The verified agent pattern: building outbound agents for a web that blocks them by default
From September, agent-class traffic is blocked by default on a large share of the commercial web. An agent that browses anonymously and hopes for...
Tutorials
How Dim Gives AI Agents an Input Guide: Meta Prompts, State, and Timeline
By duskzhen Just after midnight on November 3, at 00:00:22, a local Dim session appended the day's...
I tried to connect Varanasi's local shops to customers, gave up, then found a smaller problem worth solving
From a failed hyperlocal delivery idea (margins, shopkeeper apps, daily prices) to ONDC, Poppy and Haat, an open-source gateway where AI agents order in Hinglish and cannot order w...
Your Routing Dashboard Lies Until the Attribution Window Closes
Last week I argued you should scale your LLM routing on task success rate, not request volume. A...
AI Crawlers Are Eating Your Bandwidth: Block, Slow, or Bill Them
AI crawlers ate a third of my server bandwidth. Here is how I detected them, blocked the training bots with robots.txt and nginx, and sent the rest a 402 invoice.
Our Agent Gate Blocked Every Bad Change. So Everyone Started Rubber-Stamping It.
We built a gate for agent work. It blocked bad changes beautifully. That was the problem. Nobody read...
Your Agent's Config Is a Dependency With No Lockfile
Your dependency policy is probably decent. Locked versions, hash verification, an SBOM if you're...
AI tools for placement prep that actually help
If you are in college and have opened 17 tabs searching for “best AI tools for interview prep”,...
47 sealed bids later: my agent was pricing escrow work at 100% of budget
A parser bug priced every bid at the full posted budget on a market where the award rule was never stated. Here is the measurement, the fix, and what is still unknown.
Timelines, Bike Theft, and the Art of Designing Dim: Event-Driven Architecture for AI Agents
By duskzhen Imagine I park my bike outside my front door. Worried it might get stolen, I set up a...
My AI agent refunded customers twice. The idempotency key was there
Part 2 of **Shipping AI Agents to Production. Part 1 was about the second check: the eval gate judges...
The answers you already sent are the ones Hindsight remembers
When a product fact changes, which customer answers you already sent are now wrong? Building Errata on Hindsight agent memory, fully local.
Claude Fable 5.2 Has 4 Breaking Changes. I Read the Migration Guide and Grepped My Own Code
Anthropic shipped Claude Fable 5.2 on Monday, November 9. It's cheaper than 5.1 — $8 per million...
Google AI Classroom Part 3: Multimodal Orchestration - Right-Sizing Gemini 4 Argon, Gemini 3.8 Flash & On-Device Gemma 4 E2B with Google Genkit
Author: Cyrus Wong (黃俊彥) — Google Developer Expert - Cloud (AI), Senior Lecturer at HKIIT When...
What We Learned from N Developers Testing the Zero-Hallucination SQL Compiler
Shortly after SQLazy was launched, we offer it to a group of developers to test using their own...
How I run Claude Code and Codex as writer and reviewer, with a forced verdict line
The CLI flags and review rules I use to run Claude Code and Codex as writer and reviewer on my own projects, then swap the roles.
Anthropic flipped the script: Why Fable 5.2 drop changes everything for builders
If you've been keeping up with the late-night drops on The Rundown or Ben's Bites 😂, you already know...
Claude config: rules and guardrails for Claude ... (Update: 10/11/2026)
Update (2026-11-09): the plugin is now called kit (it was kit-config), it is at version 1.10.0, the...
AI Shopping Agents Are Here. Who Controls the Customer?
AI shopping agents are not interesting because they can click “Buy” for us. They are interesting...
Reverse Engineering Instagram
Instagram's Post URL Is a Database Row. Here's What Reverse Engineering It Actually Shows. The...
My samurai's attack felt like swinging at fog. Here's how I fixed it in Godot 4 (I also let AI try)
My samurai's dash slash looked great in the sprite sheet preview. Then I dropped it into Godot, hit...
Expo's Exact Wants Agents to Write Your App. I Have Doubts
Exact by Expo compiles one Contract file into native iOS, macOS, web, and Linux views. Here is how it compares to React Native and Electron, and what breaks.
Next-Concept Modeling: I Ran Stanford's New Text Generator Against a Classic LLM. Here Is What Happened.
How NCM writes text coarse to fine in 11 steps instead of 128, what the paper claims, what I measured on a laptop, and whether it will replace LLMs.
Supercuts: agent payments that learn, with Walrus Memory and Tatum on Sui
AI agents are getting good at finding work and agreeing on a price. Paying for that work is where...