A cast with scripts performs. Characters with depth find the play.
Submit a real use case. Get a prompt built with Behaviour Priming.
+Submit a use case. I'll build a prompt with Behaviour Priming. You test both — you decide.
+Emerges from instructions
Noisy — every word is potential interference
Unstable under unexpected input
-Drift = more instructions
+More rules. More problems.
Designed field
Built from values and principles
Dense — every word earns its place
Stable — handles what you didn't anticipate
-Drift disappears
+No more duct tape.
The difference is not whether a field exists. It's whether it was designed or happened by accident. Designed fields hold. Accidental fields eventually break.
@@ -116,8 +136,9 @@ hero:This is not a framework. It's not a methodology to adopt. It's a shift in how you see the thing. Once you see it, the prompts write themselves differently. The results hold differently. The drift disappears.
- +This is not a framework. It's not a methodology to adopt. It's a shift in how you see the thing. Once you see it, the prompts write themselves differently. The results hold differently. The prompt became stable.
+The method exists. It has a name.
+There are moments in life when you feel like Don Quijote. And sometimes, you just feel heard.
+By the way.
If you ever need a votable Quake 3 server or a working stats tool — strikenet.com has been running since 1999. I bought the domain from my first employer when I left. The server still runs. The stats tool is dockerized and occasionally gets a fix. Some things are worth keeping alive.
diff --git a/prompt.forge/index.md b/prompt.forge/index.md index 8756d17..1622a09 100644 --- a/prompt.forge/index.md +++ b/prompt.forge/index.md @@ -1,10 +1,29 @@ --- layout: home +title: "//prompt.forge — NEONCODE!" +head: + - - meta + - name: description + content: "Submit a prompt use case — get a Behaviour Priming compiled version back. Test both, vote on what works better. Open research into prompt architecture." + - - meta + - name: keywords + content: "prompt forge, behaviour priming test, prompt comparison, compiled prompt, prompt architecture experiment, LLM prompt quality" + - - meta + - property: og:title + content: "//prompt.forge — neoncode.systems" + - - meta + - property: og:description + content: "The live test. Behaviour Priming — does it work for you? Submit a use case. Test both. You decide." + - - meta + - name: twitter:title + content: "//prompt.forge — neoncode.systems" + - - meta + - name: twitter:description + content: "The live test for Behaviour Priming. Submit a use case. Test both. You decide." hero: - name: "//prompt.forge" text: "Send me your prompt. I'll rebuild it." - tagline: I want to know if Behaviour Priming works for you the way it works for me. You test both. You decide. + tagline: You test both. You decide. actions: - theme: brand text: Join the Experiment @@ -16,7 +35,7 @@ hero: ## The Experiment -**[Behaviour Priming](/)** works for me. Through this experiment, I'm testing whether that's true for others too. +This is the live test. Behaviour Priming — does it work for you? ### How It Works diff --git a/proto.labs/index.md b/proto.labs/index.md index 0695f15..9cfdcd3 100644 --- a/proto.labs/index.md +++ b/proto.labs/index.md @@ -1,8 +1,27 @@ --- layout: home +title: "//proto.labs — NEONCODE!" +head: + - - meta + - name: description + content: "Experiments built on Behaviour Priming: a Jobs-to-be-Done interview prompt and a Learning Zone Mode for adaptive AI teaching. Try them, break them, share what works." + - - meta + - name: keywords + content: "behaviour priming prompts, Jobs-to-be-Done prompt, learning zone mode, AI teaching prompt, prompt experiments, jobs to be done" + - - meta + - property: og:title + content: "//proto.labs — neoncode.systems" + - - meta + - property: og:description + content: "Experiments built on Behaviour Priming. Take what's useful. Break what isn't." + - - meta + - name: twitter:title + content: "//proto.labs — neoncode.systems" + - - meta + - name: twitter:description + content: "Experiments built on Behaviour Priming. Running right now." hero: - name: "//proto.labs" text: '"I''ve never done it before, so I''m sure it''ll work."' tagline: You won't learn without trying. And you won't find out what's possible. actions: @@ -13,9 +32,7 @@ hero: ## Current Experiments {#experiments} -Built on **[Behaviour Priming](/behaviour.priming/)** — the method described in the [manifest](/). Some of these are polished enough to use. Some are still rough. All of them are real. - -Take what's useful. Break what isn't. +Built on **[Behaviour Priming](/behaviour.priming/)** — the method described in the [manifest](/). This is what's running right now. Take what's useful. Break what isn't. ### Job To Be Done Prompt diff --git a/proto.labs/job-to-be-done.md b/proto.labs/job-to-be-done.md index af111a3..7097e6c 100644 --- a/proto.labs/job-to-be-done.md +++ b/proto.labs/job-to-be-done.md @@ -1,5 +1,22 @@ --- layout: home +title: "Job To Be Done Prompt — //proto.labs — NEONCODE!" +head: + - - meta + - name: description + content: "A guided Jobs-to-be-Done interview prompt that uncovers the hidden context behind what you're trying to accomplish — then generates job documentation and an optimised prompt. Built on Behaviour Priming." + - - meta + - property: og:title + content: "Job To Be Done Prompt — NEONCODE!" + - - meta + - property: og:description + content: "You don't know how much context you're missing until something asks you for it. A Jobs-to-be-Done interview prompt built on Behaviour Priming." + - - meta + - name: twitter:title + content: "Job To Be Done Prompt — NEONCODE!" + - - meta + - name: twitter:description + content: "You don't know how much context you're missing until something asks you for it." hero: name: "Job To Be Done" @@ -28,7 +45,7 @@ Tried this prompt? [Tell me how it worked](https://github.com/evilru/prompt.forg ## The Prompt ::: tip Copy this prompt -Copy the prompt below and use it with your AI assistant to start a guided JTBD interview. +Copy the prompt below and use it with your AI assistant to start a guided Jobs-to-be-Done interview. ::: ````markdown diff --git a/proto.labs/learning-zone-mode.md b/proto.labs/learning-zone-mode.md index 6f7845c..8b7999a 100644 --- a/proto.labs/learning-zone-mode.md +++ b/proto.labs/learning-zone-mode.md @@ -1,5 +1,22 @@ --- layout: home +title: "Learning Zone Mode — //proto.labs — NEONCODE!" +head: + - - meta + - name: description + content: "An adaptive teaching prompt that keeps you learning instead of atrophying. Detects your zone — comfort, learning, or panic — and adjusts accordingly. Built on Behaviour Priming." + - - meta + - property: og:title + content: "Learning Zone Mode — NEONCODE!" + - - meta + - property: og:description + content: "AI can make you lazy. What if it asked instead of answered? An adaptive teaching prompt built on Behaviour Priming." + - - meta + - name: twitter:title + content: "Learning Zone Mode — NEONCODE!" + - - meta + - name: twitter:description + content: "AI can make you lazy. What if it asked instead of answered?" hero: name: "Learning Zone"