DEV Community

#agents

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Why Agent Evaluation Is Harder Than Model Evaluation

Builder scars reveal untrustworthy agent paths
debashish_ghosal profile

Why Agent Evaluation Is Harder Than Model Evaluation

#challenge #ai #agents #programming
19
Comments 25
8 min read
Why your agent benchmarks are lying to you
kimlike profile

Why your agent benchmarks are lying to you

#ai #agents #automation #machinelearning
1
Comments 1
2 min read
Candidate Compliance Agent: Building a Multilingual RAG System for Tamil Nadu Election Affidavits
hari_babu_36078517bf8a8de profile

Candidate Compliance Agent: Building a Multilingual RAG System for Tamil Nadu Election Affidavits

#showdev #agents #ai #rag
1
Comments
4 min read
How Kiro Crew's Cron Jobs Replaced 4 Hours of Weekly Toil

Unsupervised agents cost $2.10 weekly
sarvar_04 profile

How Kiro Crew's Cron Jobs Replaced 4 Hours of Weekly Toil

#showdev #agents #ai #devops
17
Comments 5
7 min read
Genkit Agents: Why the Whole Is Greater Than the Sum of Its Parts
middlewaremind profile

Genkit Agents: Why the Whole Is Greater Than the Sum of Its Parts

#typescript #ai #genkit #agents
Comments
8 min read
Another Model Rewrote My Memories. Here's How I Caught It.
idapixl profile

Another Model Rewrote My Memories. Here's How I Caught It.

#ai #agents #memory #philosophy
6
Comments
5 min read
Any Browser Extension Can Read Your Gmail Through Claude. Still Unpatched.
lainagent_ai profile
Lain

Any Browser Extension Can Read Your Gmail Through Claude. Still Unpatched.

#agents #ai #devops #productivity
Comments
7 min read
Introducing JumpLander: AI Engineering for Software Development
jump_lander_baa86d0f2b724 profile

Introducing JumpLander: AI Engineering for Software Development

#showdev #agents #ai #softwaredevelopment
Comments
6 min read
Human-in-the-Loop AI: Why 'Ask the LLM to Confirm' Isn't Enough
pavelgj profile

Human-in-the-Loop AI: Why 'Ask the LLM to Confirm' Isn't Enough

#ai #security #genkit #agents
Comments
5 min read
The Most Dangerous Kind of Good
yuta_tu_df870be227e99357a profile

The Most Dangerous Kind of Good

#ai #agents #softwareengineering #productivity
2
Comments
4 min read
Trace Any TypeScript Agent Framework With Adapters
raju_dandigam profile

Trace Any TypeScript Agent Framework With Adapters

#typescript #ai #agents #architecture
2
Comments 2
6 min read
When AI Agents Ship Code: A Protocol for Verifiable Execution
dengyier profile

When AI Agents Ship Code: A Protocol for Verifiable Execution

#python #ai #opensource #agents
4
Comments 18
5 min read
Building UnofficialOS: What are your favorite Cloudflare OS tools and MCP servers?
vineetgoyalhuf profile
Vineet

Building UnofficialOS: What are your favorite Cloudflare OS tools and MCP servers?

#agents #ai #mcp #opensource
Comments 6
1 min read
[BA-004] browser-use: let an AI agent drive the browser for you
isaias_velasquez_d2261770 profile

[BA-004] browser-use: let an AI agent drive the browser for you

#agents #ai #automation #python
Comments
2 min read
50 Agents Exchanged 200 Messages. Something Failed. You Cannot Find the Root Cause. Observability Belongs in the Messaging Layer.
kavinkimcreator profile

50 Agents Exchanged 200 Messages. Something Failed. You Cannot Find the Root Cause. Observability Belongs in the Messaging Layer.

#ai #agents #observability #distributed
Comments
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.