Subscribe
Sign in
Home
Chat
Roadmaps
LLM Engineer's Handbook
Agent Engineering Course
Contact Me
Archive
Perks
About
Latest
Top
Discussions
Building a Support Chatbot on Amazon Bedrock
One search or an AI agent that can search again? I tested both.
Oct 31
•
Marcelo Acosta Cavalero
6
4 Key Decisions to Solidify Your Harness
How to tell a harness bug from a model bug.
Oct 27
•
Tejas Kumar
12
3
Build an LLM Wiki From First Principles
One token-efficient memory for your repos, company docs, articles, and videos.
Oct 20
•
Paul Iusztin
33
7
Context Inspector: Measuring Context Quality Before the LLM Call
6 signals that catch missing, stale, or conflicting evidence in your RAG pipeline
Oct 17
12
5
5
The Future of AI Coding: Multi-Agent
Using orchestration to get the best results
Oct 13
•
Johannes Millan
21
6
3
Learning Harness Engineering by Building a Coding Agent From Scratch
A complete guide to harness engineering, starting from first principles.
Oct 10
•
Paul Iusztin
31
2
4
1:41:13
The Agentic Software Factory Hierarchy of Needs
How to build software with agents that keep working while you’re away
Oct 9
•
Hugo Bowne-Anderson
and
Eleanor Berger
15
7
2
Stop Guessing. Evaluate Your RAG App.
From vibe checks to a 61-case score you ship on, in 5 steps
Oct 6
•
Paul Iusztin
and
Alexey Grigorev
21
9
6
September 2026
Will Your Next Change Break Your Agent?
Replay your agent's real failures after every prompt, tool, or model change
Sep 29
•
Paul Iusztin
17
7
6
Agent Evals 101: Stop Guessing, Start Measuring
How to benchmark and regression-test any agent harness
Sep 22
•
Paul Iusztin
28
8
3
Inside a Software Factory
Go from vibe coding to generating clean, maintainable code
Published on O'Reilly Radar
•
Sep 19
Stop Babysitting Your Coding Agents
Run the harness remotely on Modal, triggered by your CLI, a webhook, or a nightly cron.
Sep 10
•
Paul Iusztin
25
9
5
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
