AI command nodes

AI commands are commands that use Tana AI to run actions, and is now available on Tana Core.

For an intro on command nodes and all non-AI commands, see Command nodes


Ask AI

Can be run on a single node, a single field, or can be configured with prompts, batch processing, temperature etc. Accepts user-provided OpenAI keys.

Generic AI query

A generic AI query command that streams content into Tana. Accepts user-provided OpenAI keys.

Make API request

Making an API request involves specifying the API endpoint, choosing the appropriate HTTP method, providing any necessary headers or authentication, and handling the response from the API. This process allows different software systems to exchange data and functionality seamlessly.

Generate image(s) with DALL-E

Returns an AI-generated image using DALL-E.

Cluster children with embeddings

Takes a list of children, gets embeddings, and does unsupervised clustering. Given that you have to manually specify number of clusters, this is more of an experiment until we have server-side processing.

Fill in all empty AI fields

System command that uses the field's context to fill empty AI fields

Transcribe audio

Sends an audio file to WhisperAI and returns a transcription.


Add tags using GPT interpretation

Add meeting bot

Send a meeting agent to a video call to transcribe what participants are saying. Many of these fields map onto the ones being synced by the Calendar integration.

  • Meeting link (required): Where to find the link to the meeting
    • Works well with Google Meet and Zoom. Coming soon: MS Teams
  • Transcript field (required): Where to place the transcript of the meeting
  • Attendees field: Where to find attendees for the meeting
    • Having attendees here improves participant identification during the transcription process and when making meeting notes and attributing who said what
  • Recording target: The link to the recording will be placed here. It will be deleted after 7 day
  • Meeting date field: Where to find the date of the meeting. The bot will join automatically when the meeting starts.
    • If a meeting has no date filled in, it will join immediately when you hit "Add meeting agent" button.
  • Transcription provider: Which provider to use for transcription
  • Meeting bot name: Name of the bot to use for the meeting
    • When the agent joins the meeting, the name of the agent can be changed here to "Tam's assistant"
  • Post process command: Command to run after transcription is completed. The default is a command with the Text processing agent, see below.

Text processing agent

Take a transcript (or any text), extract summaries and other things, put them in a target location.


  • Transcript source (required): Where to find the transcript. The field with the text for processing.
    • Could be a meeting transcript, article, voice memo or similar.
  • Status attribute: Use this if you need to override the default system provided status attribute.
    • You may be using several text processors on the same transcript. You can have each text processor triggered based on a different status field.
  • Text processing agent mode: Which mode to run the text processing agent in. Defaults to meeting if not set. Available modes: meeting|generic.
    • There are two modes: meeting or generic. For standard meetings, we recommend the meeting setting as it has been optimized to process action items, entities, and attribution of ideas to attendees. For other uses like processing a voice memo, we recommend generic. Default: meeting

Note: If all you define is the Transcript source, the processing agent will create a summary of the transcript, output as a child of the node.

Tag choices (optional)

  • Attendees field: Where to find users to be used for speaker identification
    • Field where attendees are listed. Most applicable to meetings where the meeting agent identifies speakers and can link them to the list in this field.
  • Tags to use for entities: Entities (e.g. persons, companies) will be detected and replaced for these tags
  • Tags to use for action items: Action items (e.g. decisions, todos) will be extracted for these tags
  • Tags to use for item extraction: Looks for sections of the transcript that match these tags, and extracts them as nodes

Note: if no tags are defined, the processor will not look for anything specific and only run the summary.

Targets (optional)

  • Summary target: Where to place the summary of the meeting
  • New entities target: Where to place discovered entities
  • Action items target: Where to place discovered action items
  • Extracted items target: Where to place extracted items

Note: If you don't set targets, things are placed as children

Prompts (optional)

  • Summary prompt: Prompt to use for generating the summary
  • Augment prompt: Prompt to use for augmenting the attendees
  • Action items prompt: Prompt to use for detecting action items. Use ${sys:actionItemTags} to get configured tags
  • Entities prompt: Prompt to use for detecting new entities, Use ${sys:entityTags} to get configured tags
  • Extracted items user prompt: Additional prompt to use for extracting items (optional).

