Long-form notes on software and AI engineering.
2026
How to Connect Your Agents to Slack
Learn how to connect your agents to Slack. We'll talk about the app manifest, credentials, monitoring, and the security details that keep a public platform safe.
pro builderstutorialslackHow to Recursively Improve Your Agents
Learn how to recursively auto-improve your agents using simulations mined from usage data.
pro builderstutorialauto-improvementBuild an agent platform without writing a single line of code
Today I'll show you how to build your own agent platform without writing a single line of code.
tutorialplatformcoding agentsFastAPI for Agents
The valley of death between an offline agent and a live service.
essayplatformRL Tutor: an agent for learning post-training
I want to learn how to fine-tune my own models. So I'm building an agent to help me with it.
post-traininglearningSelf-Driving Agent Infrastructure
Build, manage, and recursively improve your agents.
essayauto-improvementplatformOwn Your Agent Stack
The market is finally catching up to a simple fact, that every company needs to own their agent stack.
essayplatformImage search using text classification
I built a simple image search engine by distilling images into text labels using gemini 3.5 flash. No image embeddings, just a labeling agent and hybrid search.
tutorialsearchAgent Platform That Builds Itself
I'm sharing my foundational agent platform that builds itself.
tutorialplatformcoding agentsAuto-Improving Software
Coding agents have changed how we build software. Now they're changing how we improve it. In this post I share an agent platform that coding agents build, run, and improve on their own.
auto-improvementcoding agentsplatformAgentic Software Engineering
Building, running, and scaling agents as production services
essayengineeringContext Providers
A thin layer between agents and tools that fixes context pollution, scope collisions, and prompt bloat.
engineeringcontextHow to Build an Agent Platform
A unified agent platform you can run locally or on Railway for $20/mo. Runtime, evals, scheduler, interfaces, and a Claude Code loop that recursively improves your agents.
tutorialplatformrailwayDynamic Software
For fifty years, software has been static. Then 2024 happened. The control flow came alive and a new category of software was born.
essaySystems Engineering
The Key To Building Agentic Software That Works
essayengineeringScaling Agentic Software
What is the simplest architecture for running a multi-agent system at scale?
essaymulti-agentDash: The Data Agent Every Company Needs
A self-learning, multi-agent data system. Free, open-source, runs in your cloud, lives in Slack.
datamulti-agentslackThe Programming Language for Agentic Software
The agentic era requires new primitives, a new execution model, and new runtime contracts
essayengineeringBuild Your Own Multi-Agent System
Build a production-grade multi-agent system. Run locally using docker and deploy to production on Railway.
tutorialmulti-agentrailwayEvals Don't Give You a Working Product
Two years and billions in funding later, 80% of AI projects still fail. Are evals the solution or the problem?
essayevalsLearning Machines: Technical Design
How Learning Machines work under the hood.
engineeringmemorylearningLearning Machines: Why AI Memory Hasn't Been Solved (Yet)
Every AI memory system I've used is missing something.
essaymemorylearning
2025
Memory: How Agents Learn
How to build agents that are not only capable, but learn and improve over time.
essaymemorylearningGPU Poor Continuous Learning with Gemini 3
How to make agents better without fine-tuning or retraining. System-level learning that actually works.
tutoriallearningSelf Learning Research Agent That Tracks Consensus Over Time
Build a self-learning research agent that captures consensus, explains what changed, and improves over time.
tutoriallearningresearchSelf Improving Text2Sql Agent with Dynamic Context and Continuous Learning
Learn how to build a text-to-sql agent with dynamic context and poor man's continuous learning.
tutorialdatalearningAgent Security 101
Stop sending your agent transactions to telemetry services. Give your Agents a database and keep your data private.
essaysecurityWTF are Agents?
Understanding Agents by mapping out how they work.
essayfundamentalsAgent Engineering 101
A practical guide to Agent Engineering: the intersection of software, systems and security engineering.
essayengineeringAgentic Culture
An open-source experiment in collective memory and in-context cultural accumulation for multi-agent systems.
multi-agentmemoryBecoming AI-first
Lessons from 100s of conversations on AI products and how teams are adopting AI.
essayai adoptionIntroducing Agno
The multi-agent framework, runtime, and UI built for speed.
agno