Most “problem / solution” articles assume the reader already has the problem and rush to the product. The ones that convert make the reader name their own symptom first, then earn the right to suggest a path. That sequence has a name in copywriting: PAS — Problem, Agitate, Solution (reference). The 12 prompts below bake PAS (and its extension, PASTOR: Problem, Amplify, Solution, Transformation, Offer, Response) into reusable templates you can run through any current model.
TL;DR
- Lead with the reader’s symptom, not your solution. Diagnose before you treat.
- Every prompt below carries six elements: audience, goal, voice, constraints, format, examples. Skip one and the output goes generic.
- For draft quality, route the work: Claude Sonnet 4.6 / Opus 4.7 for prose and voice fidelity, GPT-5.5 for outlining and repurposing, Gemini 3.1 Pro for context-rich expansion (all current as of June 2026).
- Use AI for drafts 1-2; a human owns draft 3, and draft 3 is what ships.
Who this is for
Content marketers building trust before a pitch, founders writing about their problem space, and SEO writers ranking on problem-stage queries (“why is my X failing”, not “buy X”).
When not to use these prompts
Skip them for product-led pages that only need to demo a feature. Skip them when the “solution” is too narrow to actually serve the problem you stated — readers feel the bait-and-switch and bounce.
Which model to run these on (June 2026)
The templates are model-agnostic, but draft quality varies by task. Pick by job, not brand loyalty.
| Task | Best pick | Why |
|---|---|---|
| Nuanced prose, voice match | Claude Sonnet 4.6 / Opus 4.7 | Strongest tone consistency; 1M-token context for long source dumps |
| Outlines, rewrites, repurposing | GPT-5.5 | Fast, versatile across formats; default in ChatGPT since ~Apr 2026 |
| Expanding a rough idea with industry context | Gemini 3.1 Pro | Pulls in surrounding context well; 1M context, cheapest tokens (2/12 per 1M) |
Pricing for reference (June 2026): ChatGPT Plus $20/mo, Claude Pro $20/mo ($17 annual), Google AI Pro $19.99/mo. Any one tier is enough to run all 12 prompts. See our ChatGPT vs Claude vs Gemini comparison and Claude vs ChatGPT for long documents for the full breakdown.
Prompt anatomy / structure formula
Every problem-solution prompt should carry six elements:
- Audience: one specific reader, not “marketers”.
- Goal: one outcome — read / click / agree / share.
- Voice: 2-3 anchor adjectives (“plain, direct, a little dry”).
- Constraints: word count, banned phrases, must-include facts.
- Format: paragraph, bulleted, headed, or table.
- Examples: 1-2 tone samples — the single strongest lever for matching voice.
Best for
- Search-stage problem-solution articles
- SEO long-tail problem queries
- Sales enablement long-form
- Inbound funnel content
- Diagnostic / framework pieces
12 copy-ready prompt templates
Use [problem], [persona], and [symptom] as placeholders — swap them before you run.
1. Problem-first skeleton
Topic: [problem]. Audience: [persona]. Write a PAS-shaped outline:
(1) Hook — recognise the reader's symptom, (2) Diagnose the underlying
problem, (3) Why common solutions fail, (4) A better framework,
(5) Worked example, (6) When to apply / not.Variables to swap: problem, persona
2. Symptom recognition opener
Write a 100-word opener that names 3 specific symptoms readers experience.
