AIQB
TutorialsSelected

Five bugs in my LLM app that never threw an error

Source: DEV Community·

Summary

I spent two and a half weeks building an agent that reads a project's code review history and...
CategoryAI Tutorials & Practice
TierSelected
Published
Indexed by AIQB
SourceDEV Community
AIQB record IDintel-e156dcafaf827e7092bf4701
Read original source ↗More Tutorials

Related stories

Matched by category, entity tags and source

TutorialsSelected
Building a Closed-Domain Agentic AI Knowledge Assistant with Hybrid RAG
I recently built an "Agentic AI Knowledge Assistant" that combines "Retrieval-Augmented Generation...
Source: DEV Community
TutorialsSelected
Building an Agentic RAG AI Agent with FAISS, BM25 and Qwen
I recently completed a project as part of my AI Engineering learning journey: an Agentic RAG AI Agent...
Source: DEV Community · Qwen
TutorialsSelected
Your MCP Server Says It Is Read-Only. Who Checked?
MCP servers describe their own tools. A tool can publish readOnlyHint: true, and an agent harness may...
Source: DEV Community
TutorialsSelected
Bugs Are Innocent Until Reproduced: Building Verdict, an Evidence-First Agent Harness
Most flaky bug reports end in one of two places: "cannot reproduce" or a patch nobody can prove fixed...
Source: DEV Community
TutorialsSelected
An agent trajectory dataset needs more than final answers
An agent trajectory dataset should preserve the behavior that produced an outcome, including the...
Source: DEV Community
TutorialsSelected
Memory Allocation
Why should you care? Every program needs memory. When you create: int age = 20; ...
Source: DEV Community
TutorialsSelected
The undo has to exist before the write does
An agent that changes something runs in the order decide, act, report. Verification, where there is...
Source: DEV Community
TutorialsSelected
I built an AI agent for production incidents. The interesting part is when it refuses to act.
I wrote this for the All Things Agentic Hackathon. Every incident-response demo you have seen ends...
Source: DEV Community
TutorialsSelected
Why the AI character would not calm down, and how I fixed it
An early version of Say It Ahead had a basic problem. A user could listen carefully, ask good...
Source: DEV Community
TutorialsSelected
OpenAI Is Cutting Off Cursor: The AI Coding Lock-In Lesson Every Developer Needs
Last Friday, thousands of developers opened their AI code editor and found out that one of the models...
Source: DEV Community · OpenAI / Cursor