--- title: "#prompt-engineering articles | Hashnode" description: "Explore 385 articles tagged #prompt-engineering on Hashnode. Tutorials, guides, and how-tos from the community." url: "https://hashnode.com/tag/prompt-engineering" --- Tag # #prompt-engineering 385 posts · 7 followers [Santosh](https://hashnode.com/@sant-sh) · [17h ago](https://hashnode.com/posts/context-memory-and-skills/6af3de39464130a954259750) ### [Context Engineering for AI Agents: Memory, State, Prompts, and Skills](https://blog.sant.sh/context-memory-and-skills?utm_source=hashnode&utm_medium=feed) Separate context, memory, retrieval, working state, and skills. Build resumable records and reusable procedures that preserve source evidence. 6 min read · [blog.sant.sh](https://blog.sant.sh/context-memory-and-skills?utm_source=hashnode&utm_medium=feed) [Hamza](https://hashnode.com/@loopengineeringai) · [5d ago](https://hashnode.com/posts/i-stopped-prompting-harder-i-started-engineering-the-loop/6aedb599089366803bbf5170) ### [I stopped prompting harder. I started engineering the loop.](https://loopengineeringai.hashnode.dev/i-stopped-prompting-harder-i-started-engineering-the-loop?utm_source=hashnode&utm_medium=feed) I used to ask AI for the whole app in one prompt. Then I would ask again, and again, and get a slightly different mess each time. The problem was not the model. It was the way I was working. One promp 1 min read · [loopengineeringai.hashnode.dev](https://loopengineeringai.hashnode.dev/i-stopped-prompting-harder-i-started-engineering-the-loop?utm_source=hashnode&utm_medium=feed) [Adam Jaber](https://hashnode.com/@adamjaber) · [5d ago](https://hashnode.com/posts/llm-eval-noise-aa-test/6aed67410cbb90fbbad3483c) ### [LLM Eval Noise: Run an A/A Test Before You Trust a Prompt Win](https://simplyexplained.hashnode.dev/llm-eval-noise-aa-test?utm_source=hashnode&utm_medium=feed) Score your prompt against itself, count flipped cases instead of averages, and keep a holdout you touch once. With Python you can paste. 11 min read · [simplyexplained.hashnode.dev](https://simplyexplained.hashnode.dev/llm-eval-noise-aa-test?utm_source=hashnode&utm_medium=feed) [3](https://hashnode.com/posts/llm-eval-noise-aa-test/6aed67410cbb90fbbad3483c) [Muhammad Ahmad](https://hashnode.com/@mahmadmanzoor) · [6d ago](https://hashnode.com/posts/agent-instructions-that-actually-change-behaviour/6aec51797885879be7891100) ### [Agent instructions that actually change behaviour](https://mahmadmanzoor.hashnode.dev/agent-instructions-that-actually-change-behaviour?utm_source=hashnode&utm_medium=feed) Make agent instructions change behaviour: short CLAUDE.md rules with triggers, skills for how-tos, hooks for hard limits, and probe tests. 9 min read · [mahmadmanzoor.hashnode.dev](https://mahmadmanzoor.hashnode.dev/agent-instructions-that-actually-change-behaviour?utm_source=hashnode&utm_medium=feed) [2](https://hashnode.com/posts/agent-instructions-that-actually-change-behaviour/6aec51797885879be7891100) [SelfHealing](https://hashnode.com/@selfhealing) · [6d ago](https://hashnode.com/posts/your-ai-agent-remembers-the-wrong-things-a-no-code-memory-hygiene-routine/6aec3f9db3de6430f815e2cb) ### [Your AI Agent Remembers the Wrong Things: A No-Code Memory Hygiene Routine](https://selfhealing.hashnode.dev/your-ai-agent-remembers-the-wrong-things-a-no-code-memory-hygiene-routine?utm_source=hashnode&utm_medium=feed) Five operator habits that stop stale knowledge, invented preferences and private notes from contaminating the agents your business runs on. 5 min read · [selfhealing.hashnode.dev](https://selfhealing.hashnode.dev/your-ai-agent-remembers-the-wrong-things-a-no-code-memory-hygiene-routine?utm_source=hashnode&utm_medium=feed) [Jason Vertrees](https://hashnode.com/@jvertrees) · [Nov 4](https://hashnode.com/posts/give-your-ai-the-intent-not-just-the-rule/6aeb5dc5fc9f4ef946a2c93b) ### [Give Your AI the Intent, Not Just the Rule](https://jvertrees.hashnode.dev/give-your-ai-the-intent-not-just-the-rule?utm_source=hashnode&utm_medium=feed) A short memo on why prohibitions alone don't constrain coding agents. 3 min read · [jvertrees.hashnode.dev](https://jvertrees.hashnode.dev/give-your-ai-the-intent-not-just-the-rule?utm_source=hashnode&utm_medium=feed) [LeakBait team](https://hashnode.com/@leakbait) · [Nov 4](https://hashnode.com/posts/we-built-a-prompt-injection-game-where-each-level-adds-one-real-defense/6aeb06ea027160259ca85b73) ### [We built a prompt-injection game where each level adds one real defense](https://leakbait.hashnode.dev/we-built-a-prompt-injection-game-where-each-level-adds-one-real-defense?utm_source=hashnode&utm_medium=feed) Disclosure: LeakBait is our own free project; this post was drafted with AI help. LeakBait is a browser game: a chatbot guards a fake 8-letter password and you try to talk it into leaking. Every run g 2 min read · [leakbait.hashnode.dev](https://leakbait.hashnode.dev/we-built-a-prompt-injection-game-where-each-level-adds-one-real-defense?utm_source=hashnode&utm_medium=feed) [Learn Prompt with AI](https://hashnode.com/@learnpromptwithai) · [Nov 4](https://hashnode.com/posts/how-to-write-better-ai-prompts-the-4-part-framework-i-use-every-day/6aeaedaf15b883470f1f07b5) ### [How to Write Better AI Prompts: The 4-Part Framework I Use Every Day](https://learnpromptwithai.hashnode.dev/how-to-write-better-ai-prompts-the-4-part-framework-i-use-every-day?utm_source=hashnode&utm_medium=feed) Most bad AI output isn't the model's fault. It's the prompt's. When I started using AI tools for real work, my prompts looked like search queries: "write email about discount." The results were generi 2 min read · [learnpromptwithai.hashnode.dev](https://learnpromptwithai.hashnode.dev/how-to-write-better-ai-prompts-the-4-part-framework-i-use-every-day?utm_source=hashnode&utm_medium=feed) [Ignacio Di Rocco](https://hashnode.com/@idirocco) · [Nov 3](https://hashnode.com/posts/why-generic-synthetic-examples-fail-in-category-specific-scenarios/6aea14df5ea170c1ad922669) ### [Why Generic Synthetic Examples Fail in Category-Specific Scenarios](https://idirocco.hashnode.dev/why-generic-synthetic-examples-fail-in-category-specific-scenarios?utm_source=hashnode&utm_medium=feed) A targeted generator-prompt change, what 93.6% actually means, and lessons from AI Waiter 4 min read · [idirocco.hashnode.dev](https://idirocco.hashnode.dev/why-generic-synthetic-examples-fail-in-category-specific-scenarios?utm_source=hashnode&utm_medium=feed) [Promptclay](https://hashnode.com/@promptclay) · [Nov 2](https://hashnode.com/posts/treat-image-prompts-like-functions-slots-locks-and-defaults/6ae868609a47a45a1445761a) ### [Treat image prompts like functions: slots, locks and defaults](https://promptclay.hashnode.dev/treat-image-prompts-like-functions-slots-locks-and-defaults?utm_source=hashnode&utm_medium=feed) A small template system for Gemini and ChatGPT image prompts, built from five real ones 7 min read · [promptclay.hashnode.dev](https://promptclay.hashnode.dev/treat-image-prompts-like-functions-slots-locks-and-defaults?utm_source=hashnode&utm_medium=feed)