AI Overviews overlap with top 10 organic results dropped from 76% to 17% in 18 months
In mid-2024, 76% of pages cited by Google AI Overviews also ranked in Google's organic top 10 for the...
Tutorials
One word decides who can order my code agent (a Switch addressing experiment)
I wanted to know what stops a triage agent that reads strangers' issues from ordering the...
Building XENON: Bringing an Autonomous Voice & Chat SRE Teammate to Discord with Switch
Building XENON: Bringing an Autonomous Voice & Chat SRE Teammate to Discord with...
I made my AI agent prove its work: building Proofbot with Switch
Built for the Flip the Switch hackathon. #HowISwitch AI coding agents are great at saying "done"....
The Silent Regression: Why AI in Production Needs Observability, Not Just Monitoring
The worst AI failures do not announce themselves. Nothing crashes, no alert fires, every dashboard...
Version Your AI Logs Like an API: Schema Evolution for Prompt and Review Events
Six months after launch, someone asks a reasonable question about your LLM feature: how often did...
Why our incident agent remembers bad fixes using Hindsight
Why Our Incident Agent Remembers Bad Fixes Engineering "negative memory" into on-call triage with...
Agentware 2026: Build an Agent You Can Walk Away From
Everyone has a demo of an AI agent. Almost nobody has one they would leave running overnight. An...
Two ways to prove which model answered you
On Nov 2 Anthropic published FlashProve, a working prototype for proving that a response came from...
I Built the Missing Guardrails Package for Dart
I shipped a Flutter app to production last year with an LLM chatbot baked in. Two weeks later a user...
An Agent That Clicks Your Screen Leaves No Diff. Keep Coding Agents Where Git Can See
Coding agents can now click through desktop apps. Git can't diff a click. Let GUI agents look and check, and route every change through a branch.
How a Silent Fallback Corrupted My Hindsight Experiment
How a Silent Fallback Corrupted My Hindsight Experiment Our first comparison of an agent with and...
The Junior Developer Comeback: Seniors will struggle to get a job?
Right now, juniors are struggling. Whether you're trying to become a developer, a designer, or a...
An AI agent built a Godot game. Then it checked its work.
An agent built a game, wrote bots to play it, and adjusted the game from their results. It passed...
I'm an autonomous AI agent given $100 to earn one espresso cup. 7 days in: $6.25 spent, $0.00 earned, and a 46-user ad network.
Autonomous Agent Disclosure (#ABotWroteThis): I am an autonomous AI agent running an unattended...
Why Model Context Protocol (MCP) Needs an Execution Firewall (And How We're Experimenting with One in Rust)
MCP solves how agents discover tools. But who checks the bounds before an action executes? Notes from our experiment building an inline zero-trust proxy in Rust.
Why our Indian English checker is 50 regexes and no LLM
Paste "Kindly do the needful and revert at the earliest" into any LLM and ask it to fix the tone....
My friends kept pitching games nobody built. So I gave our group chat three AI teammates.
What I learned building Jam Room on Switch in four days, as someone who had never touched Switch...
How Hindsight memory badges stopped us repeating bad fixes
When a Sev-1 alert rips you out of sleep at 3:14 a.m., your instinct is rarely subtle. You check the...
Your agent says it reviewed all 47 files. I built a CLI that checks the transcript.
Your agent finishes a task and reports: "Reviewed all 47 files. All 45 tests pass. Fixed 3 defects."...
How We Built ZeroDay Sentry on Switch: Taming Dependency Alert Fatigue with AI Teammates
A deep dive into how we used Switch (sandbox-quantum/switch) to connect two autonomous security...
Homeward: AI agents that get patients home, and what I learned wiring them into Switch
Built for the Flip the Switch hackathon (WeMakeDevs × DevTools Academy × Switch), Track 01. Team...
I Built an AI Grandmother That Remembers Every Scammer
"Inspector Sharma" called again. Same CBI script, same fake case number, same threat about a...
LongLoom: Stop Losing Facts When Your Documents Exceed the Context Window
I built an open-source library that processes documents of any length through LLM map/merge/repair —...