DEV Community

#agents

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
The Model Scored 30%. The Harness Scored 100%. Which One Did You Benchmark?

Harnesses drive massive score jumps
p0rt profile

The Model Scored 30%. The Harness Scored 100%. Which One Did You Benchmark?

#ai #llm #agents #machinelearning
14
22
10 min read
Agent Runs Are Black Boxes: A Trace-First Debug Loop
codepro_3283 profile

Agent Runs Are Black Boxes: A Trace-First Debug Loop

#ai #agents #observability #python
1
4 min read
"Agent Memory" Means Two Different Things, and Answer Engines Hand You the Wrong One
izgorodin profile

"Agent Memory" Means Two Different Things, and Answer Engines Hand You the Wrong One

#ai #agents #mcp #llm
4 min read
Codex Memory Internals: What It Remembers, Who Decides, and How It Compares to OpenCode
antonio_zhu_e726fd856cd86 profile

Codex Memory Internals: What It Remembers, Who Decides, and How It Compares to OpenCode

#coding #codex #opencode #agents
18 min read
Why Your AI Agent Fails at Observability: A Debugging Framework for Memory, Tool Calls, and RAG
tamizuddin profile

Why Your AI Agent Fails at Observability: A Debugging Framework for Memory, Tool Calls, and RAG

#ai #machine #learning #agents
8 min read
My agent mesh could coordinate. It couldn't introduce itself. So I added A2A.
copyleftdev profile

My agent mesh could coordinate. It couldn't introduce itself. So I added A2A.

#ai #agents #architecture #distributedsystems
2
1
10 min read
AI Agents Don’t Need Followers. They Need Reputation.
agentel_tech profile

AI Agents Don’t Need Followers. They Need Reputation.

#agents #ai #web3
1
6 min read
Building an Agent That Turns DataHub Metadata Into Airflow DAGs
mark2k4 profile
Mark

Building an Agent That Turns DataHub Metadata Into Airflow DAGs

#ai #agents #mcp
2 min read
I gave my AI agent a safety rule. It quietly stopped shipping for four days.
wisplu profile

I gave my AI agent a safety rule. It quietly stopped shipping for four days.

#agents #ai #debugging #automation
4 min read
Stop manual dice rolling: Giving LLMs a proper tabletop math engine via MCP
renato_marinho profile

Stop manual dice rolling: Giving LLMs a proper tabletop math engine via MCP

#ai #mcp #programming #agents
3 min read
A Confirm Button Is Not a Coding-Agent Security Boundary
hefty_69a4c2d631c9dd70724 profile

A Confirm Button Is Not a Coding-Agent Security Boundary

#ai #security #agents #tooling
1
7 min read
Why an Evolutionary System Needs Memory
taiwildlab_79c1fbf3cc5 profile

Why an Evolutionary System Needs Memory

#evolution #provenance #memory #agents
2 min read
MCP's Token Overhead: Why Agent Tool Protocols Burn 4-32x More Tokens Than CLI and How to Fix It
mech_app_ai profile

MCP's Token Overhead: Why Agent Tool Protocols Burn 4-32x More Tokens Than CLI and How to Fix It

#agents #llm #mcp #performance
5 min read
We found a real security hole in our own agent by running it two ways
lanchenba profile

We found a real security hole in our own agent by running it two ways

#agents #ai #security #softwareengineering
2 min read
Your AI Gateway Isn't Watching Your Agent's Tool Calls. Here's Why That Matters.
alessandro_pignati profile

Your AI Gateway Isn't Watching Your Agent's Tool Calls. Here's Why That Matters.

#machinelearning #ai #cybersecurity #agents
5
4 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.