Since the beginning, Tana was always meant to work with AI. After extensively testing with our users on the possibilities, we are now officially building and integrating AI into Tana. We're calling this Tana AI.
Tana AI provides access to the best LLMs in the world. We pair each task with the ideal model for the job. Every model will already be fine-tuned for use in Tana, so you don't have to worry about that.
All savings we receive on volume pricing are yours. When you sign up to a Tana paid subscription, you get access to not only all the fine-tuned AI models we subscribe to, but also the volume pricing we receive.
There is no need to bring your own AI API keys to Tana anymore. But if you want to use your own key for some things, we have left two commands (Ask AI + Ask AI (non-streaming) that you can use with your own OpenAI key.
AI should be like electricity: you turn it on, and it just works.
There are many features in Tana that work with AI. For an extensive list, see the next section on Features using AI.
You can chat with your knowledge using AI in Tana! AI chat comes in two flavours: Ask AI where you get a standard chat, and Ask AI about this content which takes into consideration the context you add into the chat.
Talk to Tana and get your thoughts transcribed straight where you want it. Use live transcribe or audio-enabled fields and tags to speak straight into Tana.
Tana AI requires a paid subscription. You can only use AI in Tana if you are on a paid plan.
AI actions require credits to run. Monthly AI credits are included in any paid subscription. Credits can be topped up as you need.
Instantly capture ideas, thoughts or plan your day by talking to your phone. Tana will transcribe your memo and turn it into structured content by autofilling fields if you apply a supertag. See more in Voice memo
Pick a supertag to see fields that Tana will pick up content for
Helps you iterate on, rewrite or get insights from your content. Edit AI responses and apply Supertags to parts of responses to add them directly into your notes. See more in AI chat.
The Google Calendar integration will import your meetings, classify them with the right supertag and show them in a calendar on your Today page, so you can start taking notes with one click. Get notifications for upcoming meetings to take notes with one click. See more in Calendar integration.
We have added a new way to trigger commands to happen when nodes are added or removed from another node. They are called Events, and can be set up for any node and supertag.
For nodes: Run Configure node and go to On child added/On child removed:
For supertags: Go to Supertag config > AI and Commands > On added/on removed
The command line Open GPT log monitor will open a monitor that shows you how many credits are being used for various AI work. Right now it only shows credits spent using OpenAI models. We hope to add support for other models in the future.
Click on the line items to expand and see the payloads.
The Tana Labs experiment AI for builders is what kickstarted the work on AI in Tana over a year ago. All the things you were able to do with AI for builders, you can do with a Tana paid subscription, without the need to bring your own key.
ImprovedWe now support o3-mini in most AI commands, such as Ask AI and AI Chat. We currently only offer "reasoning effort" set to the default, which is medium. This has improved cost per token over GPT-4o, which about the same performance. However, reasoning tokens might cause costs to increase in total. ()
ImprovedThe new prompt expression system nodes are now also available in the System prompt field on chat agents ()
FixedWe made a change to AI prompt processing to automatically expand all search nodes, but this caused far too much irrelevant content to be sent to AI processing in some cases. We are reversing this change for now, note that you can always specify that reference nodes should be expanded by using the Expand references system field. ()
FixedFix for Claude not working with custom agents that have an initial prompt ()
NewClaude from Anthropic is now available as a custom model in commands where you can configure model. ()
ImprovedAsk AI command (streaming) now supports the prompt workbench ()
FixedWe fixed a bug where some users could not use Claude in Ask AI command nodes ()
ImprovedWe added a new parameter to Ask AI command nodes, to request output to be opened in new panel. (See Draft Panel) ()
FixedThe Transcribe audio system command now supports nodes with source material. ()
FixedMade sure that prompt workbench uses the same default AI model as the AI command nodes ()
ImprovedAutofill will now set default values for fields from extract tagged entities. (E.g., when using the Extract tagged item-fields, autofill will now work better for the tagged nodes extracted into those fields) ()
FixedWe fixed an issue where the voice memos did not respect the users timezone when filling out date fields. No more jetlag. ()
NewWe introduced the command node Start AI Chat, and support for custom chat agents, which can specify model, temperature, system prompt, initial prompt and initial greeting (all with support for prompt expressions). They can also be given commands available to run from inside the chat. ()
NewWe introduced the new Draft panel! With prompt editing!
The updated draft panel makes it easier to review and edit AI generated results. In combination with the new ability to view and edit the prompt, Tana now offers a simple and powerful way to iterate together with AI. ()
ImprovedWe now use Tana headings when appropriate for content received from AI (you can ask for "Markdown headers" explicitly in your prompt if you want) ()
ImprovedWe have added meta-prompt generation for the generate image dialogue (ie. we first ask GPT to rewrite to a more complete prompt, before generating the image) which gives better results. We also stopped writing the result of the meta-prompt generation into the description of images, when using the Generate image with DALL-E command node. ()
FixedFixed bug where AI-generated images could not be shown full screen. ()
ImprovedCustom Autofill improvements: 1. AI instructions for the title, 2. AI instructions for the description, 3. Actually support autofill description when enabled (disabled by default), 4. Update the default values in the configuration panel for custom autofill behavior to reflect the actual defaults and resolve the bug with toggling those values. ()
ImprovedCustom Autofill improvements for voice memo only: 1. Toggle to include or exclude for autofill, 2. AI instructions for content and support for autofilling based on that. ()
ImprovedRemoved global system prompt from Ask AI, no longer necessary given improved LLM models. ()
InfoAdded GPT4o-2024-11-20 as a model choice (not yet default model) ()
How much AI is included in Tana's subscription plans?
Jan 07, 2025
How fast does Tana update to the latest AI models?
Sep 12, 2024
Does the GPT log monitor show AI credits usage by the Meeting agent?
Sep 12, 2024
How are AI credits used on shared workspaces?
Sep 05, 2024
Examples
Use AI to connect Readwise tags to my list of topics
Sep 12, 2024
The Tana API that is used to power the Readwise integration is exactly the same (and therefore has the same limitations) as the Input API. It can only write new nodes to Tana, and the API can only write a single value to new fields.
So, to get all your tags out of Readwise, we recommend a comma-separated format, and then using AI to link to the correct nodes in your graph.
Here's a video of how it works (no audio):
Here is the prompt:
PROMPT
Look at each keyword separated by the commas:
Input: [${rwTags}]
And try to find equivalents in this list of all keywords: //Insert search node here that finds all keywords/topics