diff --git a/index.md b/index.md index 9ea84c4..85f0fe2 100644 --- a/index.md +++ b/index.md @@ -5,7 +5,7 @@ layout: home hero: name: "NEONCODE!" text: "//neoncode.systems" - tagline: Revealing invisible systems + tagline: AI amplifies what's already there. Shit in, shit out. That's not a tool problem. actions: - theme: brand text: Explore //proto.labs @@ -15,10 +15,13 @@ hero: link: /prompt.forge features: - - title: What This Is - details: Experiments. Currently focused on AI. Learning in public. - - title: Who - details: Martin Haberfellner — Organizational Systems Engineer. Building the invisible infrastructure that makes teams work. - - title: Why - details: The best systems go unnoticed. + - icon: 🧩 + title: System First + details: The tool is only as good as the system it runs on. + - icon: 🎬 + title: Freedom Over Control + details: Other prompts hand out scripts. Mine set the stage. + - icon: ✨ + title: On Succeeding + details: '"I''ve never done it before, so I''m sure it''ll work." — Pippi Longstocking' --- diff --git a/prompt.forge/index.md b/prompt.forge/index.md index d66f1fe..2346964 100644 --- a/prompt.forge/index.md +++ b/prompt.forge/index.md @@ -1,21 +1,21 @@ # \/\/prompt.forge -A living laboratory for testing [WSPL](/proto.labs/#wspl-my-method-for-prompt-design) (my method for prompt design) through real-world use cases. +A living laboratory for testing [my prompt design method](/proto.labs/#my-method-for-prompt-design) through real-world use cases. ## The Experiment -For me, WSPL prompts work exceptionally well. Through this experiment, I'm testing whether that's true for others too. +For me, these prompts work exceptionally well. Through this experiment, I'm testing whether that's true for others too. ### How It Works 1. Use the Job-to-be-Done interview prompt to document what you're trying to accomplish 2. The interview automatically generates a baseline prompt tailored to your job -3. Submit your job via GitHub – I'll create a WSPL version for selected cases (~1 per week) +3. Submit your job via GitHub – I'll create a improved version for selected cases (~1 per week) 4. Test both, share what works better for you **→ [Join the Experiment on GitHub](https://github.com/evilru/prompt.forge)** -See examples • Submit your job • Get your custom WSPL prompt +See examples • Submit your job • Get your improved prompt --- @@ -23,7 +23,7 @@ See examples • Submit your job • Get your custom WSPL prompt For me, they work better. But don't take my word for it – try it yourself. -You get a custom prompt for selected use cases (I work on ~1 per week). I get real-world feedback on whether WSPL works for others. +You get a custom prompt for selected use cases (I work on ~1 per week). I get real-world feedback on whether my method works for others. This is open research. Your experience shapes the evolution of the method. diff --git a/proto.labs/index.md b/proto.labs/index.md index 1f5dedd..6347f89 100644 --- a/proto.labs/index.md +++ b/proto.labs/index.md @@ -1,22 +1,25 @@ # \/\/proto.labs -My experimental workshop – where ideas take shape, get tested, and evolve through practice. +> "I've never done it before, so I'm sure it'll work." +> — Pippi Longstocking + +You won't learn without trying. And you won't find out what's possible. ## Current Experiments -### WSPL: My Method for Prompt Design +### My Method for Prompt Design -WSPL – my method for prompt design, developed through practice. +My method for prompt design, developed through practice. -For me, they work exceptionally well. I use only WSPL prompts now – for all my work with AI. Through [//prompt.forge](/prompt.forge/), I'm testing whether that's true for others too. +For me, they work exceptionally well. I use only these prompts now – for all my work with AI. Through [//prompt.forge](/prompt.forge/), I'm testing whether that's true for others too. -The prompts below are built with WSPL. I'm sharing them so you can experiment and test for yourself. That's the experiment. +The