DEV Community

#prompting

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
What Is Context Window? (And Why AI Forgets the Beginning of Your Conversation Midway Through)

What Is Context Window? (And Why AI Forgets the Beginning of Your Conversation Midway Through)

Comments
4 min read
A Good SKILL.md Is the Cheapest Reliability Upgrade You'll Make

A Good SKILL.md Is the Cheapest Reliability Upgrade You'll Make

Comments
6 min read
Your "Act As An Expert" Prompts Are Lying To You

Your "Act As An Expert" Prompts Are Lying To You

Comments
3 min read
Stop Saying 'Think Step by Step': What Addy Osmani's Opus 5.5 Prompting Guide Actually Says

Stop Saying 'Think Step by Step': What Addy Osmani's Opus 5.5 Prompting Guide Actually Says

2
Comments
7 min read
Prompt Registry & CI Eval Gates for Safe LLMs

Prompt Registry & CI Eval Gates for Safe LLMs

Comments
4 min read
Prompt Caching Playbook for Agentic LLMs — Costs & Latency

Prompt Caching Playbook for Agentic LLMs — Costs & Latency

1
Comments
5 min read
Typos don't break LLM prompts. One missing quote mark does.

Typos don't break LLM prompts. One missing quote mark does.

3
Comments 2
5 min read
I told the model to separate fields with <TAB>. It did exactly that, and I lost 79 percent of my data.

I told the model to separate fields with <TAB>. It did exactly that, and I lost 79 percent of my data.

1
Comments
3 min read
DSPy: Replacing Prompt Engineering with Declarative Optimization Compilers

DSPy: Replacing Prompt Engineering with Declarative Optimization Compilers

Comments
3 min read
Claude Code Best Practices for Prompting and Context

Claude Code Best Practices for Prompting and Context

Comments
1 min read
The 12-Prompt Eval I Run Before I Trust Any Model Upgrade

The 12-Prompt Eval I Run Before I Trust Any Model Upgrade

Comments
3 min read
Upgrade Your Prompt Stack for Sonnet 5 and GPT-5.6 Without Rewriting Everything

Upgrade Your Prompt Stack for Sonnet 5 and GPT-5.6 Without Rewriting Everything

Comments
4 min read
Structured Output That Survives a Model Swap: The JSON Scaffold I Actually Ship

Structured Output That Survives a Model Swap: The JSON Scaffold I Actually Ship

Comments
3 min read
6 Sneaky Ways to Get AI to Actually Finish the Code/Email/Essay Instead of Trailing Off Mid-Sentence

6 Sneaky Ways to Get AI to Actually Finish the Code/Email/Essay Instead of Trailing Off Mid-Sentence

Comments
6 min read
GPT-5.6 Prompting Guide: Two Defaults That Bill 1.5x and 10x More

GPT-5.6 Prompting Guide: Two Defaults That Bill 1.5x and 10x More

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