Suggested prompts in the empty AI state
Seed the blank AI box with realistic starter prompts so users can borrow a good first move instead of freezing at an empty input.
Why this can grow a startup
Blank inputs ask the user to do product design in public. They have to imagine what the AI can do, translate that into a prompt, and take the risk of looking wrong if the product disappoints. Suggested prompts remove that cognitive tax. They turn the first session into selection instead of invention, teach the shape of good requests, and give the product more chances to create an early success that users can then adapt to their own work.
Company example
PostHog added prompt suggestions after seeing users open Max AI, stare at the empty box, and forget the kinds of product questions the assistant could actually answer.
Source and metric
Source: PostHog Newsletter · Browse PostHog Newsletter tactics
PostHog says suggested prompts helped counter the common empty-box failure mode where users felt intimidated and forgot possible use cases.
Source discovered: May 26, 2026
When to use it
Use this when Onboarding, Activation, Retention is relevant to ai products, activation, ux and you can run a bounded test with a free budget.
When not to use it
Do not use it as a substitute for customer evidence, a clear owner, or a measurable stop condition. Local platform rules and market behavior still need checking.
Founder checklist
- Read PostHog Newsletter and identify what is directly supported.
- Choose one channel context: Onboarding, Activation, Retention.
- Define the test around PostHog says suggested prompts helped counter the common empty-box failure mode where users felt intimidated and forgot possible use cases..
- Set an owner, evidence window, and stop condition before launch.
Explore the context
Apply this with an operator
Choose product surfaces that compound distribution without hiding weak activation or retention.