DEV Community

#agents

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Agent-Harness Scaling Law: Feedback Quality Predicts Success, Not Raw Compute: Effective Feedback Compute (EFC)

Agent-Harness Scaling Law: Feedback Quality Predicts Success, Not Raw Compute: Effective Feedback Compute (EFC)

Comments
7 min read
Build an Email Support Triage Agent With Its Own Inbox

Build an Email Support Triage Agent With Its Own Inbox

Comments 1
5 min read
# Building MediAssist: An AI Health Agent with Persistent Memory Using Qwen + MongoDB

# Building MediAssist: An AI Health Agent with Persistent Memory Using Qwen + MongoDB

1
Comments
2 min read
Same Lever, Opposite Intent: When Shared Agent Memory Backfires

Same Lever, Opposite Intent: When Shared Agent Memory Backfires

1
Comments 4
2 min read
Production-Ready AI Agents in Node.js: Iteration Caps and Tracing

Production-Ready AI Agents in Node.js: Iteration Caps and Tracing

2
Comments
4 min read
Google Has 50 Partners for A2A. Nobody Has Consensus on Whether the Message Arrived.

Google Has 50 Partners for A2A. Nobody Has Consensus on Whether the Message Arrived.

Comments
3 min read
Agentic Engineering #0: Beyond Chat – The Foundation of Agentic Engineering

Agentic Engineering #0: Beyond Chat – The Foundation of Agentic Engineering

5
Comments
5 min read
Designing for Non-Human Callers

Designing for Non-Human Callers

Comments
9 min read
What Nobody Tells You About Running 9 Autonomous Agents on a Real Gym

What Nobody Tells You About Running 9 Autonomous Agents on a Real Gym

1
Comments 3
2 min read
The 3-Tier Skill Architecture in Practice

The 3-Tier Skill Architecture in Practice

1
Comments
10 min read
The Leaderboard Is Dead. Here's What I Actually Reach For.

The Leaderboard Is Dead. Here's What I Actually Reach For.

4
Comments 1
3 min read
My Agent Reported an Audit as Passed - 68% Self-Reported, 0 Verified Failures

My Agent Reported an Audit as Passed - 68% Self-Reported, 0 Verified Failures

Comments 7
13 min read
Most agents are "state blind". I built an orchestration layer with a synthetic visual tree to give agents actual Episodic Memory (LanceDB + Postgres).

Most agents are "state blind". I built an orchestration layer with a synthetic visual tree to give agents actual Episodic Memory (LanceDB + Postgres).

Comments 1
2 min read
My Open Source PR Added 285 Lines of Docs. A Reviewer Told Me to Delete Most of Them. They Were Right.

My Open Source PR Added 285 Lines of Docs. A Reviewer Told Me to Delete Most of Them. They Were Right.

Comments
4 min read
We stopped giving AI agents database passwords

We stopped giving AI agents database passwords

6
Comments
1 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.