Skip to main content

Work with AI

Untitled

TL;DR​

In Heptabase, you can chat directly with AI, manually edit and annotate important AI responses, then drag them onto whiteboards for visual organization. Additionally, you can use "@cards" to let the AI base its answers on your notes or video content, enabling systematic and deeper research into topics.

Introduction​

In the age of AI, people commonly use well-known AI apps like ChatGPT, Google Gemini, and Claude to learn or research topics they care about. However:

  1. When exploring complex topics involving multiple interconnected concepts, you might want to extract knowledge provided by AI from linear chats and place it on a large whiteboard for analysis and future review.

  2. When asking questions, you often want AI to reference your previously written notes or saved knowledge content.

These scenarios are precisely what Heptabase's AI features excel at.

Integrating Whiteboards and AI​

In Heptabase, each whiteboard represents a topic you're interested in. When you open a whiteboard, you can click the Chat button at the top-right corner to view all chats belonging to or mentioning that whiteboard. In each chat, you can chat not only with collaborators on the whiteboard but also enable AI mode to interact with the latest AI models from companies like OpenAI, Google, Anthropic, and xAI.

Untitled

Whiteboards serve two main purposes in AI chats:

  1. Thinking Tool: To better organize messages received from AI, you can directly drag valuable messages onto the whiteboard for visualization. As your chat messages and dragged content grow, you'll be able to build a deeper and more comprehensive understanding of the topic on your whiteboard.

  2. Topic-based Folder: You can organize all AI chats related to a particular topic within the same whiteboard, making future reference easier.

Untitled

Integrating Cards and AI​

Beyond simply chatting with AI, you can also @mention your cards in messages to the AI, allowing it to answer your questions based on the content of these mentioned cards. Currently, AI can read note cards, journal cards, highlight cards, and video cards with transcripts. Soon, we will also support PDF and image cards.

Untitled

One feature I particularly enjoy when using Heptabase's AI chat is the ability to edit the AI’s responses: highlighting important paragraphs, adding my annotations, and removing unnecessary information.

Upcoming Features​

Heptabase's AI feature is currently in beta and requires users to input their own API Key. Over the coming months, we will gradually offer free AI usage credits to Pro Plan users and introduce advanced AI plans for users who prefer not to use an API Key. Additionally, we will launch many more advanced AI features, such as:

  • Allowing AI to answer questions based on user-specified whiteboards, PDF cards, the entire knowledge base, or other MCP services;

  • Allowing AI to answer questions based on manually selected card content ranges (e.g., selected blocks in a note card, highlights or page ranges in a PDF card, timestamp ranges in a video card, etc);

  • Giving AI the capability to edit cards and whiteboards according to your prompts;

  • Enabling other AI services to call and read/write Heptabase data via the Heptabase MCP Server;

  • ...

Stay tuned!