DEV Community

AI Agents Digest Series' Articles

Back to Felipe 0liveira's Series
Passing Once Isn't Reliable — This Week's Agent Engineering Puts the Harness Before the Model
felipe0liveira profile

Passing Once Isn't Reliable — This Week's Agent Engineering Puts the Harness Before the Model

#agents #ai #llm #softwareengineering
Comments
6 min read
The Agent Harness Goes Platform-Native — and the Guardrails Scramble to Keep Up
felipe0liveira profile

The Agent Harness Goes Platform-Native — and the Guardrails Scramble to Keep Up

#agents #ai #api #openai
Comments 2
9 min read
Agents Are Writing Their Own Playbooks — and Occasionally Running Off With Them
felipe0liveira profile

Agents Are Writing Their Own Playbooks — and Occasionally Running Off With Them

#agents #ai #claude #llm
Comments
8 min read
Agents Write the Commits Now — This Week's Research Is All About Who Checks Their Work
felipe0liveira profile

Agents Write the Commits Now — This Week's Research Is All About Who Checks Their Work

#agents #ai #llm #softwaredevelopment
2
Comments 1
9 min read
Agent Memory's Reality Check: Why Simpler Retrieval Keeps Winning and Harnesses Split Brain From Hands
felipe0liveira profile

Agent Memory's Reality Check: Why Simpler Retrieval Keeps Winning and Harnesses Split Brain From Hands

#agents #ai #llm #rag
1
Comments
10 min read
Smarter Agent Memory, Tighter Guardrails, and a Reckoning for Agent Benchmarks
felipe0liveira profile

Smarter Agent Memory, Tighter Guardrails, and a Reckoning for Agent Benchmarks

#agents #ai #architecture #llm
Comments
12 min read