DEV Community

Artificial Intelligence

Artificial intelligence leverages computers and machines to mimic the problem-solving and decision-making capabilities found in humans and in nature.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
tool-output-format: Render Tool Results as LLM-Friendly Markdown

tool-output-format: Render Tool Results as LLM-Friendly Markdown

Comments
5 min read
Replay Every LLM Prompt Against a New Model Before You Migrate

Replay Every LLM Prompt Against a New Model Before You Migrate

Comments
3 min read
50 Users Ask the Same Question. Your Agent Makes 50 API Calls. Here's the Fix.

50 Users Ask the Same Question. Your Agent Makes 50 API Calls. Here's the Fix.

Comments
4 min read
agentcast-rs: Repair, Validate, and Retry LLM JSON Output in Rust

agentcast-rs: Repair, Validate, and Retry LLM JSON Output in Rust

Comments
5 min read
A/B Test Your Prompts Without a Framework

A/B Test Your Prompts Without a Framework

Comments
5 min read
Stop Paying for the Same Tool Call Twice: Memoize LLM Tool Calls with tool-call-cache

Stop Paying for the Same Tool Call Twice: Memoize LLM Tool Calls with tool-call-cache

Comments
5 min read
Why is Your Chatbot Saving "Good Morning" as the Customer's Name? 🤖🤦‍♂️

Why is Your Chatbot Saving "Good Morning" as the Customer's Name? 🤖🤦‍♂️

Comments
3 min read
llm-json-repair: Three-Pass Local JSON Repair for LLM Responses in Rust

llm-json-repair: Three-Pass Local JSON Repair for LLM Responses in Rust

Comments
4 min read
Priority Queue for Agent Sub-Tasks: Stop Processing Low-Priority Work First

Priority Queue for Agent Sub-Tasks: Stop Processing Low-Priority Work First

Comments
4 min read
Heuristic Prompt Compression: Cut Your Context Window Usage Without Losing Key Information

Heuristic Prompt Compression: Cut Your Context Window Usage Without Losing Key Information

Comments
4 min read
My agent made a $400 mistake. I had no idea why. So I built a WHY layer.

My agent made a $400 mistake. I had no idea why. So I built a WHY layer.

Comments
5 min read
llm-fallback-chain: Ordered Provider Failover for LLM Calls

llm-fallback-chain: Ordered Provider Failover for LLM Calls

Comments
5 min read
perfectcorp-tryon-concierge: Virtual Try-On via Chat

perfectcorp-tryon-concierge: Virtual Try-On via Chat

Comments
5 min read
Your Agent Loop Needs a Real Exit: llm-stop-conditions

Your Agent Loop Needs a Real Exit: llm-stop-conditions

Comments
5 min read
Why Every Library in the Agent Stack Has Zero Runtime Dependencies

Why Every Library in the Agent Stack Has Zero Runtime Dependencies

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