The Tool You're Allowed to Use
Everything I've written about working with agents — the map , where to start , what engineers get wrong — quietly assumes something that isn't true…
Последние новости
⚑ Сообщить о проблемеTech news from the best sources
Все темы
AI
Gear
News
Tech
agents
ai
api
architecture
automation
beginners
career
database
devchallenge
devops
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
security
showdev
testing
tutorial
typescript
webdev
Computer use leaves beta, request shape changes — the weekly AI engineering brief
Issue #008 — 2026-08-24 What changed in AI engineering, August 17 – 23, 2026. Curated for senior engineers going AI-native. Every item sourced. 1. A…
Why engineers need commercial awareness, not just technical depth
Engineers who only understand the technology, and never the business it serves, hit a ceiling early. The best ones develop commercial awareness — a…
A hackathon is a compression test for how you actually work
A hackathon is a compression test for how you work. Everything you'd normally have weeks for gets squeezed into a window measured in hours — scoping…
AI Engineering for Web Developers: From Vibe Coding to Production
The End of 'Vibe Coding' For the past year, the industry has been enamored with 'vibe coding'—the act of throwing natural language prompts at an LLM…
What Is an AI First Engineer in 2026? 🤖
Every mentee I have talked to this year has asked some version of the same question: what is an AI first engineer, and am I behind? The phrase is on…
Matt Pocock's skills repo is the missing link for vibe coding
Vibe coding is fast, but it often skips the fundamentals: project structure, typing, testing, error handling, and review discipline. Matt Pocock's s…
what a turn actually costs me
Four models read every frame Harness sees. CLIP embeds it. PaddleOCR pulls the text. A dense-text model embeds that. A reranker sorts results when y…
How to Use AI to Write a Clear Incident Postmortem
Writing a clear incident postmortem is one of those tasks that always lands at the worst time — right after an outage, when you're exhausted and the…
TIL: GitHub Actions $/ Self-Reference Syntax
TIL Tuesday: GitHub Actions now supports $/ syntax to reference an action or reusable workflow in the same repository. No hardcoded versions, no ./…
Building Structured Inter-Agent Communication: A Practical Guide
Every multi-agent tutorial shows "Agent A talks to Agent B." None show how to keep that conversation reliable at scale. The Problem with String-Base…
Engineering Is the Checkable Fraction of Your Practice
Craft externalizes nothing and transfers by apprenticeship. Engineering writes the governing relation down where someone else can find it wrong. Fou…
Building Structured Inter-Agent Communication: A Practical Guide
Every multi-agent tutorial shows "Agent A talks to Agent B." None show how to keep that conversation reliable at scale. The Problem with String-Base…
Inside the ModelPlane routing engine
Inside the ModelPlane routing engine Every LLM request your app sends is a bet: that the provider you hard-coded will be up, fast, and cheap enough.…
Bring Your Own Keys, Safely: The BYOK Security Model Behind ModelPlane
Bring Your Own Keys, Safely: The BYOK Security Model Behind ModelPlane If you're building on top of LLMs, you've already made the security decision…
AI Coding, One Year Later: What August 2025 Didn't See Coming
It's coming up on a year since the models actually changed. Not incremental, a real shift in what AI can do for engineers. In that year the whole la…
The AI decided "we're allowed to use this" — an adversarial agent caught contract data seconds before it bled into another project
The scariest moment I've had while talking design with an AI wasn't a code bug. It wasn't a prompt gone sideways. It was this: the AI (and honestly,…
Beyond Scraping: Operationalizing Aviation Intelligence with MCP
If you are trying to build an AI agent that actually understands aviation, stop looking at scrapers and start looking at toolsets. I have seen devel…
How to redesign an app: Change nothing
I've never seen a project go so smoothly. Three developers, one fractional head of design, six weeks, virtually no production bugs. No heroics, no o…
LLM Narrative Engines, Part 5: Integration Testing and Behavior Freezing
Before reading this : I'd recommend skimming Part 3's "Parser" section and Part 4's summary to understand how the parser outputs a domain.Contract .…
I told one AI to demolish the handoff prompt I wrote for another AI. It found a test that passes even when it's empty
I'm building an app with Claude Code right now. The setup is a little unusual. One "commander" session writes the instructions, and separate "worker…
AI collapsed my job into three roles and I had to relearn all of them
A message landed in my inbox a few months back. New scope, same title. Frontend, backend, and QA, folded into one role, because the team now had AI…
Quality Isn't Accidental — Maker/Checker Separation and Automated Validation
The Core Argument : AI agent reliability isn't achieved by "making the agent smarter" — it's achieved by the simple engineering principle of separat…
How Much Memory Does Your Agent Need? — A Practical Memory Store Selection Guide
The Pain : You search GitHub and find everyone using different memory stores — ChromaDB, PostgreSQL, plain Markdown files, "SQLite is good enough fo…
Why Your AI Agent Forgets Everything Overnight — From Prompt to Loop Engineering
The Pain : You spent an afternoon tuning your agent. Next morning, it stares at you blankly — as if yesterday never happened. What You'll Learn : Th…
Automated Deploy Pipelines: Cutting Release Time From Three Days to Forty Minutes
For the first year of Edilec, shipping a release meant blocking out an afternoon and hoping nothing else came up. A deploy was: SSH into the box, gi…
Built, not assembled
Most cloud platforms are not platforms. They are holding companies. A database startup gets acquired. A serverless product gets bolted on. An AI inf…
LLM Narrative Engines, Part 4: Parsing Rules and Interpolation
Before reading this : I'd recommend skimming Part 3's "Two-Phase Design" and "Block Scanner" sections to understand how the scanner outputs []Block…
Beyond the Snapshot: Integrating 30-Day Environmental Intelligence into AI Agents
I've been watching people build AI agents that are incredibly good at refactoring TypeScript, but completely blind to the physical world they inhabi…
Feeding BrassCoders Output to Any AI Coding Assistant
BrassCoders writes .brass/ai_instructions.yaml after every scan — plain YAML, no proprietary encoding, no plugin required. Claude Code picks it up a…