AIQB
TutorialsOrdinary

Our comment section redesigned our agent permissions. Here's what we still can't solve

Source: DEV Community·

Summary

In September I wrote about AI agents in our framework, Kumiko, and why a handler without a...
CategoryAI Tutorials & Practice
TierOrdinary
Published
Indexed by AIQB
SourceDEV Community
AIQB record IDintel-8e0349b4c35ce562e1579cfb
Read original source ↗More Tutorials

Related stories

Matched by category, entity tags and source

TutorialsOrdinary
Your Agent Should Not Run as You: What Windows Now Offers for Containing AI Agents
If you run a coding agent on Windows today, its shell commands usually run with your full user...
Source: DEV Community
TutorialsOrdinary
Treat Your LLM Agent Like a New Bank Teller
I have spent most of my career building financial systems: a multi-tenant SACCO platform, an...
Source: DEV Community
TutorialsOrdinary
Why Does RAG Hallucinate When the Right Documents Exist?
You check the logs. The right document was retrieved. It's sitting in the prompt, rank 2 of 5. And...
Source: DEV Community
TutorialsOrdinary
Green proofs, empty promises: when AI agents write their own specifications
I asked AI coding agents to write formally verified code. Every solution passed the verifier. Then I...
Source: DEV Community
TutorialsOrdinary
How Claude Code and Codex tell you your limits (and why counting tokens doesn't work)
I use Claude Code and Codex every day. Both can tell you where you stand on your limits: /usage in...
Source: DEV Community · Claude
TutorialsOrdinary
The Hardest Part of a Local Agent Is Deciding When to Stop
Every agent demo I have seen ends the same way: a task, a burst of activity, a confident summary....
Source: DEV Community
TutorialsOrdinary
A Script and a Task Are Not the Same Thing
The word "task" gets used for two very different objects, and the confusion costs people weeks. A...
Source: DEV Community
TutorialsOrdinary
Dark Factory vs. Light Factory: Where Should AI Agents Run Unwatched?
"Code must not be written by humans." "Code must not be reviewed by humans." Those are the two...
Source: DEV Community
TutorialsOrdinary
Experiments in Software Factories #1: Production app in 40 minutes
pastmonday.com is a real SaaS: auth, billing, uploads, and AI chat. A software factory of four Claude Code skills built it in about 40 minutes, and every backend service on the bill is Neon, including the brand new Object Storage and AI Ga…
Source: DEV Community · Claude
TutorialsOrdinary
My CI Was Red for 255 Commits and Nobody Looked
A CI job failed on every single push to my release branch. Including its very first run. For 255...
Source: DEV Community