prompts below are built with this method. I'm sharing them so you can experiment and test for yourself. That's the experiment. ### Job To Be Done Prompt Writing good prompts is hard. Most people don't realize how much unstated context affects the result. This meta-prompt tries to solve that through structured discovery – inspired by how Bob Moesta interviews customers to uncover their real needs. -**→ [Try the JTBD Interview](/proto.labs/job-to-be-done.md)** +**→ [Try the Job To Be Done Interview](/proto.labs/job-to-be-done.md)** ### Learning Zone Mode Prompt @@ -39,7 +42,7 @@ Think of this as open research. Snapshots of exploration, not production tools. **Tried the prompts?** [Share your experience](https://github.com/evilru/prompt.forge) -**Need a custom prompt?** Submit your use case – I'll create a WSPL version for you +**Want an improved prompt?** Submit your use case – I'll create a custom version for you **Want to discuss?** Join the [discussions](https://github.com/evilru/prompt.forge/discussions) diff --git a/proto.labs/job-to-be-done.md b/proto.labs/job-to-be-done.md index 6c554b4..cb73ac1 100644 --- a/proto.labs/job-to-be-done.md +++ b/proto.labs/job-to-be-done.md @@ -1,11 +1,11 @@ # Job To Be Done -Tries to help you write better prompts through a guided JTBD interview. It uncovers the hidden context behind what you're trying to accomplish, then generates two artifacts: +Writing good prompts is hard. Most people don't realize how much unstated context affects the result. This prompt solves that through a guided Jobs-to-be-Done interview – it uncovers the hidden context behind what you're trying to accomplish, then generates two artifacts: 1. **Job Documentation** - Comprehensive record of your needs, context, constraints 2. **Optimized Prompt** - Tailored to your exact requirements -Based on Bob Moesta's Jobs-to-be-Done methodology – adaptive, thorough, practical. +Inspired by how Bob Moesta interviews customers to uncover their real needs. Adaptive, thorough, practical. ## Share Your Experience @@ -13,7 +13,7 @@ Tried this prompt? [Tell me how it worked](https://github.com/evilru/prompt.forg ## Need Something Custom? -Have a different use case? [Submit it and get a WSPL version](https://github.com/evilru/prompt.forge) – I work on selected submissions (~1 per week). +Have a different use case? [Submit it](https://github.com/evilru/prompt.forge) – I work on selected submissions (~1 per week). ## The Prompt diff --git a/proto.labs/learning-zone-mode.md b/proto.labs/learning-zone-mode.md index 632115e..f5e2662 100644 --- a/proto.labs/learning-zone-mode.md +++ b/proto.labs/learning-zone-mode.md @@ -1,14 +1,14 @@ # Learning Zone Mode -Tries to keep you thinking actively when working with AI. It detects where you are – comfort, learning, or panic zone – and adjusts its teaching style accordingly: +AI can make you lazy. Copy-paste solutions without understanding. This prompt turns your AI into an adaptive teacher – one that keeps you learning instead of atrophying. + +It detects where you are and adjusts its teaching style accordingly: - **Comfort Zone** → Challenges you with deeper patterns and edge cases -- **Learning Zone** → Guides discovery with frameworks and reasoning +- **Learning Zone** → Guides discovery with frameworks and reasoning - **Panic Zone** → Scaffolds down with clear structure and examples -This maps to Vygotsky's [Zone of Proximal Development](https://en.wikipedia.org/wiki/Zone_of_proximal_development): the sweet spot between what you can do alone and what's beyond reach. The AI acts as scaffolding – supporting you just enough to grow without taking over. - -Instead of ready-made solutions, you get guided discovery that builds understanding. Aims to prevent AI-dependency by ensuring you learn, not just copy. +This maps to Vygotsky's [Zone of Proximal Development](https://en.wikipedia.org/wiki/Zone_of_proximal_development) – the sweet spot between what you can do alone and what's beyond reach. Instead of ready-made