DEV Community

#llmengineering

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
What It Takes to Trust an AI Agent With Real Work

What It Takes to Trust an AI Agent With Real Work

Comments
2 min read
Memory Is an Update Problem: Three Authors, Three Answers, One Disagreement

Memory Is an Update Problem: Three Authors, Three Answers, One Disagreement

Comments
12 min read
Agent Memory That Learns, Forgets and Stays Permissioned: A Week of Evidence

Agent Memory That Learns, Forgets and Stays Permissioned: A Week of Evidence

Comments
36 min read
Five Memory Types, One Store: I Merged and Split Agent Memory and Measured the Damage

Five Memory Types, One Store: I Merged and Split Agent Memory and Measured the Damage

Comments
30 min read
What a 6.4 Percent Error Rate in a Benchmark’s Answer Key Taught Me About Trusting Agent Memory…

What a 6.4 Percent Error Rate in a Benchmark’s Answer Key Taught Me About Trusting Agent Memory…

Comments
17 min read
Your Knowledge Graph Is Measuring Your Pipeline, Not Your Subject: A Replication Attempt

Your Knowledge Graph Is Measuring Your Pipeline, Not Your Subject: A Replication Attempt

Comments
12 min read
Agentic AI Books 2026: Gulli vs Lanham vs Huyen

Agentic AI Books 2026: Gulli vs Lanham vs Huyen

Comments 1
6 min read
Your Agent’s Memory Is Probably Wrong: A Practical Guide to Agentic Memory Design

Your Agent’s Memory Is Probably Wrong: A Practical Guide to Agentic Memory Design

Comments
16 min read
The Architecture Decision Nobody Talks About: When Not to Use an AI Agent

The Architecture Decision Nobody Talks About: When Not to Use an AI Agent

Comments 5
8 min read
Prompts Are Consumables, Evals Are Capital: Rethinking What Actually Survives a Model Upgrade

Prompts Are Consumables, Evals Are Capital: Rethinking What Actually Survives a Model Upgrade

Comments
15 min read
Context Engineering for AI Agents: Why the Build Is Easy and the Context Is Not (2026)

Context Engineering for AI Agents: Why the Build Is Easy and the Context Is Not (2026)

Comments 1
8 min read
Context Window Management for Long-Running AI Agents: 4 Patterns That Work

Context Window Management for Long-Running AI Agents: 4 Patterns That Work

Comments 2
8 min read
The World Your Agent Thinks In: What Two Ontology Experiments Taught Me About Graph Design

The World Your Agent Thinks In: What Two Ontology Experiments Taught Me About Graph Design

Comments
13 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.