Morphic animated logo
AI + Creative Intelligence

The Prompt Is Not the Product

Short answer: A great prompt can improve an AI output, but the prompt itself does not provide the persistent context, workflow, standards, memory, evaluation, and constraints required for consistently strong creative work. The real product is the system around the model that determines how intelligence gets applied over time.
By Weston Baker · Founder, Morphic

For the last few years, much of the conversation around generative AI has focused on prompts.

Prompt engineering. Prompt libraries. Prompt templates. Secret prompts.

Better prompts absolutely produce better results.

But we think the importance of the prompt is often overstated.

Because for serious creative work, the prompt isn't the product.
The system around the model is.

A prompt is a moment

Imagine asking an AI:

“Create a new homepage for our company.”

To do that well, it might need to understand:

Company
What the company does, who it serves, and how it makes money.
Positioning
How it is positioned, what competitors say, and what customers value.
Evidence
What claims it can substantiate.
Brand
What the brand should feel like and what visual decisions have already been made.
Existing work
What the current website contains and what has worked in prior materials.
Decisions
What leadership has previously rejected and what should become precedent.

You can put all of that into a giant prompt.

But should you have to?

And should you have to reconstruct it every time?

Companies accumulate knowledge

A great internal team doesn't start every project with amnesia.

Neither does a great agency.

Over time, people learn:

Language
The CEO hates that phrase.
Audience
Customers respond to this idea.
Proof
We need evidence whenever we make that claim.
Imagery
That photography doesn't feel like us.
Segments
Our investors understand the company differently from our customers.
History
We tried that positioning last year and moved away from it.
Pattern
This layout has become part of our visual language.

That knowledge improves future work.

AI should work the same way.

Context is infrastructure

Instead of thinking about AI as:

Thin architecture
Prompt → Model → Output
→
Creative system
Context → Model → Evaluation → Output → New knowledge

The more useful architecture is closer to:

Inputs
Company knowledge + brand intelligence + previous decisions + task context + relevant creative knowledge.
Reasoning
The model applies the right context to the current task.
Evaluation
The work is checked against strategy, standards, and what the system already knows.
Learning
What happens during the task becomes new knowledge for future work.

Now the model isn't being asked to reconstruct the company from whatever happens to fit into today's conversation.

The system supplies the right context for the task.

And what happens during the task can improve the system.

Better models don't eliminate this need

Models will continue getting better. They'll reason better. They'll generate better design. They'll understand images better. They'll write better code.

That's great.

But a smarter model still doesn't automatically know your company.

It doesn't inherently know which direction your team approved last Tuesday.

It doesn't know why a particular positioning statement was rejected.

It doesn't know which previous creative work should become precedent.

Those aren't model-intelligence problems.

They're organizational-context problems.

The valuable layer is what surrounds the model

As foundation models become increasingly capable, differentiation moves toward the systems built around them.

Knowledge
What does the system know?
Retrieval
What does it retrieve?
Memory
What decisions does it preserve?
Expertise
What expertise does it bring into the task?
Quality
How does it evaluate output?
Learning
How does it learn?
Consistency
How does it maintain consistency across time?

Those questions matter enormously for creative work.

From prompting to creative intelligence

At Morphic, this is increasingly how we think about the category.

The goal isn't to create a magical prompt that produces the perfect website.

It's to build a system that understands enough about the company and the work to make every generation better informed.

Workflow
Understand → Diagnose → Recommend → Plan → Create → Evaluate → Refine → Remember

The prompt still matters.

It's how a person expresses intent in the moment.

But the prompt shouldn't have to contain everything the system needs to know.

The best creative partner you've ever worked with wasn't good because you gave them perfect instructions every time.

They were good because they understood you.

AI should aspire to the same standard.

Common questions

Frequently asked questions

Short answers about why prompts matter—but why the context, memory, evaluation, and systems around the model matter more for serious creative work.

01

Are prompts still important if the prompt is not the product?

Yes. Prompts are how people express intent in the moment. The point is that a prompt should not have to reconstruct the entire company, brand, project history, and creative strategy every time.

02

What should sit around the model besides a prompt?

Useful layers include company knowledge, brand intelligence, task context, approved and rejected decisions, relevant creative knowledge, evaluation criteria, and memory of what was learned from previous work.

03

Is a longer prompt the same thing as better context?

No. A long prompt can contain more information, but useful context is selected, structured, current, and relevant to the task. More tokens are not automatically more understanding.

04

Do better foundation models make this system layer unnecessary?

No. Better models improve reasoning and generation, but they still do not automatically know your company’s latest decisions, internal history, approved patterns, or why previous directions were rejected.

05

What is the practical difference between a prompt-based tool and a creative system?

A prompt-based tool primarily responds to the current instruction. A creative system combines that instruction with persistent context, planning, evaluation, and memory so the work can become more coherent and informed over time.

Morphic

Turn better thinking into better creative work.

Morphic combines company context, creative intelligence, design systems, and AI to help teams create better websites and brand materials—and improve them over time.