Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
agents
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
Clean AI Development
Marco Sbragi
Marco Sbragi
Marco Sbragi
Follow
May 1
Clean AI Development
#
discuss
#
ai
#
devops
#
agents
1
 reaction
Comments
3
 comments
4 min read
Show HN: I made an AI that reviews iPhone apps – 1h of autonomous GUI work
jg-noncelogic
jg-noncelogic
jg-noncelogic
Follow
Mar 28
Show HN: I made an AI that reviews iPhone apps – 1h of autonomous GUI work
#
showdev
#
agents
#
automation
#
ios
Comments
Add Comment
1 min read
Human-in-the-Loop Agent Systems in Java
mgd43b
mgd43b
mgd43b
Follow
for
AgentEnsemble
Mar 28
Human-in-the-Loop Agent Systems in Java
#
java
#
ai
#
agents
#
enterprise
Comments
Add Comment
6 min read
Why Your AI Agent Breaks After Week Two (And How to Fix It)
Adam cipher
Adam cipher
Adam cipher
Follow
Mar 28
Why Your AI Agent Breaks After Week Two (And How to Fix It)
#
ai
#
agents
#
api
#
programming
Comments
Add Comment
2 min read
Cursor Introduces a TypeScript SDK for Building Programmatic Coding Agents With Sandboxed Cloud VMs, Subagents, Hooks, and Token-Based Pricing
Manas kolaskar
Manas kolaskar
Manas kolaskar
Follow
May 1
Cursor Introduces a TypeScript SDK for Building Programmatic Coding Agents With Sandboxed Cloud VMs, Subagents, Hooks, and Token-Based Pricing
#
typescript
#
cursor
#
agents
#
cloud
Comments
1
 comment
3 min read
ARC-AGI V3 Explained: The New AI Benchmark That Breaks Every Agent
Max Quimby
Max Quimby
Max Quimby
Follow
Mar 29
ARC-AGI V3 Explained: The New AI Benchmark That Breaks Every Agent
#
ai
#
machinelearning
#
agents
#
benchmark
Comments
Add Comment
3 min read
The $12 Cost Tracking Bug That Inverted My Score/$ Comparison
Pavel Gajvoronski
Pavel Gajvoronski
Pavel Gajvoronski
Follow
Apr 20
The $12 Cost Tracking Bug That Inverted My Score/$ Comparison
#
buildinpublic
#
ai
#
agents
#
costoptimization
1
 reaction
Comments
Add Comment
6 min read
Connect to Any Agent on iOS/Android! Claude, Codex, Copilot, Gemini, OpenCode and more
Jun Han
Jun Han
Jun Han
Follow
May 1
Connect to Any Agent on iOS/Android! Claude, Codex, Copilot, Gemini, OpenCode and more
#
showdev
#
agents
#
ai
#
mobile
1
 reaction
Comments
Add Comment
2 min read
The Amnesia Tax: Why Stateless Agents Are Eating Your Margins
Aamer Mihaysi
Aamer Mihaysi
Aamer Mihaysi
Follow
Mar 28
The Amnesia Tax: Why Stateless Agents Are Eating Your Margins
#
ai
#
agents
#
llm
#
engineering
Comments
Add Comment
3 min read
Designing an MCP Registry for Agents, Not Just Humans: Metrics, Experiments, and a Call for Collaboration
anhmtk
anhmtk
anhmtk
Follow
May 1
Designing an MCP Registry for Agents, Not Just Humans: Metrics, Experiments, and a Call for Collaboration
#
showdev
#
mcp
#
agents
#
api
1
 reaction
Comments
Add Comment
2 min read
Beyond the Hype: Building Practical AI Agents with Memory and Reasoning
Midas126
Midas126
Midas126
Follow
Mar 28
Beyond the Hype: Building Practical AI Agents with Memory and Reasoning
#
ai
#
machinelearning
#
agents
#
development
Comments
Add Comment
5 min read
Beyond the Hype: Building Practical AI Agents with Memory and Reasoning
Midas126
Midas126
Midas126
Follow
Mar 29
Beyond the Hype: Building Practical AI Agents with Memory and Reasoning
#
ai
#
machinelearning
#
agents
#
development
Comments
1
 comment
5 min read
Your Nginx Logs Are Your Sales Pipeline (In the Agentic Economy)
Jonathan Bulkeley
Jonathan Bulkeley
Jonathan Bulkeley
Follow
Mar 28
Your Nginx Logs Are Your Sales Pipeline (In the Agentic Economy)
#
ai
#
webdev
#
nginx
#
agents
1
 reaction
Comments
Add Comment
5 min read
The Context Window Is the New Memory Architecture
Aamer Mihaysi
Aamer Mihaysi
Aamer Mihaysi
Follow
Mar 28
The Context Window Is the New Memory Architecture
#
ai
#
agents
#
llm
#
productivity
Comments
Add Comment
4 min read
GPT-5.1 scored 26%. Gemini 3 Flash scored 74%. Same prompt, same tools.
ThomasP
ThomasP
ThomasP
Follow
Mar 28
GPT-5.1 scored 26%. Gemini 3 Flash scored 74%. Same prompt, same tools.
#
ai
#
llm
#
benchmark
#
agents
Comments
Add Comment
8 min read
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account