

    • X
    • LinkedIn
    • Threads
    • Bluesky
    Show More Show Less
    1 hr and 9 mins
  • Agents, Engineers, and Citizen Developers
    Oct 6 2026
    Cory O'Daniel is CEO and co-founder of Massdriver, an internal developer platform and platform orchestrator for governed self-service infrastructure using Terraform, OpenTofu, and Helm. He has spent more than 20 years building teams and startups and working with cloud infrastructure. He created Bonny, an Elixir-based Kubernetes operator framework, and is a co-founder of OpenTofu.Dan and Cory discuss what infrastructure agents need to act safely. Massdriver models environments and resource relationships so agents can query context directly, while separate agent identities and attribute-based permissions constrain their access. Cory describes a staging workflow that tests infrastructure changes through real deployments before he promotes a release to production.Cory explains how a tested, consistent codebase supports his team's Claude Code workflow, why enforceable tooling matters more than long instruction files, and why human review still matters. He argues that engineers should build quality controls and deployment paths for domain experts who can now create software themselves, with collaboration and operational ownership still needing attention.Full episode notesTranscriptChapters(00:00) - Self-service infrastructure and the arrival of agents(03:11) - An API built around infrastructure context(09:03) - Agent identity and attribute-based permissions(15:54) - A four-person team, agents, and technical debt(23:12) - Future engineering roles and enforceable quality(30:20) - Backlog zero and autonomy for citizen developers(34:29) - Claude Code workflows, examples, and memory(40:54) - Testing infrastructure changes before production(48:00) - Reusable presets and shared provisioners(55:06) - Terraform is easy; organizations are complex(57:09) - Citizen developers and the future of cloud platforms(01:00:53) - When production apps run on someone's laptop(01:03:23) - Domain expertise, autonomy, and engineering's value(01:10:30) - Collaboration beyond Git and code in OCI registries⠀Links from the show--------------------MassdriverMassdriver ArchitectThe Citizen DeveloperCory O'Daniel's personal websiteTerraformOpenTofuPostgresGraphQLKubernetesattribute-based access controltest-driven developmentdomain-driven designGhosttyCheckovWizSnykGitOpsOCIElixirGolang⠀Guests-------Cory O'Daniel, CEO & Co-Founder, MassdriverWebsiteLinkedIn⠀Follow the podcast-------------------LinkedInThreadsInstagramTikTok⠀Follow Dan Gerlanc-------------------XLinkedInThreadsBluesky
    Show More Show Less
    1 hr and 17 mins
  • Building a Software Factory with Gas City
    Sep 29 2026
    Stephanie Jarmak is an AI Engineer at Omni working on multi-agent orchestration and code intelligence. She is a research affiliate for NASA's Science Explorer (SciX) and a maintainer of Gas City, an open-source orchestration builder for multi-agent coding workflows. Dan and Stephanie discuss how she became a Gas City maintainer by learning from review agents, encoding contribution standards in skills, and building an issue-triage workflow. Automating those steps exposed new reliability problems, from failures across dependencies to excessive alerts and agents that overreact to hypothetical risks. Their conversation connects these experiments to Stephanie's move from planetary science into search and AI engineering. They examine the appeal of building with agents, the responsibility for maintaining what those agents produce, and the mixed emotions of seeing models solve once-difficult research tasks. Personal game projects and Omni's approach to shaping her role show how her curiosity carries across both work and home. Full episode notes Transcript Chapters (00:00) - Contributing to open source with coding agents(08:51) - Learning the review standards and becoming a maintainer(12:58) - Automating a Gas City workflow(21:02) - Astronomy, computers, and a different path into development(27:40) - Working styles and responsibility for agent output(34:46) - Production responsibility and AI skepticism(40:12) - Human judgment and agents solving science tasks(45:55) - Pre-mortems, silent failures, and too many alerts(48:34) - Slack as an agent dashboard and shareable Gas City packs(53:45) - Building games and creative projects with the kids(59:06) - From planetary science to search and Sourcegraph(01:09:48) - Omni and a role shaped around the person(01:15:03) - Decision models and making automation easier ⠀ Links from the show -------------------- Gas CityBeadsGas TownDoltSteve YeggeClaude CodeCodexThe Six Types of Working GeniusTerminal-Bench ScienceHarborSlackSunoForgeScryfall17LandsSciXSourcegraphAmpOmniinformation retrievalpre-mortemreinforcement learning from human feedbackJev ⠀ Guests ------- Stephanie Jarmak, AI Engineer, Omni WebsiteLinkedIn ⠀ Follow the podcast ------------------- LinkedInThreadsInstagramTikTok ⠀ Follow Dan Gerlanc ------------------- XLinkedInThreadsBluesky
    Show More Show Less
    1 hr and 19 mins