DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Building a Ride-Share Zone-Balancing Agent with LangGraph — Part 2: Teaching the Agent to Read Ops Notes

Building a Ride-Share Zone-Balancing Agent with LangGraph — Part 2: Teaching the Agent to Read Ops Notes

Comments
7 min read
Node.js Support Ticket Classification with LLM JSON Schema Tags

Node.js Support Ticket Classification with LLM JSON Schema Tags

Comments
7 min read
Speech-to-Text Plus Multi-Model Transcript Summaries: One API Key or Two?

Speech-to-Text Plus Multi-Model Transcript Summaries: One API Key or Two?

Comments
6 min read
My AI Answered in 5.8 Seconds and Said Nothing Useful. I Almost Blamed the Model.

My AI Answered in 5.8 Seconds and Said Nothing Useful. I Almost Blamed the Model.

2
Comments
8 min read
Play in GenAI is now in its applications

Play in GenAI is now in its applications

Comments
1 min read
Selecting a Compatible API Gateway: Token Cost, Batch Work, and Data Residency

Selecting a Compatible API Gateway: Token Cost, Batch Work, and Data Residency

Comments
7 min read
The translation model that cost 15 more was also the most confidently wrong

The translation model that cost 15 more was also the most confidently wrong

2
Comments
4 min read
The Guardrail Pointed at a File That Never Existed

The Guardrail Pointed at a File That Never Existed

Comments 2
6 min read
Why We Calculate Astrology Charts Before Asking an LLM to Explain Them

Why We Calculate Astrology Charts Before Asking an LLM to Explain Them

Comments
2 min read
what actually makes a system agentic?

what actually makes a system agentic?

2
Comments
1 min read
Langfuse TypeScript prompt regression gates with GitHub Actions

Langfuse TypeScript prompt regression gates with GitHub Actions

Comments 2
3 min read
We judged the same frozen answers 15 times. The judge wasn't the noisy part.

We judged the same frozen answers 15 times. The judge wasn't the noisy part.

Comments
6 min read
Your offline LLM eval isn't measuring your model — it's measuring your rate limits

Your offline LLM eval isn't measuring your model — it's measuring your rate limits

Comments 1
3 min read
2.Self-Hosted AI: n8n + Ollama, local AI workflows on your Mac

2.Self-Hosted AI: n8n + Ollama, local AI workflows on your Mac

Comments
4 min read
Serving 500 concurrent LLM chats on one 4-core box with tier-aware queueing

Serving 500 concurrent LLM chats on one 4-core box with tier-aware queueing

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