Use second person ("You've noticed..."). Make them feel seen, but don't
flatter. Skip "we all know that...".3. Why common solutions fail
List 3 common solutions to [problem] and why each falls short. Don't
straw-man — pick real solutions readers may already have tried. For each:
when it works, where it breaks, and the missing piece that causes the break.Variables to swap: problem
4. Diagnose vs treat framing
Many readers want to fix [symptom]. Distinguish diagnose (what's actually
happening) from treat (the action). Write a 200-word section on why treating
the symptom without diagnosis fails — with one specific anti-pattern.Variables to swap: symptom
5. Framework introduction
Introduce a 3-4 step framework for [problem]. Each step: (a) name with a
verb, (b) what to do, (c) the success signal. Don't force an acronym —
forced acronyms cheapen the framework.Variables to swap: problem
6. Worked example
Apply the framework to a concrete example. Use real names if you can, or
invent specific details (50-person B2B SaaS, churn at 7%). Walk through each
step, show what changes, and name the win condition.7. Anti-pattern callout box
Insert a "What's NOT this framework" callout. 3 things readers commonly do
that LOOK like the framework but miss the point. Each: 1-line action +
1-line consequence.8. Edge cases / scope limits
Add a "when this won't work" section. Name 3 cases where the framework
fails: too small, too large, wrong industry, or a regulatory boundary.
Confidence over hedging.9. CTA without sales-iness
End with a CTA that respects the trust earned. Three variants: (a) further
reading, (b) one specific next action they can take without us, (c) optional
product CTA framed as "if you want, we can do X for you". Don't pitch first.10. Counter-thesis section
Some experts disagree with this approach. Add 150 words steel-manning the
strongest counter-argument. Acknowledge cases where the counter-thesis is
correct. Tone: confident, not defensive.11. Problem-solution headline test
Write 5 headlines for this problem-solution article. Variety: (a)
symptom-led, (b) framework-named, (c) question, (d) outcome, (e) contrarian.
Skip "The ultimate guide...".12. Trust-erosion audit
Audit my problem-solution article: (1) Where does it pitch too early?
(2) Where does it assume the reader has the problem instead of helping them
check? (3) Where do anti-patterns get straw-manned? (4) Does the framework
actually do what the headline claims?Common mistakes
- Vague audience — output reads generic for everyone, useful to no one.
- No tone anchor — every variant comes back the same safe flavour.
- No constraints — without a word cap and banned phrases, models pad.
- Skipping examples — 1-2 samples beat any adjective for voice match.
- Trusting the first draft — models land on the safe middle; push for draft 2.
- AI clichés left in — “in today’s fast-paced world”, “delve”, “unlock”. Cut them.
- No fact-check pass — models are confidently wrong sometimes; verify claims.
How to push results further
- Give 1-2 tone examples. “Be friendly” is noise; a sample paragraph is signal.
- Constrain ruthlessly: word count, banned phrases, must-include facts.
- Read the draft aloud before publishing — clunky sentences surface fast.
- Cut adverbs and adjectives that don’t carry weight.
- Anchor the prompt in one real person from your audience, named.
- Test the headline standalone, out of context, before you commit to it.
FAQ
- How long should the piece be?: Match the channel and the query intent — a problem-stage SEO post often runs 1,200-2,000 words; a sales-enablement piece can be shorter. Length follows the question, not a target.
- Which model writes the best problem-solution draft?: For prose and voice, Claude Sonnet 4.6 or Opus 4.7; for fast outlines and repurposing, GPT-5.5; for context-rich expansion, Gemini 3.1 Pro (all June 2026).
- Can AI write the whole draft?: Use it for the first two passes; a human owns the third, and the third is what ships. Editorial judgment is the part that earns trust.
- PAS or PASTOR — which framework?: PAS (Problem-Agitate-Solution) is enough for most articles. Use PASTOR when you need the extra Transformation and Offer steps, typically closer to a sale.
- How often should I refresh it?: When the audience or the claims change, or quarterly for evergreen content. Time-sensitive figures (pricing, model versions) need a check each refresh.
- Should I publish without an edit pass?: No. AI is confident, not always correct, and the trust you build in the problem section evaporates at the first wrong fact.
Related
- Blog outline prompts
- Case study prompts
- Article rewrite prompts
- Brand story prompts
- Writing & Copywriting Prompts hub
Tags: #Prompt #Writing #Problem-solution