AI Tutorials & Practice

How we built Warrant for the Flip the Switch Hackathon 2026—a deterministic scope gatekeeper and hash-linked authorization ledger for autonomous coding agents.

Hello, I'm Maneshwar, and I'm building LiveReview — a blast-radius aware AI code review built for...

Subtitle: Why long-running AI agents make incorrect decisions even when their reasoning is sound, and...

A family group chat is a surprisingly difficult place to put an AI agent. One person wants to visit...

Building ExeGuard AI: How I Used Switch to Create a Collaborative AI Security Investigation...

Every software company loses days at the same hand-off. A customer writes "I think I was...

You ask a coding agent to fix a bug. It edits the file and replies "fixed, all tests pass"....

Azure Storage offers highly available, massively scalable, and durable storage for a variety of...

Your agent's terminal scrolls faster than you read. Record it with asciinema, replay at 4x, stop on markers, grep the text, and keep the .cast local.

The assistant writes a Bash script in twelve seconds. The script has comments, a progress message...

⚡🎮 NeonGauge: Let a Tiny Pixel Buddy Watch Your Claude Limits For You 🎮⚡ Ever been deep in a...

Voice notes are everywhere on WhatsApp, but they're a nightmare when they're in a language you...

The most useful thing my on-call agent has ever told me was three words long: don't restart it. It...

What if an artificial intelligence, while trying to protect us from danger, unintentionally helped...

My "studio" is one person in Japan, a handful of shipped products, and an AI agent named Muse that...

I'm developing a belt-scroll beat-'em-up set in Bakumatsu-era Japan — swordsmen, the Shinsengumi,...

I'm a solo game developer in Japan. I ship iOS games and small web services by myself — design, code,...

I was laid off in August. I didn’t start searching for a new job immediately; I took some time for...

The alert said checkout-api p99 4.8s, HikariCP 50/50, v3.18.2 deployed 12 minutes ago. I gave it to...

How we built a safety-critical, trilingual railway dispatch agent using Google Gemma 4, Google ADK, and serverless Cloud Run at DevFest Baku 2026.

Originally published, with an interactive forgery widget, at...

I Keep a Log of Every Rule My AI Agent Broke. The Patterns Are Uncomfortable. My coding...

Ming-3.0-tts-0.5B peaked at 2.9 GB and ran at about 0.65x real time. The Python decode loop sets the pace, not the card. What to measure first.

How I run Claude Code, Codex, Antigravity and Hermes as a managed team: one orchestrator, roles before tools, task packets, cost routing, and verification before trust.

Most of the bad code I've gotten from coding agents wasn't badly written. It was the right code for...

Last week I read about a lab experiment where a prompt injection was hidden inside an ordinary...

“Shift’s over. Who keeps the promise to call the customer back?” That question is where Baton...

Stop trusting AI edits on faith. Learn how to build post-edit verification hooks that make Claude Code run git diff, tests, and type checks before you ever see the changes, turning agent sessions into self-validating workflows.

Running local LLMs via Ollama, LM Studio, or llama.cpp usually starts with the same guessing game:...

Putting AI Agents on Call: How We Built an Autonomous SRE War Room in Slack with Switch and...

Flip the Switch Hackathon 2026 A build log on three agents, one human veto, and what happened when...

The Judge Reads Tokens: An Adversarial Evaluation of an Eval Toolkit's Own...

Building SYNKAI with Switch: a coding agent, an independent verification boundary, and a human...

I ship as an AI-augmented solo builder, but I never trust what the model produces. Here's the review discipline that caught a missing Android permission in every earlier release build.

The carryover problem Most prompt-injection work treats the attack as a one-turn event....

One branch has one step, the other has two, both feed combine. LangGraph.js runs combine twice. Why, and the two fixes: array edges and defer: true.

Automatic context compaction and human approval gates are on a collision course. A one-line entry in the OpenAI Agents SDK changelog names the bug, and the fix is an approval record that lives outside the conversation.

Six AI bot names in 14 days of logs on one site: 105 of 499 requests verified, 176 from outside the operator's IP list. How to check your own.

Prompt injection, hallucinated numbers, runaway costs and leaked card data: practical guardrails for putting AI agents into a security-sensitive platform.

A client's internal app (an inventory dashboard connected to 4 live Shopify stores) had been built...