Weyland Joyner
  • Writing
  • Bookshelf
  • Links
  • Language Learning
Categories
All (14)
agents (8)
ai (4)
books (1)
consulting (1)
data (1)
distributed-systems (1)
history (1)
meta (1)
software (12)
writing (1)

[Building Agents, 3] I Guess Handoff is the Most Important Feature

agents
software
ai
The point of an agent is that it should have a tight, simple core loop for tool calling and returning a response to the user. At this level the tool call, or sequence of tool calls, is the unit of work. Once you get above this level of abstraction, you’re looking at the thread itself as the unit of work, and here’s where you get into some design decisions within the agent harness. What should we do to keep our threads short and focused?
Feb 10, 2026
Weyland Joyner

[Building Agents, 2] Treat Agent Threads like Unix Tools

agents
software
ai
In other words have them do one thing, well, and succinctly.
Feb 10, 2026
Weyland Joyner

[Building Agents, 1] Getting Started

agents
software
ai
I ended up porting Thorsten Ball’s post on building a basic coding agent to Typescript1. At first I was using Ink for a React component-based terminal UI, but that got restrictive. Fortunately I found Mario Zechner’s Pi agent project.
Feb 10, 2026
Weyland Joyner

Unleashing the Agents on Github

software
agents
“I wish I could see the prompts that led to changes”
Feb 8, 2026
Weyland Joyner

Kernighan & Pike & Unix & Agents

software
agents
“Every Unix Command Becomes a Startup”
Feb 8, 2026
Weyland Joyner

More on Context - Steve Yegge’s Beads

software
agents
Steve Yegge has a great post about Beads, his agent-first issue tracker. He goes into reasons a plain markdown tracking system doesn’t work at scale, and his findings shed some light on how agents approach their work with limited context.
Feb 7, 2026
Weyland Joyner

Digital Twin Universe(s)

software
agents
StrongDM introduces the idea of a Digital Twin Universe to validate end-to-end “scenarios” for software built (they prefer the term “grown”) in “dark factories”1 by agents.
Feb 7, 2026
Weyland Joyner

Thoughts on Context Engineering

software
agents
“Think about context windows as a Commodore 64 with a small amount of memory”
Feb 7, 2026
Weyland Joyner

Ralph Wiggum, Gas Town, etc

software
ai
Steve Yegge identifies 8 stages of AI-assisted coding adoption.
Feb 5, 2026
Weyland Joyner

Kleppmann on Local-First

software
distributed-systems
This is Martin Kleppmann, author of Designing Data Intensive Applications, talking about Local-First Software.
Feb 4, 2026
Weyland Joyner

Carl Bosch’s Nobel Prize Speech

books
history
How did you go about productizing a chemistry experiment in the early 20th century?
Feb 4, 2026
Weyland Joyner

a16z on Forward-Deployed Engineers

software
consulting
There’s been a good deal of buzz about FDEs lately. That’s a job that I’ve been doing under some alias since the mid-2010s.
Feb 3, 2026
Weyland Joyner

[DuckDB] The Lost Decade?

software
data
This fascinating post confirms some hunches I started to have in the late 2010s when everybody was overengineering their ETL pipelines.
Feb 2, 2026
Weyland Joyner

On Writing

writing
meta

Why I’m starting this blog

Jan 20, 2026
Weyland Joyner
No matching items
 

© 2026 Weyland Joyner