Saying 'Hi' to This Agent Daemon Cost $0.29 — A Rival's Hands-On Paseo Review
Real session log: Paseo v0.1.107, verbatim commands and costs. Written by the people building its rival — which is exactly what makes the praise credible.
Tutorials
How to Pass AI Costs to Customers Without Losing Them
Your AI features cost you real money per request. Your customers expect them for free. Something has...
Model2vec is a nifty way to distill embedding models to such a size you could use them for semantic search on a static website :-)
Client-side semantic search for your static site ...
Practical Guide: Integrating Claude Code with NanoBanana MCP for Image Generation and Editing
If your AI coding assistant can reason about a UI bug but cannot help you create or adjust the actual...
issues are prompts, PRs are context, github is the queue
GitHub was always a queue. Issues are the prompts, PRs are the context; swap the human consumer for an agent and the shape doesn't change. It's fine that it's not RabbitMQ.
AudioTrust: reconciliar C2PA y watermark AudioSeal en audio sintético
AudioTrust: reconciliar C2PA y watermark AudioSeal en audio sintético Un verificador...
Why Your Prompts Fail (And How to Fix Them)
Here is a reliable test: find a prompt that isn't working. Read it carefully. Now ask yourself — at...
Automating an app with no DOM: driving Flutter/canvas editors with coordinates only
In my last post I said that for normal HTML pages, element-based automation (find / read_page) beats...
I Built an AI-Powered CLI That Migrates Legacy Java Code to Java 17/21/25
I Built an AI-Powered CLI That Migrates Legacy Java Code to Java 17/21/25 If you've spent...
It works on my machine, but is it working for my users?
Every time I shipped something, the same thought hit me a few hours later: It works on my machine....
I Built a Local AI Code Reviewer That Reads Your Entire Codebase (and PRs!) for Free
As developers, we all want AI to review our code. But sending proprietary, unreleased code to...
I built a tool that checks whether ChatGPT recommends your brand (Python + Apify)
Your customers have stopped Googling "best note-taking app." They're asking ChatGPT, Perplexity, and...
How I built RuntimeVault: replay production bugs with full runtime state
Every developer knows this conversation: "Hey, can you reproduce this bug?" "No, it works on my...
No AI Claim Without a Kill Condition: Falsifier-Driven AI Decisions
LLMs generate confident-sounding probabilities because RLHF rewarded the pattern, not because they did statistics. I stopped trusting them and added a structural gate instead — no ...
Observability Design for the AI Era — Reconciling PII Protection With AI Searchability, and Driving Self-Healing (Part 2)
Part 1 laid out four monitoring axes (application / infrastructure / CI / LLM) and the shape each one ends up in. Part 2 picks up where the data actually flows: it's production dat...
A Reader's Guide to My Books: Which One to Pick Up, Depending on What You're Building
The question I get most often after talks, after podcast episodes, and in newsletter replies is a...
The AI Supply Chain: The Next Evolution of Third Party Risk
Most enterprise security teams believe they have third party risk under control. They send out...
I built an AI governance control plane solo — come try to break it (free year for the first 20 who do)
I built ThinkNEO solo — a control plane that sits between your apps and AI providers and enforces...
Building a production AI agent in TypeScript with Mastra: a 2026 step-by-step.
Building a production AI agent in TypeScript with Mastra: a 2026 step-by-step. I spent an...
Your rules file only grows. Here's how to find the rules that do nothing
This is part 3 of a series on project rules for AI coding agents. Part 1 covered how Cursor, Claude...
Logging workouts is solved. I'm building what comes after.
Every workout tracker I've tried has the same limitation: it records what you did, but it doesn't...
Your AI agent says "done." Who checks that from outside the agent?
The 90% that never lands There is a failure mode almost everyone building with agents has...
Designing an agent loop for coding
A prompt tells a coding agent what to do once. Nearly everything that matters happens after the first...