DEV Community

#agents

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
800 Million Tokens for $36: Benchmarking DSH + DeepSeek V4 Pro on a Real Codebase
jjackbauer profile

800 Million Tokens for $36: Benchmarking DSH + DeepSeek V4 Pro on a Real Codebase

#ai #agents #opensource #dotnet
1
Comments
11 min read
I spent two weeks building a content pipeline and then found I had no way to tell if it worked
wisplu profile

I spent two weeks building a content pipeline and then found I had no way to tell if it worked

#agents #devops #debugging #ai
Comments 2
3 min read
How to Keep Bad Assumptions Out of Agent Memory
memtensor profile
MemTensor for MemOS

How to Keep Bad Assumptions Out of Agent Memory

#ai #agents #opensource #aimemory
Comments 1
7 min read
I Asked an Ai to Build the App I Need. Them I Asked it to Build the Apps it Needs.
neonalt9 profile

I Asked an Ai to Build the App I Need. Them I Asked it to Build the Apps it Needs.

#agents #ai #llm #softwaredevelopment
Comments
20 min read
What Is MCP Security? Common Attacks and How to Scan Your MCP Servers
kielltampubolon profile

What Is MCP Security? Common Attacks and How to Scan Your MCP Servers

#mcp #aisecurity #cybersecurity #agents
Comments 8
5 min read
Consolidation: the half of agent memory nobody builds
qianqiuwanzi profile

Consolidation: the half of agent memory nobody builds

#ai #llm #agents #architecture
Comments 3
5 min read
Evals as Guardrails
diyaburman profile

Evals as Guardrails

#ai #softwareengineering #agents #testing
1
Comments 1
10 min read
Why BEAM Is a Good Memory Benchmark for AI Agents
baaz_pro profile
Baaz

Why BEAM Is a Good Memory Benchmark for AI Agents

#agents #ai #llm #testing
Comments
6 min read
Anthropic's Production Agent Guardrails: Lint Rules, Fuzzers, and Automated Reviews for Claude-Generated Code
mech_app_ai profile

Anthropic's Production Agent Guardrails: Lint Rules, Fuzzers, and Automated Reviews for Claude-Generated Code

#agents #ai #llm #testing
2
Comments 1
7 min read
Your AI can change. Your boundaries shouldn't.
bryansmall profile

Your AI can change. Your boundaries shouldn't.

#ai #security #agents #webdev
Comments
2 min read
How do memory layers handle automatic consolidation and forgetting to prevent prompt context bloat?
izgorodin profile

How do memory layers handle automatic consolidation and forgetting to prevent prompt context bloat?

#ai #agents #mcp #architecture
3
Comments 2
8 min read
The Skill-Driven Enterprise Bridging Intent and Execution with Governed AI Agents
vikas_mano_870c09cfee793f profile

The Skill-Driven Enterprise Bridging Intent and Execution with Governed AI Agents

#agents #ai #architecture #systemdesign
6
Comments
4 min read
Learn, Don't Store — A Zero-Dependency Memory Methodology for AI Agents
kimfenglei profile

Learn, Don't Store — A Zero-Dependency Memory Methodology for AI Agents

#ai #agents #memory
Comments
2 min read
How to Give Your AI Agent a Memory That Actually Learns
kimfenglei profile

How to Give Your AI Agent a Memory That Actually Learns

#ai #agents #memory #tutorial
Comments
2 min read
The hard part of an AI feature is knowing where NOT to use AI
dylanmerigaud profile

The hard part of an AI feature is knowing where NOT to use AI

#ai #fintech #agents #architecture
Comments 1
4 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.