Skip to main content

Claude/ChatGPT Prompt to Draft a Go-To-Market Plan for a New Feature

Generate a structured SaaS GTM plan: ICP, persona messaging, activation path, pricing options, launch mechanics, and 30-60-90 day metrics.

Fill in the placeholders

Edit the values, then copy your finished prompt.

Your Prompt
prompt.txt

                                

What this prompt does

This prompt assigns the AI a senior B2B SaaS product marketer role and makes it draft a go-to-market plan tight enough to execute the following week. You provide the [feature_name], [product_name], [primary_persona], and [pricing_model]. It returns an ideal customer profile, three message variants tuned to the persona and adjacent buyers, an activation path with the aha moment named, pricing-impact options, launch mechanics across channels with owners, and a 30-60-90 day metric plan — all in under 800 words.

The structure works because it ties the launch to what actually shipped. By grounding the activation path in [feature_name] and naming the aha moment, the prompt keeps the messaging honest rather than aspirational. [primary_persona] aims the three message variants at the right buyer, and [pricing_model] shapes the pricing-impact options (include in plan, paid add-on, or usage-based) so they fit your existing structure. The 30-60-90 metric plan turns the launch into something measurable instead of a one-off announcement.

When to use it

  • You just built a feature and need a GTM plan that matches what shipped.
  • You want messaging tied to the real activation path, not invented positioning.
  • You need three message variants for the primary persona and adjacent buyers.
  • You are deciding whether to bundle, charge for, or meter a new feature.
  • You want launch mechanics with owners across email, in-app, docs, and social.
  • You need a 30-60-90 metric plan you can commit to publicly.

Example output

You get a scannable plan with headers: an ICP describing industry, size, role, and the pain the feature removes; three persona-tuned message variants; an activation path from signup to first value with the aha moment named; pricing-impact options against your model; launch mechanics across channels with owners; and a 30-60-90 day metric plan with leading and lagging indicators — all under 800 words.

Pro tips

  • Make [feature_name] match what actually shipped, so the activation path describes real behaviour rather than a roadmap wish.
  • Define [primary_persona] precisely, since the three message variants are tuned to that buyer and adjacent ones.
  • Use [pricing_model] to anchor the pricing options; the model weighs bundling versus add-on versus usage-based against your existing structure.
  • Treat the 30-60-90 metrics as the part you commit to publicly, and tighten them until each is measurable.
  • Re-run the message variants if they sound interchangeable; good variants should feel aimed at distinct buyers with distinct pains.
  • Name the aha moment in the activation path explicitly, since the whole plan hinges on getting a new user to that first-value moment quickly.
  • Assign real owners to the launch mechanics, since a channel with no owner is a step that quietly does not happen on launch day.

Frequently Asked Questions

Is the plan specific enough to act on?
It is built to be executable the next week, with an activation path, message variants, channel owners, and timed metrics. You still need to plug in real names and dates, since the model produces the structure and reasoning but cannot know your team's actual capacity or calendar.
How does it handle pricing decisions?
It gives pricing-impact options against your `[pricing_model]`: include the feature in an existing plan, sell it as a paid add-on, or meter it as usage-based. These are options to weigh, not a final answer, so review them against your margins and positioning before committing.
Will the metrics be realistic?
The 30-60-90 plan offers leading and lagging indicators, but the model cannot know your baselines. Treat its targets as a starting framework, set the actual numbers from your own data, and commit publicly only to figures you can genuinely move.
Can it tailor messaging to a specific buyer?
Yes, it tunes three message variants to `[primary_persona]` and adjacent buyers. Define that persona precisely for sharper output, and re-run if the variants feel interchangeable, since strong variants should read as if aimed at genuinely different readers.
Engr Mejba Ahmed

Need this built for real?

Engr Mejba Ahmed

AI Developer · Software Engineer

I'm Mejba — I design and ship production AI systems, automations, and full-stack apps. If you want this turned into a working solution for your team, let's talk.

More in AI for Business & SaaS

Engr Mejba Ahmed

Engr Mejba Ahmed

Claude Code Expert · Online

👋

Hey there!

Quick Actions

WhatsApp Instant reply

Chat on WhatsApp

+880 1723 741224 · Instant reply

Popular Questions

Engr Mejba Ahmed is connected
Engr Mejba Ahmed is typing...
Engr Mejba Ahmed avatar

✉ Want me to follow up? Drop your email

Engr Mejba Ahmed avatar

📞 Connect Directly

Choose how you'd like to reach me

WhatsApp

+880 1723 741224

Email

[email protected]

✓ Details sent! I'll get back to you shortly.

Powered by OpenAI

335+

Blog Posts

25

AI Courses

63

Projects

Services & Expertise

Pricing & Process

Learning & Resources

Connect & Support