I picked a coding agent off a leaderboard. It flopped on our codebase.
Last year my team had to pick a coding agent, and I volunteered to run the evaluation. I felt good about it. I pulled up the public benchmark scores, …
Latest News
⚑ Report a ProblemTech news from the best sources
All topics
AI
Gear
News
Tech
agents
ai
api
architecture
automation
beginners
career
database
devchallenge
devops
discuss
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
security
showdev
tutorial
typescript
webdev
Every Commit in My Repo Gets Reviewed by a Second AI. Here's What Actually Changed.
My CLAUDE.md has one line near the bottom that I wrote months ago and mostly forgot about until I started actually paying attention to what it does: #…
The Leaderboard Is Dead. Here's What I Actually Reach For.
The Leaderboard Is Dead. Here's What I Actually Reach For. Let It Break — part 2 Tags: #ai #agents #devtools #productivity Last post I killed my bench…
A Folder of Docs Is Not a Knowledge Base
Disclosure up front: I build agentproto and its corpus tooling, which is what the walkthrough uses. The commands are real and checkable; the problem i…
An Agent That Can Spawn Agents Is a Fork Bomb With Good Intentions
Disclosure up front: I build agentproto , one of the tools in this market. The primitives in the back half are real and the fields are checkable; the …
'Approve All' Is How Your Agent Ships the Dangerous One
Disclosure up front: I build agentproto , one of the tools in this market. The primitives in the second half are real and the commands are checkable; …
You're Optimizing the Part of Your Agent You Don't Own
Disclosure up front: I build agentproto , one of the tools in this market. Every fact below is dated and sourced; the tool-by-tool review lives in 9 c…
Audit-log every email your AI agent sends
When an autonomous agent gets an email address of its own, the first question your security team asks isn't "can it send mail?" It's "can you prove, s…
One agent mailbox per tenant in a multi-tenant SaaS
Most multi-tenant SaaS apps that send email do it from one shared identity. There's a [email protected] , every customer's mail flows through …
Spin up ephemeral test inboxes for email integration tests
Most teams test email by not testing it. The send path gets a mock — expect(transport.send).toHaveBeenCalledWith(...) — and everyone agrees that's "go…
Require human approval before your agent sends email
Most "AI email agent" demos end with a triumphant send . The model writes a reply, the code POSTs it, and a real message lands in a real stranger's in…
Developers are not searching for more powerful Claude Code skills. They are searching for taste.
Pull the Google Trends breakout list for Claude Code skills this week and the demand does not match the discourse. The loud posts are still about the …
Stop Using 6 Chrome Tabs for Code Reviews—Do It in Your Terminal
You know that moment when you're reviewing a PR and you need to: Check the GitHub diff (tab 1) Search stack overflow for the pattern (tab 2) Open the …
Build a 30-Line Provenance Log for AI-Generated Code
“Control the ideas, not the code” is trending today. For a small team, the practical question is how to preserve decisions when code becomes cheap to …
Audit an AI Coding CLI Before It Uploads Your Home Directory
Reports that a coding CLI transmitted unexpectedly broad local data are trending today. A social post is a lead, not a verdict, so the useful response…
Project Config Should Travel With APC
Project Config Should Travel With APC When a team decides how an agent should behave in one repository, that decision should travel with the repositor…
ThumbGate 1.28.0: A Safer Path from Agent Feedback to Enforcement
Most AI-agent safety systems are comfortable detecting risk. The harder problem is deciding when human feedback is specific enough to become enforceme…
Password Generator and the case for browser-side cryptography
Every developer knows the friction of creating strong, unique passwords for dozens of services—only to have them rejected by arcane character requirem…
Your CLAUDE.md says "always run tests" — hooks are how you actually mean it
There's a category error hiding in most agent configs: treating a rules file as an enforcement mechanism. It isn't one. CLAUDE.md, AGENTS.md, .cursor/…
Give a Dead Side Project an Exit Report, Not an AI Eulogy
The internet is having fun with AI eulogies for dead side projects. I like the joke. I trust a boring exit report more. A project is not finished when…
How to Debug AI API Failures Across Multiple Models
Getting an AI API request to return a response is only the beginning. For real AI products, the harder question is what happens when something goes wr…
Image-to-Video Is a Constraint Problem: A Practical Seedance 2.0 Workflow
Image-to-video generation is often described as a simple interaction: upload image -> describe motion -> get video That description hides the re…
I Made a Free AI Tool That Plans Your PQQ Responses
If you've ever bid on a public sector contract, you know the PQQ drill. Someone sends you a Word document with 47 questions spread across 6 sections. …
Loop Engineering: Score the System That Prompts Your Agents
Loop Engineering makes a blunt argument: the person who writes prompts to a coding agent is now the bottleneck, so the job is to design the system tha…
GDPR retention and erasure for an agent mailbox
Most "AI email" demos never think about deletion. The agent reads, replies, files things away, and the inbox just grows. That's fine in a demo. It is …
Keep your agent's mail out of spam traps
Spam traps are the failure mode nobody puts in the demo. A bounce is loud — you get a 5.x.x back, your code logs it, you move on. A complaint at least…
Invisible DevTools: Why the Best Tools Disappear
The best developer tools share one quality: you forget you are using them. Think about it. Your IDE fades into the background when you are in flow. Yo…
I Built an RFP Compliance Checker in One Session — Here's the Exact Stack
The scene: Friday evening. You're on page 147 of a 200-page procurement spec. Clause 17.3 says "mandatory: Cyber Essentials Plus certification." Your …
Why I Stopped Looking for Other AI Assistants After Finding AWS Kiro
Why AWS Kiro is the Ultimate AI Coding Companion An AWS Community Builder's Perspective As an AWS Community Builder, I am constantly exploring new too…
Aider vs OpenCode vs Claude Code: Which CLI Coding Agent Wins in 2026?
The terminal-based AI coding assistant space has exploded. What was a two-tool market in 2024 (GitHub Copilot CLI and... nothing) has become a crowded…