Templates offer a simple way to onboard someone into a complicated product area.

Suggesting basic ideas like "give me ideas to help with my kids' homework" can be sufficient to help someone understand how a product works. It falls flat when the person doesn't know how to write more advanced prompts, or when nuances to how to use the product are difficult to grasp.

Templates solve for both of these.

In their simplest form, Templates make it easy to construct a familiar frame for doing a task. For example, you might already use Figma's Figjam to create a workspace for a retrospective with your product team. Sit down for a moment and think about the last thing like this you created. Now try to describe it in a way that is most likely to get an image generator to produce what you have in mind. Tough, right?

Beyond saving you users the time it would take to create and arrange all of the boxes for this workspace, Figjam makes it so you don't have to describe it (or at least, not most of it). Set a few parameters and add a bit of information in the open chat, and Figma will create it for you based on its logic for this template.

This blend of parameters, suggested prompts, and open text give templates their power. Any tool that would require a long and specific prompt to get a predictable outcome would benefit from a template.

They are very common in ai writing tools like Copy.ai. Users can select a template, fill out a few words (instead of writing a 500 word prompt), and the machine will generate a first draft.

Hypotenuse's image generating tool also includes a template, using shortcuts to add parameters to make it easy for the user to generate their prompt.

You can imagine other uses.

  • Excel users could benefit from a template that prompts users with smart defaults about which columns or formulas to include.
  • Recipe sites could ask a user to include or exclude specific ingredients (maybe based off weight loss goals or medical needs) along with an open text to describe their meal. Imagine being able to remix with a photo of food you saw in a restaurant but sculpted to your dietary preferences!

One thing to consider is that templates aren't always necessary. If the task someone is going to perform is fairly simple, limit how many hoops they have to jump through the first time. Figjam offers another good example of this, giving people the option to adjust their template AFTER they have built it. Sometimes you have to know that you missed the mark before looking for help to get back on target.

Details and variations

  • Include pre-set content templates in new accounts and/or let admins and users save templates for others to use
  • Templates can be robust, like a workflow, or simple like a mad-libs style prompt that users only need to update with a few variables
  • Templates can also be built into the interface to break up complicated prompts, such as how hypotenseuse uses followups to help users build a robust input before generation

Considerations

Positives

True time savings
Templates keep a user from having to spend time generating the perfect prompt. Consider how you could show the user your work upfront like copy.ai's templates, or share the generated prompt afterwards so they can tune it to their needs as they get more advanced.

Blank slate
Since these are just emerging as a pattern, there is a ton of blank canvas to play with as you shape an experience perfect for your users. How could you convert your existing product template library into smart templetized prompts?

Potential risks

Inflated expectations
Just because a tool generates a complicated prompt for the user doesn't mean it's helpful. Be wary of oversetting expectations, especially if you require someone to do the work upfront. Consider constraining your template generation experience to optimize for the parameters you provide, and show the user their work in the form of the actual prompt so they can trace the input to the output.

Limitations unknown
Because these rely on a familiar pattern of a recognizable template, when they don't work as expected it is immediately obvious to the user. Figjam can create a flow chart, but not a wireframe flow (which results in a flow chart). That was a let down. Provide extra context and be clear about what your templates can do. It's better to do one thing perfectly than three things poorly.

Use when:
Multiple tokens and parameters are needed to form a strong initial prompt and it is unlikely the user will know how to build the prompt, or will be unwilling to take the time and effort to do so.
Related patterns:
No items found.

Examples

Figjam's template modal gives a small number of parameters to choose from that represent common uses of the product
Users can see the fingerprints of the prompt as parameters are selected, and add more information to make it their own
Copy.ai puts templates right at the user's fingertips with an easy to find "browse prompts" button in the chat indow
After selecting a template in copy.ai, the parameters are shown inline to the prompt itself. This helps users understand why this information is being asked, making it more likely their answers are useful while teaching how to prompt effectively
Zapier offers several sample templates to build on the front side of Zaps. Here, a user is prompt to give specific parameters that will feed into the image generator
Another example of a Zapier template
Hypotenuse's image generator template includes even more options. You could see this being connected to variables so every image is automatically created with the brand's key tokens and to specific sizes based on the targeted campaign details
Figma keeps the template window handy, allowing users to tune their canvas after they generated it
No items found.