Yesterday
- LLMs generate code incredibly fast, but to ensure they generate exactly what is intended, they need clear boundaries. Abstractions and Domain-Specific Languages (DSLs) provide a strong harness that guides LLMs right from the start. Unmesh Joshi describes how the example of...
This week
- Some more of my notes from Thoughtworks Future of Software Development Retreat. When we had our first retreat in Utah early this year, nobody had heard of Harness Engineering. This time we had a whole session on it. When comes to the guide side of harnesses, most of the...
- Look at the past history of this blog. There are many blog posts about programming with AI, a few of them date back to January 2024 (like this: https://antirez.com/news/140). I’m a relatively well regarded programmer, after all. I don’t have the need to still be in the “loop” as...
- July 12, 2026 On Saturday, beneath a sparkling blue sky, I joined the march to Stop the AI Race. We gathered in front of OpenAI’s office in Mission Bay, then marched through the city to Anthropic’s HQ beside the Transbay Transit Center. Stop the AI Race If this had been a...
- It’s our job to build the software factory - not just the software. Software engineers maintain the assembly line allowing anyone to prompt for a change and ship immediately. We set up the infrastructure that makes agents successful. We act proactively through prompts (skills,...
- OpenAI’s latest flagship model hit general availability this morning, and comes in three sizes: Luna, Terra, and Sol (from smallest to largest). The new models are priced per 1M input/output …
- Jul 10, 2026 Don't you mean extinct? In 1993, Jurassic Park came out and revolutionized the use of CGI in films[1]. To the public the experience was magic. But for some of the people in the movie industry, it was a rude awakening. Director Steven Spielberg had hired stop-motion...
- Your agents can now react to real-time events using a custom signal provider. Connect to any external source — GitHub, Slack, CI pipelines, or your own APIs and......
- You can now run your agents and workflows on schedules. Configure them using cron syntax and a default prompt for agents or inputData for workflows — letting yo......
- Power users generate 10x as many lines of code vs the median, most of the AI spend is coming from input tokens not output ones, and almost half of AI changes are accepted without manual review by devs (!!)...
- Birgitta Böckeler now reports on her recent experiences trying local models for coding. She compares them using two standard tasks, and tries out the most promising model for day-to-day use. more…...
Last week
- Birgitta Böckeler recently spent some time trying out running local LLMs for some programming tasks. In this memo she outlines the factors that influence how viable they are for the job. more…...
- July 6, 2026 I don’t generally feel compelled to enthuse about AI models, even when I like them, because there is so much enthusiasm out there already, and it feels like remarking, in 1977, “Wow, that movie Star Wars was really thrilling and technically impressive, wasn’t...
- You can now add skills directly to your Mastra agents. Download packaged ones or write your own. Use them with both code-registered or file-based agents. We fir......
- Last week, Thoughtworks ran a second Future of Software Development Retreat, this time in Europe. As with the previous event, I’ll be sharing some fragmentary thoughts on this. There were five parallel streams, so I could, at best, only attend ⅕ of sessions. This isn’t an event...
- In the before times, code was deterministic and self documenting. Why don't we show AI what we want by... just writing some of the code?...
- When a sector goes too fast, it loses support Without a doubt, the pace of the AI ecosystem is dizzying. Just processing it all is difficult enough. Scaffolding it, finding themes, and understanding the shape of it is nearly impossible. Recently, Mike Migurski introduced me to...
- Are there any ‘intelligent’ router solutions out there which select the right model for the right task? I looked into it, and there are a few options....
- You can now build file-based agents in Mastra. Each agent is defined by a folder with model config, instructions, tools, skills, memory, and workspace as separa......
- The European Union AI Act will begin to be enforceable in August 2026, one month from now1. One of the biggest new requirements is Article 50, which requires all AI outputs to be “detectable as artificially generated”. In other words, if LLM providers want to do business in the...
- The action in agentic engineering has moved from prompting to operating. Autonomy isn't one ladder, it's two axes (agency and orchestration) and six levels you move between per task. The real question is what level a task deserves, and what verification makes that level...
- Your Mastra agents can now record their browser sessions with browser recording. Each run writes a video file to disk letting you replay every step your agent t......
- You can now connect your agents to events from external systems using a WebhookSignalProvider. Each event arrives as a notification signal, injected into the ag......
Rows per page
