KKling4 AI·Nov 2How I turn a prompt library into a weekly shot list (50 Seedream examples as raw material)A prompt library is not a to-do list until you schedule it. I use the 50 Seedream 5.0 prompts article as raw material: pick five genres for the week, swap every sample noun for something we actually n3 min read·ai-image-lab.hashnode.dev
PPowerduck·Oct 29Redact Before You Paste It Into the Coding AgentThe prompt is not a scratchpad. A token, an internal hostname, or customer PII you paste into the agent lives in a log you do not fully control, long after the fix ships.3 min read·blogs.powerduck.com
BBrian King·Aug 26Using AI to Write My Posts.Or: Swimming in a Cesspool of AI Slop.10 min read·solodev.app
JJothimani Radhakrishnan·Jul 12Prompt #2: CloudWatch Agent Setup for a Java App Load Test - in One PromptDeep metrics, log shipping, and a ready dashboard before your performance test starts - plus the war story of why it matters.6 min read·runbook.opsinsights.dev
JJothimani Radhakrishnan·Jul 12Prompt #1: Turn Your AI Agent into Your Hashnode Publishing AssistantOne prompt that lets an LLM read, draft, and publish on your Hashnode blog - token stays safe in an env var.4 min read·runbook.opsinsights.dev
AAryan Mankame·Jun 9ChatPromptTemplate Is Not a Prompt: Following a Request from LangChain to Transformer AttentionLangChain request through ChatPromptTemplate, tokenization, embeddings, attention, system prompts, privacy filtering, and next-token prediction.9 min read·wethinkbig.hashnode.dev1
HHomi Choudhury·May 6From Figma Screen to Production Code with LLMs and Figma MCP Part 2 - How we set up LLM-powered workflows to generate complete, production-ready components from Figma designs — using MCP, Code Connect, and structured instruction files.12 min read·homi.hashnode.dev
Bbill hong·Apr 22I Added a Paragraph to My AI Character's System Prompt. She Invented a Different One.Adding a "don't do X" paragraph to my AI character's system prompt backfired. Here's the rule I now run every character design through.6 min read·billhongtendera.hashnode.dev1
RRahul Sehrawat·Apr 13System, User, Tool: the Real Prompt HierarchyEvery LLM call has three kinds of messages: system, user, and tool. They disagree all the time. Here is who wins, why, and how to design prompts that don't get overridden by the next user turn.10 min read·ai-zero-to-hero.hashnode.dev
RRahul Sehrawat·Apr 13Prompts Are Code, Not ConfigMost teams treat prompts like magic strings. Then they wake up to a regression nobody can explain. Here is how to treat prompts like code — versioned, templated, tested — without making a career of it.10 min read·ai-zero-to-hero.hashnode.dev