AI Product
Partial Autonomy Applications
The Autonomy Slider
Andrej Karpathy created the autonomy slider. It classifies AI products by their level of autonomy.
AI-Enhanced Products: Add LLM features to an existing product. The core workflow stays the same. Examples: Miro, Jira, Slack, Google Docs.
AI-First Products: Design the UX around the LLM or agent. Examples: ChatGPT, Claude, Devin.
AI Value Ratio
Another angle to look at AI products is from the perspective of the AI Value Ratio: the ratio of human input to (valuable) AI output. This concept was introduced by swyx in the AI Engineer World's Fair 2025 Keynote. It is similar to the concept we use in product design, least amount of effort to achieve the most value.
1:0.5 - Copilot: suggesting code as you type
1:1 - Chatbot: returning equivalent value to your prompt
1:10 - Reasoning models, workflows: multiply your input through workflows
1:10000 - Deep Research, NotebookLM: generate comprehensive insights from simple queries
ðŸ’: A chatbot demands a paragraph but returns one line. Worse ratio than traditional products. Why would users use it?
AI as the Engine
AI can act as an engine, adding LLM power to an existing product. Here, AI is a key component, not the whole product.
Simon Wardan's YOW! 2025 talk explores this idea. View slides.
AI as an Assistant
This pattern deeply integrates LLM features into a traditional UI. It creates tight interaction between the UI and the LLM.
Examples include code assistants that are tightly integrated into the development environment.
AI as an Agent
In this model, the UI is built around the agent. See this Manus replay for an example:
Last updated