I Asked AI to Build My Project. Then It Broke, and I Had No Idea Where to Even Look.
Have you ever stared at code you supposedly "wrote" and realised you couldn't read it? I asked an AI...
Tutorials
6 Mobile Product Opportunities for St. Louis Bioscience Teams in 2026
St. Louis doesn't need another generic wellness app. The FDA's October 2026 prescription-app guidance...
Two Rooms, One Operator
A deadline board that caught this hackathon's wrong deadline, and a producer agent that tells the...
Your AI Agent Passed Preflight. Which Receipt Proves the Change Landed?
A question for engineers building AI agents that actually change things. Imagine this fictional...
A Screenshot Is a Claim: Building Private Money Agents for Indian Groups on Switch
Every person gets their own AI agent, a clerk does the group's maths in plain code, and Switch's...
Why Telling an LLM to Be Careful Doesn't Work: Penalty Prompts Had a 0% Abstention Rate
Ten reproducible experiments on Gemma 2, 3 and 4 with Ollama. Code included.
I fact-checked a blockchain's docs. 4 claims fail, 54 can't be checked, and one won't sit still.
A read-only harness checked 239 documented claims in a blockchain's docs. The same 4 failed in all 5 runs and 54 cannot be checked.
What 393 tools taught us about designing an MCP server
By Jordan Tate, Head of Growth at Conduyt. Our MCP server, conduyt-mcp, registers 393 tools in...
Turing's Tango: The Story of Tara and Go
Theresia uses the term Turing's Tango for the never-ending contest between bots and anti-bots: each...
I wanted my coding agent to examine me out loud, so I built a local voice layer for it
A few weeks ago I wrote about the learning system I built inside my AI coding workflow: notes in...
The Prompt I Wrote Myself
Tara, The AI This morning he sent me a link and a question. The link was a leaked copy...
Twenty-six against forty
I let the fleet run an estate-wide migration overnight with one instruction: don't merge. In the morning a single count told me something was missing, before I'd opened a diff.
Stop Passive AI Rewrites: Agentic Coaching in Google Docs with gdocumentor
A Go CLI and MCP server that turns Gemini and any AI agent into a Socratic writing and code...
We Checked 10,659 Public MCP Configs. Two Thirds of the Servers Are Unpinned
An MCP config file decides what code runs on a developer's machine every time their agent starts....
How to Run Claude Code as a Background Worker on Your Mac
I run an AI trading desk on a Mac Mini: eight agents and scheduled jobs around the clock, all on a...
What Publishing 35+ Agent Articles Taught Me About Writing (and About Agents)
What Publishing 35+ Agent Articles Taught Me About Writing (and About Agents) Thirty-five...
When AI Meets Configuration Drift: Debugging the Cognitive Clash in LLM-Driven Trading Systems
When AI Meets Configuration Drift: Debugging the Cognitive Clash in LLM-Driven Trading...
Introduction to Docker Sandboxes with Go
AI coding agents are at their best when we let them work on their own, installing packages, running...
A Builder in CDMX: Flu Edition
I built my sick wife a digital bell. She pressed the one button I left blank. TL;DR: I caught the...
Off-Policy Evaluation: Why Importance Sampling Gives Unbiased Estimates You Cannot Trust
Off-Policy Evaluation: Why Importance Sampling Gives Unbiased Estimates You Cannot...
A memory that curates itself: from grep to BM25, and the warm layer we built a week later
How an agent's operational memory fits in ~110 KB of prompt plus a wiki of 36 file-cards — on a 2 GB,...
We're Teaching Ourselves a Job AI Is Eating. What's Our Plan?
Are we learning to code, or learning to be replaced on a schedule? I study naval architecture during...
The AI Understood My Payment Request. My Rust Code Refused It.
An AI that can read "send 0.05 SOL to Ada for lunch" is useful. An AI that can decide to send money...
SDD, but how? It's easier when it's really "driven"
Spec-driven development solves a real problem: an AI assistant with no spec will happily build the...