DEV Community

Testing

Find those bugs before your users do! 🐛

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
My Agent Turned "I Haven't Decided" Into "Not Yet." Now the Model Isn't Allowed to Write Its Own Memory.
kenielzep97 profile

My Agent Turned "I Haven't Decided" Into "Not Yet." Now the Model Isn't Allowed to Write Its Own Memory.

#agents #ollama #python #testing
12
Comments 2
6 min read
Claude Haiku 5.5 Bills 5x for Prompts Over 100K Tokens. A Node Guard That Counts First
gabrielanhaia profile

Claude Haiku 5.5 Bills 5x for Prompts Over 100K Tokens. A Node Guard That Counts First

#typescript #ai #node #testing
Comments
9 min read
The Narrow Sidewalk: Where Developers Stand When Agents Write the Code
mehdimohseni82 profile

The Narrow Sidewalk: Where Developers Stand When Agents Write the Code

#dotnet #aspnetcore #ai #testing
Comments
7 min read
A file path is a claim, not a pointer
ttdiary profile

A file path is a claim, not a pointer

#testing #sre #debugging #productivity
Comments
6 min read
Your agent eval passed. Did the fixture leak the answer?
mahmaddafzal profile

Your agent eval passed. Did the fixture leak the answer?

#python #testing #ai
Comments
3 min read
Exit Criteria for a Free Model Tier
aiio_6471 profile

Exit Criteria for a Free Model Tier

#ai #testing #devops #opensource
Comments
6 min read
We tested 4 AI app builders with the same prompt. Here's what broke.
vibetierlist profile

We tested 4 AI app builders with the same prompt. Here's what broke.

#ai #nocode #testing #webdev
Comments
3 min read
Fault-Injecting the Free Seat: An Offline Fallback Contract for Local-First Agents
codepro_9661 profile

Fault-Injecting the Free Seat: An Offline Fallback Contract for Local-First Agents

#ai #testing #architecture #devtools
Comments
6 min read
A generated video still needs a receipt and a stopped runtime
renga154 profile

A generated video still needs a receipt and a stopped runtime

#python #ai #testing #webdev
Comments
2 min read
Zero Cost Is Not Zero Variance: Four Myths About Repeating an AI Coding Run
devio_3007 profile

Zero Cost Is Not Zero Variance: Four Myths About Repeating an AI Coding Run

#ai #testing #devtools #productivity
Comments
6 min read
Your Agent Benchmark Pauses the World. Production Doesn't.
vikassri profile

Your Agent Benchmark Pauses the World. Production Doesn't.

#transformers #agents #benchmark #testing
Comments
4 min read
Build a 10-Case Eval Set for Your AI Agent and Run It on Every Change
promptmaster profile

Build a 10-Case Eval Set for Your AI Agent and Run It on Every Change

#ai #agents #testing #python
Comments
6 min read
Is that an agent or a template? Three signals that fooled us, and the one test that held up
sibi_s_130d5df2798dfc3179 profile

Is that an agent or a template? Three signals that fooled us, and the one test that held up

#ai #agents #mcp #testing
Comments
3 min read
Debug a webhook locally: capture once, fix, and replay
adrian_orenes_3d446ee5af8 profile

Debug a webhook locally: capture once, fix, and replay

#webdev #tutorial #testing #api
Comments
3 min read
Replay One Span, Not the Whole Run
codepro_3283 profile

Replay One Span, Not the Whole Run

#observability #ai #testing #python
Comments
5 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.