AI and agents
A curated reading order. Explore all topics
The future of AI-native work
May 28, 2026
I had a chance to reflect at the past half year we've been building the team and culture at Sycamore after a friend asked me what AI-native development actually feels like these days. I think my answer would have sounded absurd to me even a year ago: I spend a lot less time writing code, I spend a lot less time reviewing code line-by-line, and I feel more responsible for the software.
Running Claude Code in a loop
November 15, 2025
This all started because I was contractually obligated to write unit tests for a codebase with hundreds of thousands of lines of code and go from 0% to 80%+ coverage in the next few weeks - seems like something Claude should do. So I built Continuous Claude, a CLI tool to run Claude Code in a loop that maintains a persistent context across multiple iterations.
AgentScript
February 9, 2026
A few weeks ago, I was staring at a system prompt that was 127,000 tokens long. One hundred and twenty-seven thousand tokens - just the system prompt. Most of it was, you guessed it, tool schemas: JSON definitions for every possible thing the agent could do, most of which it would never touch in any given run. My solution? I propose AgentScript: a code-first execution language where the LLM can only interact with the outside world by writing programs.
Who is the author of an AI-generated news article?
June 28, 2020
If you read major American newspapers such as Forbes or the Los Angeles Times, chances are you've already read a story entirely written by an AI-powered software system. This process is known as automated journalism, and highlights an important question about authorship: Who is the author of an article written by a virtual agent?. A 2005 study found that research participants attribute story credit to the programmers who developed the AI or the news organization publishing the story.
Machine Learning in 6 Lines
September 9, 2016
At Oswald Foundation, we’re currently building a user interface for the blind, a smartphone UI that works entirely on vibrational and speech feedback. While reengineering the Phone app, the app you use to make calls, we decided to incorporate some machine learning. If you call your Doctor in the morning every day and your parents in the evening on weekends, the app should be able to analyse that pattern and pre-populate the list of contacts relevant to the current time and location.