--- title: "#prompting articles | Hashnode" description: "Explore 90 articles tagged #prompting on Hashnode. Tutorials, guides, and how-tos from the community." url: "https://hashnode.com/tag/prompting" --- Tag # #prompting 90 posts · 3 followers [Callirra](https://hashnode.com/@callirra) · [Nov 1](https://hashnode.com/posts/h3-six-style-presets/6ae6f5d19a8319eb549fe419) ### [Six style presets, one prompt: what drama staging and action staging actually change in MiniMax H3](https://callirra.hashnode.dev/h3-six-style-presets?utm_source=hashnode&utm_medium=feed) The preset values are named after production categories most developers have never met. Here is what each one does, and how to pick 5 min read · [callirra.hashnode.dev](https://callirra.hashnode.dev/h3-six-style-presets?utm_source=hashnode&utm_medium=feed) [1](https://hashnode.com/posts/h3-six-style-presets/6ae6f5d19a8319eb549fe419) [Powerduck](https://hashnode.com/@powerduck) · [Oct 25](https://hashnode.com/posts/agent-keeps-honoring-rejected-approach-in-context/6ade2eaab5d5026e40f48aac) ### [The agent kept implementing the approach we already rejected because it never left the context window](https://blogs.powerduck.com/agent-keeps-honoring-rejected-approach-in-context?utm_source=hashnode&utm_medium=feed) We told the agent to drop the in-memory cache and read from source each time. The draft still shipped an eviction helper, a routing layer, and a cache-miss test nobody requested. A redirect removes the idea from the plan but not the window, so explored options keep acting as active requirements. 4 min read · [blogs.powerduck.com](https://blogs.powerduck.com/agent-keeps-honoring-rejected-approach-in-context?utm_source=hashnode&utm_medium=feed) [1](https://hashnode.com/posts/agent-keeps-honoring-rejected-approach-in-context/6ade2eaab5d5026e40f48aac) [Henry Jin](https://hashnode.com/@videoall) · [Oct 12](https://hashnode.com/posts/deconstructing-a-gpt-image-2-5-reference-led-restyle-prompt-clause-by-clause/6acc6046ca94148640c7dd5a) ### [Deconstructing a GPT Image 2.5 Reference-Led Restyle Prompt, Clause by Clause](https://videoall.hashnode.dev/deconstructing-a-gpt-image-2-5-reference-led-restyle-prompt-clause-by-clause?utm_source=hashnode&utm_medium=feed) Reference-led editing is the workflow where a model takes an uploaded image as a reference and regenerates it with changes described in a prompt. The hard part of writing the prompt is that it has to 5 min read · [videoall.hashnode.dev](https://videoall.hashnode.dev/deconstructing-a-gpt-image-2-5-reference-led-restyle-prompt-clause-by-clause?utm_source=hashnode&utm_medium=feed) [Ranita Dey](https://hashnode.com/@ranita) · [Jul 27](https://hashnode.com/posts/prompt-engineering-beyond-the-basics-what-actually-breaks-in-production/6a673c9de19c8c100cb7b8a6) ### [Prompt Engineering Beyond the Basics: What Actually Breaks in Production](https://techrevolution.hashnode.dev/prompt-engineering-beyond-the-basics-what-actually-breaks-in-production?utm_source=hashnode&utm_medium=feed) Learn why prompt engineering fails in production and how to build reliable, scalable AI systems with proven engineering practices. 