Articles
Industry news, technical articles, and product introductions
📚 Claude Tutorials Hub
40+ step-by-step Claude guides — prompt engineering, Claude Code, API, agents. Browse by topic →
Loading...
Auto-Generating Daily WeChat Covers with MiniMax: A Production Pipeline Postmortem
We automated our newsletter's daily WeChat cover: MiniMax image-01 renders a marketing-style background, an SVG text layer composites the headline, sharp crops to the exact 2.35:1 ratio, and Playwright drops it into the WeChat draft. The full postmortem covers why AI must never draw the title text, how one 'negative space' prompt word shoved the subject out of frame, and how word-splitting line breaks got fixed — with three real before/after images.
prompt-engineeringautomation+6
ai-tutorialsAug 5, 20266 min
125I Put My Opus 5 Config on the Recommended Diet, Then Ran 18 A/B Trials: 21% Cheaper, and I Can't Prove It's Better
"Opus 5 verifies itself, so delete your fallback prompts" is advice you hear everywhere. I took it, then isolated both configs with CLAUDE_CONFIG_DIR and ran 18 headless trials on identical tasks. Output tokens dropped 21% and wall clock 20-29%, with zero counterexamples. But two of the rewritten rules never fired at all, and one result points the other way: the old config's most thorough run covered a strict superset of what the new one found. Why cheaper and better are separate questions.
prompt-engineeringclaude-code+4
claudeAug 5, 20266 min
182Anthropic Deleted 80% of Claude Code's System Prompt. The Evals Didn't Move.
'We removed over 80% of Claude Code's system prompt' — and the evals didn't move. The popular takeaway ('write shorter prompts') is wrong: what got deleted was constraints, not information. A usable dividing line, plus the API-layer mechanics the official post left out and the two real disagreements from 343 HN comments.
prompt-engineeringclaude-code+5
ai-tutorialsJul 27, 202613 min
313Prompt Engineering for Beginners: 10 Techniques That Actually Work
Two people ask the same AI the same question and get completely different results. The difference is prompt quality. This guide covers 10 concrete, practical techniques for writing prompts that consistently get useful, accurate outputs from any large language model.
prompt-engineeringchatgpt+3
ai-promptsApr 22, 20268 min
179System Prompt Design: Make Claude Understand Exactly What You Need
Deep dive into system prompt design principles and best practices. Learn to control Claude's behavior through role definition, constraints, and output formatting.
prompt-engineeringclaude+2
claudeApr 13, 20262 min
843Structured Output and Multimodal: Formatted Responses and Vision
Learn to get Claude to output structured formats like JSON and XML, and leverage Claude's vision capabilities for understanding images, documents, and charts.
prompt-engineeringvision+3
claudeApr 13, 20262 min
619The Complete Guide to Prompt Engineering with Claude
Master the core principles and practical techniques of prompt engineering with Claude. From basics to advanced strategies for writing precise, effective prompts.
prompt-engineeringclaude+2
claudeApr 13, 20264 min
625Chain of Thought Prompting: Solve Complex Problems Step by Step with Claude
Master Chain of Thought prompting to guide Claude through step-by-step reasoning for math, logic, and complex multi-step problems.
prompt-engineeringreasoning+2
claudeApr 13, 20262 min
435Claude XML Tags Guide: Structure Prompts for Better Output
A practical guide to using XML tags in Claude prompts so context, instructions, examples, and answers stay cleanly separated.
prompt-engineeringclaude+2
ai-tutorialsMar 29, 20262 min
6857Role Prompting in Claude: When to Use System Prompts
When to use role prompting with Claude, how system prompts differ from task instructions, and how Anthropic recommends separating role from user requests.
prompt-engineeringclaude+2
ai-tutorialsMar 29, 20262 min
515Prompt Templates for Claude: Reuse Good Prompts Without Losing Quality
How to use prompt templates and variables in Claude so repeated tasks stay consistent, testable, and easier to maintain.
prompt-engineeringclaude+2
ai-tutorialsMar 29, 20263 min
189Claude Prompt Improver Guide: Turn Weak Prompts Into Reliable Templates
A practical guide to Anthropic's prompt improver for upgrading weak prompts into clearer, more structured templates with better examples and reasoning instructions.
prompt-engineeringclaude+2
ai-tutorialsMar 29, 20263 min
360