Step Functions agent tools via AgentCore Gateway
Step Functions agent tools: how AI agents call workflows via MCP through AgentCore Gateway – with a CDK stack, SigV4 test script and clear security rules.
Tutorials
Letting an AI agent query your production database? Do these 6 things first
"Just ask the database in plain English" is one of the most useful things an AI agent can do. A sales...
A Practical Taxonomy of Prompt Injection: 11 Techniques and What Stops Each One
A hands-on field guide to the main families of prompt-injection attacks, each with a short example and the specific defense that counters it.
Architecting Deterministic Safety Gates for Agentic Workflows
Architecting Deterministic Safety Gates for Agentic Workflows TLDR: The moment you let...
Claude Code hooks on Windows: when a Bash matcher sees nothing
A reader spotted a Windows gap in my earlier article about blocking destructive shell commands in...
Signal #125: Always-On Tracing, Gemini 4 Argon in Roboflow, and the Stdio Trap
This week's Signal is dominated by observability and vision pipelines. Vercel moved always-on tracing...
17 GitHub Repositories to Learn AI
GitHub is a great place to learn AI. You can find much more than just code. There are roadmaps,...
Your Agent Says It Made It Faster. Benchmark Both Branches Before You Land
Your coding agent says the code is faster. Put both commits in worktrees, time them with hyperfine and benchstat, and read the p-value before you land.
Set up spin-that-dice in 10 minutes, no Spotify app needed to start
A tested setup guide for spin-that-dice, the Spotify party dice: roll from the 305-track starter crate first, then add your own app or music server.
Building Kensho: a voice companion for mental wellbeing that actually understands Bangla
What I learned building a multilingual mental-health voice agent with LiveKit, Deepgram, Cartesia and Supabase — including why no speech-to-text provider could detect Bangla, and h...
How our Training Recipe led us to "Hallucination"
In Part 1, we laid down the foundational law of financial AI: Never allow a probabilistic language...
How I run many Claude Code and Codex agents at once with a Chief that assigns the work
Illustrated Chief workflow from the asklog film. I kept opening another coding-agent terminal and...
I Tested My Claude Code Plugin Across 1,260 Live Sessions. Four Sentences Nearly Matched It.
"All tests pass." If you use an AI coding agent, you've probably read that sentence several times...
The AI Productivity Paradox: More Starts, Fewer Finishes
AI made building cheap, so nothing forces developers to choose anymore. Three rules that stop fast output from becoming a longer to-do list.
Multi-agent consensus: how to verify the result
When three agents agree, what checks their answer? A real 404 routing bug, an independence calculation and an executable acceptance check.
Build without limits - SDLC Briefing, #4
Hi! I am Ricardo Sueiras, leading SDLC transformation at Indicium AI. That means I get to work with...
RL 9: Superhuman Achievement in Games (1992–1999)
For about 30 years, strong backgammon players opened certain rolls the same way. It was in the books....
Your Agent Used 6% of Its Context Window and Still Lost a Third of Its Tool Output
Your Agent Used 6% of Its Context Window and Still Lost a Third of Its Tool Output By Igor...
The Architectural Collapse: 'The AI Layoff Trap'
Why Senior Engineers Are the True Targets of 'The AI Layoff Trap' There is an ironic...
I recorded 87 Claude Code sessions to find out where the money goes
I wanted to know why AI coding agents get expensive on real codebases, so I stopped guessing and...
Claude Code Sends a Background Agent's Whole Transcript Every 30s for a 3-5 Word Status
agent_summary asks the agent's own model to label its last action in 3-5 words. How the timer works, how to measure its share, and why the numbers disagree.
AI Agent Tool Calls Are Distributed Transactions: Who Owns the Retry?
An agent with write tools is coordinating distributed transactions over an unreliable network, and...
I Built a Self-Hosted ChatGPT on My Laptop. Here's What Broke.
From DevOps to AI Platform Engineering — Part 1 I'm a DevOps engineer. I've spent years running...
Stop Flattening Your PDFs: Document Intelligence and Structural Chunking for RAG and Agents
Many RAG failures that look like model problems are ingestion problems. If a parser flattens a PDF...