10 min read · [techrevolution.hashnode.dev](https://techrevolution.hashnode.dev/prompt-engineering-beyond-the-basics-what-actually-breaks-in-production?utm_source=hashnode&utm_medium=feed) [Himanshu Balani](https://hashnode.com/@himanshubalani) · [Jul 16](https://hashnode.com/posts/prompting-101-guide/6a590c6172d6995298d63826) ### [Prompting 101: How Prompts Shape LLM Output + Safety Tips](https://blog.himanshubalani.com/prompting-101-guide?utm_source=hashnode&utm_medium=feed) Master prompt engineering with this Prompting guide. Learn core prompting styles, AI safety, and how to defend LLMs against prompt injection attacks. 9 min read · [blog.himanshubalani.com](https://blog.himanshubalani.com/prompting-101-guide?utm_source=hashnode&utm_medium=feed) [Alan Gornick](https://hashnode.com/@alangornick) · [May 31](https://hashnode.com/posts/schema-shot-prompting-guide/6a1c9fbaf7a2eb87f53a8b6d) ### [Free Your LLM to Pursue Goals, Not Follow Rules](https://blog.ag3-design.com/schema-shot-prompting-guide?utm_source=hashnode&utm_medium=feed) How to choreograph LLM behavior with schema-shot prompts 11 min read · [blog.ag3-design.com](https://blog.ag3-design.com/schema-shot-prompting-guide?utm_source=hashnode&utm_medium=feed) [3](https://hashnode.com/posts/schema-shot-prompting-guide/6a1c9fbaf7a2eb87f53a8b6d) [Alan Gornick](https://hashnode.com/@alangornick) · [May 25](https://hashnode.com/posts/show-dont-tell/6a13c9cf551486ce6c520cd3) ### [Show, Don't Tell: Shot-Focused and Schema-Shot Prompting](https://blog.ag3-design.com/show-dont-tell?utm_source=hashnode&utm_medium=feed) How small local models taught me to write durable, compact prompts 17 min read · [blog.ag3-design.com](https://blog.ag3-design.com/show-dont-tell?utm_source=hashnode&utm_medium=feed) [1](https://hashnode.com/posts/show-dont-tell/6a13c9cf551486ce6c520cd3) [Vamsi Krishna](https://hashnode.com/@vamsikrishna981) · [May 24](https://hashnode.com/posts/day-04-why-more-context-can-make-an-ai-system-worse/6a3e39be6ef767ce14c3bc67) ### [Day 04: Why more context can make an AI system worse](https://blog.vamsiannamreddy.com/day-04-why-more-context-can-make-an-ai-system-worse?utm_source=hashnode&utm_medium=feed) Why a larger context window does not remove the need for context discipline. 3 min read · [blog.vamsiannamreddy.com](https://blog.vamsiannamreddy.com/day-04-why-more-context-can-make-an-ai-system-worse?utm_source=hashnode&utm_medium=feed) [Vamsi Krishna](https://hashnode.com/@vamsikrishna981) · [May 23](https://hashnode.com/posts/day-02-why-llms-feel-intelligent-but-still-generate-one-step-at-a-time/6a3e2de66d4665187d556187) ### [Day 02: Why LLMs feel intelligent but still generate one step at a time](https://blog.vamsiannamreddy.com/day-02-why-llms-feel-intelligent-but-still-generate-one-step-at-a-time?utm_source=hashnode&utm_medium=feed) The practical reason LLM behavior needs constraints, validation, and repeatable output design. 3 min read · [blog.vamsiannamreddy.com](https://blog.vamsiannamreddy.com/day-02-why-llms-feel-intelligent-but-still-generate-one-step-at-a-time?utm_source=hashnode&utm_medium=feed) [Quokka Labs](https://hashnode.com/@quokkalabs) · [May 4](https://hashnode.com/posts/why-prompt-injection-is-also-a-data-security-problem/69f8741246610fd606c63ab8) ### [Why Prompt Injection Is ALSO a Data Security Problem](https://quokkalabs.hashnode.dev/why-prompt-injection-is-also-a-data-security-problem?utm_source=hashnode&utm_medium=feed) Learn why prompt injection is more than a glitch—it's a critical data security risk leading to leaks, exfiltration, and unauthorized access. 3 min read · [quokkalabs.hashnode.dev](https://quokkalabs.hashnode.dev/why-prompt-injection-is-also-a-data-security-problem?utm_source=hashnode&utm_medium=feed)