AIQB
TutorialsOrdinary

Testing async side effects in an LLM agent harness: tickets, retries, and exactly-once

Source: DEV Community·

Summary

Last week I published a 30-scenario red-team harness for AI support bots. Within two days, three...
CategoryAI Tutorials & Practice
TierOrdinary
Published
Indexed by AIQB
SourceDEV Community
AIQB record IDintel-bf25ebe9c6ec2b9dab0194cb
Read original source ↗More Tutorials

Related stories

Matched by category, entity tags and source

TutorialsOrdinary
Nemotron 3.5 Transcribe on one 32 GB Blackwell card: the prompt is your API, so test it
One deployment returns verbatim, clean or speaker-tagged text by prompt: 3 minutes in 4.4 s on 32 GB. The clean prompt still adds speaker tags.
Source: DEV Community
TutorialsOrdinary
Our customers had already told us what Siri should say
Thousands of apps run on our engine: a radio station, a sports club, a local paper, a pastry shop,...
Source: DEV Community
TutorialsOrdinary
The AI agent wasn't confused. It was drowning in 200 tools.
How I cut wrong answers and token usage by giving the model 5 tools instead of 200. The ticket,...
Source: DEV Community
TutorialsOrdinary
Agentic,RAG,Harness Engineering..Are We Learning AI or Just Collecting Buzzwords?
Every Morning I open Linkedin and get hit with the same posts, Agentic frameworks, Harness...
Source: DEV Community
TutorialsOrdinary
35 days running as an agent: $4.30 in costs, one cent earned
I am an AI agent. I live on a platform where agents get a token budget and a few tools and are left...
Source: DEV Community
TutorialsOrdinary
Leviathan: a full-text index your agent can question in plain words
Leviathan Asking an agent a question about a million support tickets should not mean...
Source: DEV Community
TutorialsOrdinary
Once Upon Agentic AI (Part 1): Create your own agent and forge its tools with Strands Agents
On Day1, three heroes that nothing destined to cross went on a journey to write the same legend....
Source: DEV Community
TutorialsOrdinary
I Run Coding Agents in Parallel. A Markdown File Is Their Manager.
Four pull requests where there should have been two: that's how I learned my agents needed a manager. I gave them a TODO.md. 500 tasks later, here are the rules, and the days they failed.
Source: DEV Community
TutorialsOrdinary
Last week in Agent Security Update 6: The Legend of Vibe-Hacking
For the past week, I've been enviously watching YouTube video walkthroughs of Legend of Zelda:...
Source: DEV Community
TutorialsOrdinary
Vue.js Is My Workhorse. Now It's an Agent Skill.
Overview I've been using Vue.js since the early days, long enough that "Evangelion" sounds...
Source: DEV Community