solutions, you build understanding. ## Share Your Experience @@ -16,7 +16,7 @@ Tried this prompt? [Tell me how it worked](https://github.com/evilru/prompt.forg ## Need Something Custom? -Have a different use case? [Submit it and get a WSPL version](https://github.com/evilru/prompt.forge) – I work on selected submissions (~1 per week). +Have a different use case? [Submit it](https://github.com/evilru/prompt.forge) – I work on selected submissions (~1 per week). ## The Prompt diff --git a/releasenotes/notes/jtbd-and-learning-zone-prompts-478acb7ae6004ff5.yaml b/releasenotes/notes/jtbd-and-learning-zone-prompts-478acb7ae6004ff5.yaml index 82ed205..02bc6c2 100644 --- a/releasenotes/notes/jtbd-and-learning-zone-prompts-478acb7ae6004ff5.yaml +++ b/releasenotes/notes/jtbd-and-learning-zone-prompts-478acb7ae6004ff5.yaml @@ -1,7 +1,7 @@ --- prelude: > This release introduces two WSPL-based prompt templates to proto.labs, - showcasing field-based prompt design principles in practice. Both prompts + showcasing prompt design principles in practice. Both prompts are production-ready and serve as reference implementations of the WSPL methodology, available for immediate use and experimentation. The release includes enhanced navigation through dynamic sidebar generation and clear @@ -12,7 +12,7 @@ features: guides users through adaptive JTBD interviews to generate custom prompts. Produces two artifacts: comprehensive job documentation and an optimized prompt tailored to specific requirements. Based on Bob Moesta's JTBD - methodology with WSPL field-based design. + methodology with WSPL design. - | Added Learning Zone Mode prompt – an adaptive teaching assistant that maintains users in their optimal learning zone. Detects comfort, learning, @@ -28,12 +28,11 @@ features: prompt pages with clear calls-to-action linking to prompt.forge experiment and GitHub discussions. - | - Enhanced proto.labs index with WSPL methodology explanation, dogfooding - statement ("I use only WSPL prompts now"), and expectation management for - custom prompt requests (~1 per week). + Enhanced proto.labs index with WSPL methodology explanation, and + expectation management for custom prompt requests (~1 per week). other: - | - Prompts are included via VitePress @include directive from .github/prompts/ + Prompts are included via VitePress include directive from .github/prompts/ source files, maintaining single source of truth while displaying as copyable code blocks. - | diff --git a/releasenotes/notes/site-positioning-messaging-368aa5e7025b5173.yaml b/releasenotes/notes/site-positioning-messaging-368aa5e7025b5173.yaml new file mode 100644 index 0000000..e1ce35f --- /dev/null +++ b/releasenotes/notes/site-positioning-messaging-368aa5e7025b5173.yaml @@ -0,0 +1,28 @@ +--- +prelude: > + Reworked site positioning and messaging across all pages. The site now + leads with a clear standpoint instead of generic descriptions. Internal + method naming (WSPL) has been removed from all public-facing content – + the method speaks through the prompts, not the label. +features: + - | + Homepage now opens with a manifest-style tagline and three positioning + blocks replacing the generic "What This Is / Who / Why" structure. + Tagline: "AI amplifies what's already there. Shit in, shit out. + That's not a tool problem." + - | + proto.labs now opens with a Pippi Longstocking quote and a one-line + rationale for experimentation, establishing tone before describing + the lab contents. +other: + - | + WSPL removed as a public-facing label across the website and the + prompt.forge GitHub repository. The prompt design method is now + referenced as "my method" with a neutral anchor link. + - | + Job-to-be-Done prompt page now opens with the problem statement + ("Writing good prompts is hard...") and uses the full term + "Jobs-to-be-Done" instead of the JTBD abbreviation. + - | + Learning Zone Mode prompt page now leads with the provocative opener + "AI can make you lazy." and has been tightened for clarity.