Subscribe
Sign in
Home
Notes
Chat
LLM Engineer's Handbook
Agent Engineering Course
Roadmaps
Perks
Contact Me
Archive
About
Latest
Top
Discussions
Agent Memory From Scratch
Ingest, query, and serve a unified memory from a single database.
Jul 14
•
Paul Iusztin
40
13
7
Your Second Brain Is a Graveyard. Make It Agent Memory.
Turn dead notes into a living LLM wiki your AI agents can query, maintain, and grow
Jul 7
•
Paul Iusztin
and
Louis-François Bouchard
33
12
5
June 2026
From Harness Lock-In to Portable Context Layer
Build a unified memory (knowledge graph or an LLM wiki) and serve it over MCP servers or skills, so any agent, open or closed, plugs in within minutes.
Jun 30
•
Paul Iusztin
44
16
4
How Evaluation-Driven Development (EDD) Works
Turn every AI agent change into a measured experiment you compare before and after to detect regressions and measure performance.
Jun 23
•
Paul Iusztin
and
Alejandro Aboy
36
5
Build, Configure, or Use As-Is: The Agentic Harness
A component-by-component teardown of an agentic harness, from tools and skills to memory, sandbox, and permissions.
Jun 9
•
Paul Iusztin
56
4
6
How to Keep Your AI Agent's Knowledge Graph Clean
The resolution, deduplication, and review pipeline that keeps agent memory usable as it grows.
Jun 2
•
Paul Iusztin
38
5
May 2026
Stop Chasing the Perfect Ontology
Start with a fixed, generic base and extend only when your data demands it.
May 26
•
Paul Iusztin
49
10
6
Inside Neo4j's Agent Memory
The knowledge-graph patterns that turn one-shot conversations into compounding intelligence.
May 19
•
Paul Iusztin
48
3
6
From Vibe Coding to a Real Engineering Team
My Claude Code agentic coding setup that ships features end-to-end
May 12
•
Paul Iusztin
82
7
13
Building Agentic GraphRAG Systems
From knowledge graphs and ontologies to a unified memory as an MCP server for your AI agent.
May 5
•
Paul Iusztin
77
1
10
April 2026
What Held Up at 3 AM: One Engineer's RAG Case Study
You iterate. You evaluate. Weave CLI unifies 11 vector databases into one workflow.
Apr 29
•
Paul Iusztin
and
dr.max
27
5
Stop Orchestrating AI Agents. Use Ralph Loops Instead.
How one simple loop beats multi-agent orchestration and context rot in production.
Apr 23
•
Paul Iusztin
26
4
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
