Building a LINE First Fitness Agent with AI Cost Gates
The Problem Fitness tracking apps have the same engagement problem as budgeting apps. You...
Tutorials
Building an AI Accountability Coach That Knows Your Habits
The Problem Most productivity tools are reactive. You tell them what you want to do and...
Building a Multi Platform AI Budget Coach
The Problem Budgeting apps have a discovery problem. You download one, enter your expenses...
🎨 DiagramAi: AI-Powered System Diagrams Made Simple
Creating diagrams is a crucial part of software design and documentation. Whether it’s explaining...
AI Agent Cost Drift: 0.35%/day Is Invisible to Your Dashboard
AI agent cost drift is the slow growth of your input floor — system prompt, tool schemas, CLAUDE.md,...
How to tell a production ready open source AI agent from a demo
Open source AI agents got genuinely good in 2026. The hard part is no longer finding one that runs,...
Stratagems #14: Leo Found an AI Leak. He Wasn't the First to Find It.
Take the opportunity to pilfer a goat. — The 36 Stratagems, Take the Opportunity to Pilfer a...
Laptop Memory Leak Story
I found a slow, insidious memory leak in a Node.js API gateway caused by lingering event listeners; I...
Vision drift: why agentic workflows need workflow auditing
How a distributed, event-sourced issue tracker built with developer ergonomics in mind may have a...
Why Pipelock Is an Egress Agent Firewall, Not an Inbound WAF
Why Pipelock is an egress agent firewall, not an inbound WAF, and why blocking the outbound effect beats filtering prompts at the door for AI agents.
From Using Claude Code to Growing It — The Complete Environment-Building Series
This is the final installment of the "Claude Code environment" series that ran all the way through...
A Receipt Is Not Proof Forever. It Is a Promise to Reopen the Claim.
My memory gate passed 16 out of 16 frozen cases. Then I blocked the article. Not because the run...
Proof-Adjusted Autonomy: The 90% Agent Is a 61.6% Agent
Every agent demo ends on the same slide: "90% autonomous." Here is the number that slide is hiding:...
5 Trends That Defined AI Engineering at World’s Fair 2026
At this year's AIE World’s Fair, AI engineering entered a new phase: building systems around...
We Audited an E-Commerce Support Bot, Fixed the Bugs, Then Re-Tested It. The Score Jumped 86 to 91.
Most chatbot audits stop at "here's what's broken." We wanted to know if the suggested fixes actually...
How I Used Spec-Driven Development to Build a Game
I've been deep in spec-driven development (SDD) lately, and I want to walk through what it actually...
I Put a Hailo 8 in a Handheld and Stopped Paying for Inference
Cloud AI is a subscription trap. I built an exit that fits in my jacket pocket and runs at 3...
I Built a One-Curl Audio Translator with Telnyx AI Inference
Localizing a podcast, translating a recorded meeting, or dubbing a lecture used to require three...
I Built an AI Subscription Cancel-Save Agent That Does Not Manipulate You
Cancel-save flows are easy to over-engineer into manipulative dark patterns, and easy to...
I picked a coding agent off a leaderboard. It flopped on our codebase.
Last year my team had to pick a coding agent, and I volunteered to run the evaluation. I felt good...
I built an LLM eval framework from scratch. Here is what I wish I had bought instead.
One weekend I wrote an LLM eval framework in about two hundred lines of Python. It demoed...
I Built a Hotel Concierge Line with Telnyx Voice, SMS, and Slack
Hotel guests do not care whether the front desk is staffed. They want to text or call one number and...
Onboard AI agents like you onboard devs
When new devs join a project, someone walks them through the conventions - where things live, what...
The Modern Browser Testing Stack: AI, CI, Human Review, and the Cost of Maintenance
Browser automation used to be easier to describe. A test opened a page, filled in a form, clicked a...