Raw Text Input
The most basic and straight forward input, raw text directly prompting the AI.
Abstracted design solutions to review the core elements & interactions in each pattern. To reflect on the best-practice fit for your context when designing in the new AI paradigm.
The most basic and straight forward input, raw text directly prompting the AI.
Adding an image accompanying a supporting text prompt.
Subtle help information presented inline with other UI elements.
Similar to raw text but more natural using voice input.
AI powered suggestions to complete prompts while being authored.
Providing indication of a prompts quality or level of details while it's being authored.
Providing the required structure & detail required for the prompt. Scaffolding the users input.
Like the structured prompt accept paginated to create a focused workflow.
Pre prompt submission AI assisted prompt editing.
Highly abstracted prompt authoring using configured options & controls.
Prompt variables presented in a conversation cloze passage style.
Adding specific files for the AI to reference to more tightly scope your resuklts.
Allowing prompts to be saved & recalled, as well as a library of pre written prompts.
Providing user control over the exact LLM modal they're using.
Providing users control over threaded or a fresh generation each time.
Review & access a history of your various thread activities.
Providing an allocated amount of generation tokens to spend.
Providing users useful options to interact with generated results.
Providing contextually relevant options per generated result.
Providing clear sources used to generate the results.
Displaying results in a timeline when contextually relevant.
Displaying results using their object categories to expose hierarchical insights.
A complete regeneration of the AI result.
Focused regeneration of specific sections of an AI result.
Defining a clear initial command for an AI agent to execute.
Reviewing an agents understanding & providing confirmation.