No-Code Agentist

Over the past year, we've been building our own internal agent infrastructure at YC: over 350 tools, self-improving skill loops, and a shared organizational brain that gets smarter overnight. In this episode of the @LightconePod, we sat down with YC General Partner Pete @koomen to talk about how he led the effort from the ground up. We cover how giving agents unrestricted access to one database was the key unlock, the self-improving skill loops that get smarter overnight, and why he thinks we've arrived at the personal computer moment for AI. 00:39 — YC's AI Stack 02:15 — The Finance Team Problem That Started It All 05:07 — SQL Access Changes Everything 07:20 — One Database to Rule Them All 09:14 — Jevons Paradox 10:07 — Denormalizing for Agents 12:15 — The Single-Player Era of Agents 14:16 — 350 Tools and a Shared Registry 16:24 — Skillify, DRY, and MECE Resolvers 18:23 — The Self-Improving Dream Cycle 20:26 — The Two-Sentence Pitch Skill 23:06 — How Super Intelligence Compounds 25:10 — Recording Everything as a Building Layer 27:10 — The Shared Organizational Brain 29:18 — Trust-Default Culture as a Requirement 30:44 — Raising the Floor for New Employees 32:35 — Horseless Carriages 34:24 — Why Chat Is the Best Interface for Agents 38:50 — Just-in-Time Software 40:49 — Centralizing vs. Decentralizing AI 43:32 — The Personal AI Revolution

[BIG UPGRADE] AutoGPT is no longer just an agent demo — it’s a full self-hosted agent platform The project that kicked off the autonomous agent wave has grown into something much more practical: a place to build, run, monitor, and deploy agents as real workflows. · Low-code https://t.co/hBy9JBwVTq

n8n remains one of the best tools for turning AI ideas into reliable automations. The visual workflow builder lets you connect LLMs, APIs, databases and custom scripts without drowning in code. Here is a practical pattern I have been running: 1. Trigger node listens for events (webhook, schedule, new email). 2. AI node does initial analysis or classification using a solid model. 3. Switch node routes based on confidence or type. 4. Hermes Agent node (or similar) handles the complex reasoning parts that need tool use and memory. 5. Final nodes update CRMs, generate reports or trigger follow up actions. Add error handling branches and logging at each step so you can debug without guesswork. The HTTP request nodes and code nodes give you escape hatches for anything custom. What makes it powerful in 2026 is pairing the no code speed of n8n with agentic tools that can adapt on the fly. You get both structure and intelligence. Start small with one recurring task, then expand. The community templates are a fast way to see real production examples.