Design Docs, Nightly Audits, and Vycari's Agent Development Loop
Agents and Engineers | Agentic AI, Software & Agentic EngineeringShow Notes
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 notes Transcript Chapters
(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 -------------------- Vycari Gemini CLI Claude Code Greptile GitHub Obsidian Antigravity SDK Roborev Hostinger Python Postgres XLA Theano JAX CUDA Gemini Flash Lite Claude Haiku GPT Luna Gemma GLM DeepSeek Supabase Neon Modal microservices continuous integration fine-tuning you ain't gonna need it ⠀ Guests ------- Allen Hutchison, Co-Founder & CTO, Vycari Website Vycari LinkedIn GitHub X ⠀ Follow the podcast ------------------- LinkedIn Threads Instagram TikTok ⠀ Follow Dan Gerlanc ------------------- X LinkedIn Threads Bluesky
More from Agents and Engineers | Agentic AI, Software & Agentic Engineering
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.
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 notes Transcript Chapters
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.
Eric Ma is a Senior Principal Data Scientist at Moderna, where he leads the Data Science and Artificial Intelligence (Research) team. Previously, he conducted biomedical data science research at the Novartis Institutes for Biomedical Research and earned his doctorate in Biological Engineering from MIT. Eric is also an open-source software developer known for leading pyjanitor and nxviz and contributing to NetworkX and PyMC.
Andrew Zigler is a GTM Engineer at LinearB and the host of Dev Interrupted, a twice-weekly podcast and newsletter about AI-native development and agentic orchestration. A classicist by training, he previously taught in Japan, built e-learning platforms, and worked in developer relations at Mattermost.