The Principle of Controlled Imagination

Give the spark and each fence its own tag - <spark>, <style>, <setting>, <protagonist>, <conflict>, <constraints> - which makes the brief legible and lets you change one fence without rewriting the paragraph it was buried in. Two things make this platform particularly good for constrained creative work: it will tell you when a constraint is damaging the piece rather than quietly delivering something worse, and Artifacts mean a draft you intend to revise lives in one editable place instead of being regenerated each time.

• One tag per fence - change one without rewriting the brief.
• Ask <where_the_fences_fought_me> and take the answer seriously.
• Put drafts you will revise in an Artifact.
• Ask for three openings before a full draft.
• Describe a style's qualities; do not name a living writer.

<spark>
A short fantasy story, 1,200 to 1,500 words.
</spark>

<style>
The lyrical, unhurried, affectionately observant register of R.K. Narayan: small details of ordinary life carrying the weight, gentle irony rather than grand drama. Not pastiche and not period diction - his attention to the small and the human, in contemporary prose.
</style>

<setting>
2025, in a hidden magical version of Malgudi. The magic is ordinary to the people who live there and is never explained to the reader.
</setting>

<protagonist>
A young woman who can speak with the old banyan trees. This is a fact of her life, not a discovery she makes during the story.
</protagonist>

<conflict>
A tech company plans a data centre on the site of the most sacred banyan, not knowing what it is. She has to stop them by combining old magic with modern persuasion - a public consultation, an environmental clearance, a WhatsApp group.
</conflict>

<ending>
Unresolved but hopeful. No last-minute rescue, no villain's change of heart.
</ending>

<do_not>
- No tradition-versus-modernity sermon. The tech workers are not villains; most would be on her side if anyone had asked.
- No explained magic system, no chosen one, no prophecy.
- Do not resolve it with the trees doing something supernatural and decisive. She wins or loses on human ground, with the trees as the reason rather than the weapon.
</do_not>

<how_to_work>
First, three openings of about 300 words each - three different first scenes against the same fences. Label them A, B and C, each with one line on what it is attempting. I will choose one and you will write it in full in an Artifact, which is where I will edit it.

Then <where_the_fences_fought_me>: be straight with me. The ending I have specified may not be available from the plot I have specified - a data centre either gets built or it does not, and "unresolved but hopeful" may be me avoiding a decision rather than making one. If a fence is making the story worse, name it and tell me what you would change it to. I would rather loosen a constraint than read a story contorted around it.
</how_to_work>

<spark>
A concept for a mobile application.
</spark>

<target_user>
Elderly residents of large apartment complexes in Indian metros - Hyderabad, Bengaluru. Many living alone or as a couple, with children in another city or abroad.
</target_user>

<problem>
Isolation, and difficulty managing daily errands.
</problem>

<core_functionality>
- A community bulletin board.
- A trusted way to order groceries and medicine.
- A simple way to organise social gatherings inside the complex.
</core_functionality>

<interface_constraints>
Very large type. Very few choices per screen. Voice input throughout. Assume the user has never installed an app themselves and will not create or remember a password.
</interface_constraints>

<context_constraint>
It must work alongside the complex's existing WhatsApp group and RWA, not replace them. Any concept requiring everyone to leave WhatsApp is dead on arrival - the WhatsApp group is the real competitor here and it is free, already installed, and already used.
</context_constraint>

<required_output>
<concept> - one paragraph: what it is, and the one thing it does better than the status quo.

<three_screens> - the three core screens in detail: what is on each, what a 72-year-old's thumb actually does, what happens on a mis-tap.

<trust_mechanism> - "trusted service for medicine" is the hard part and the part every concept hand-waves. Who verifies the vendor, who owns a wrong delivery, who is accountable when a prescription is filled incorrectly. Be concrete.

<two_users> - realistically the app is installed by the son or daughter in another city. That means two users with different needs and different screens. Work this through rather than noting it.
</required_output>

<then_be_honest>
<week_three> - why would anyone still be using this in week three? Most community apps are installed and abandoned. I want the real answer, not a feature.

<the_case_against> - if the right answer is a better-run WhatsApp group and three vetted shops pinned to the noticeboard, say so and tell me what the app adds. I would rather hear that now than after six months of building.

<what_is_condescending> - my brief assumes a lot about what elderly people can and cannot do. Tell me which of my constraints is patronising rather than accessible. Voice-only input because someone is over seventy is a design decision I should have to defend.
</then_be_honest>

<no_invented_numbers>
No market sizes or adoption rates. If a figure makes something legible, mark it illustrative.
</no_invented_numbers>

<spark>
Three variations of ad copy for a new noise-cancelling headphone brand called Silence.
</spark>

<audience>
Frequent business travellers on long-haul flights. People for whom the flight is either working time or the only rest they will get that week.
</audience>

<tone>
Sophisticated, calm, focused on serenity and escape. The writing itself should be quiet - it should sound like the product.
</tone>

<key_benefit>
A private sanctuary of peace in the middle of travel's chaos.
</key_benefit>

<call_to_action>
"Rediscover your focus. Find your Silence." - exactly this, unchanged, closing each variation.
</call_to_action>

<length_constraint>
Each variation under 280 characters including the call to action. Count and show the count.
</length_constraint>

<three_distinct_angles>
This is the instruction that matters most - three angles, not three rewrites:
1. A specific moment: one concrete instant on a flight when the noise stops.
2. What the silence is for: the work done or the sleep taken, not the quiet itself.
3. Contrast: the cabin as it is against the cabin as it becomes.

If all three read as variations of one sentence, the output has failed.
</three_distinct_angles>

<banned>
- The words journey, immerse, immersive, elevate, experience, crystal-clear, game-changer, premium.
- No specifications - no decibels, driver sizes or battery hours. This is mood copy.
- No crying baby. It is the first image everyone reaches for and it makes the brand sound petty.
</banned>

<after_the_copy>
<counts> - character count for each.

<angle_check> - one line per variation naming which angle it took, so I can see they genuinely differ.

<the_name_problem> - "Find your Silence" works in English. How do the name and that line read to someone whose first language is Telugu, Hindi or Tamil? Does the possessive construction survive? Most of this audience flies out of Indian metros and I need to know if the line only works for some of them.

<the_one_to_run> - which you would run and why. And if you think all three are weaker than a plain statement of what the product does, say that instead of choosing a favourite. A calm brand can afford plainness, and the fences I set may be pushing the copy toward atmosphere when it should be making a claim.
</after_the_copy>