- You are a senior UX researcher tasked with finding relevant “user observations”
in an onboarding transcript and reporting them back classified according to
the provided tags.
- Find all moments in the transcript when the user experience any of the
described types of observation found in the supplied tags.
- You work for Acme Inc., and it is the experiences of the user - not the
team member - you want to observe and capture. The person with the #team acme
tag works at Acme Inc. The person being onboarded is tagged #person.
- Find at least 10 items, and at least 2 of each type.

Disabling functions (optional)

  • Disable augmentation: Checkbox. Do not enhance attendees with additional information
  • Disable summary: Checkbox. Do not generate a summary

All parameters


  • Description: Prompt expression - same syntax as title expression, but can be multiline. ${sys:context} gives context of node and children.
  • Source: OpenAI

Node filter

  • Description: Search query to filter nodes that this command can be run on
  • Source: Tana

Node context

  • Description: Node context for commands - defaults to node the command is run on
  • Source: Tana

Field dependencies

  • Description: References to other fields on the same node. If any of these fields are empty, and have AI turned on, then their AI prompts will be run before evaluating this command.
  • Source: Tana

Target node

  • Description: Defines what Tana object to insert the result into. Can be a reference to a template node, or a field reference
  • Source: Tana


  • Description: What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. OpenAI generally recommends altering this or top_p but not both. Defaults to 0.
  • Source: OpenAI

Top P

  • Description: An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. OpenAI generally recommends altering this or temperature but not both. Defaults to 1.
  • Source: OpenAI


  • Description: A string that will be appended to the end of the text.
  • Source: OpenAI

Best of

  • Description: Generates best_of completions server-side and returns the "best" (the one with the highest log probability per token). When used with n, best_of controls the number of candidate completions and n specifies how many to return – best_of must be greater than n.
  • Source: OpenAI

Max tokens

  • Description: The maximum number of tokens to generate. Will be capped at maximum given prompt length. Defaults to maximum.
  • Source: OpenAI

Model to use

  • Description: Defaults to text-davinci-003 or the most capable model.
  • Source: OpenAI

Stop sequences

  • Description: Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence. One sequence on each node.
  • Source: OpenAI

Presence penalty

  • Description: Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. Defaults to 0.
  • Source: OpenAI

Frequency penalty

  • Description: Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. Defaults to 0.
  • Source: OpenAI

Combination prompt

  • Description: After running the normal prompt over all of the context, this prompt will be run with ${sys:context} set to the concatenated output.
  • Source: OpenAI

Batch prompt context

  • Description: The presence of this field enables splitting up a long context into multiple prompts, which can optionally be combined with the Combination prompt. The field ${sys:context} is determined by the dropdown options, or by a reference to a field or a node.
  • Source: OpenAI

Fill context window percentage

  • Description: The context window size includes both the prompt and the response. This parameter takes a number from 0 to 1, and determines the percentage of the context window that the prompt is allowed to fill - both for individual and batched prompts. The default is 0.5, which means that the prompt and response are equal in size.
  • Source: OpenAI


  • Description: URL, processed using title expressions
  • Source: Tana

Insert output strategy

  • Description: Default is adding as a child (except in fields, where default is replace)
  • Source: Tana


  • Description: Payload type
  • Source: OpenAI

API method

  • Description: Defaults to GET
  • Source: Tana

Parse results

  • Description: Defaults to no parsing (raw)
  • Source: Tana

Authorization header

  • Description: For authentication (for example "Bearer ....")
  • Source: Tana


  • Description: API headers, must start with a word and a colon, like "Authorization: ..."
  • Source: OpenAI

Avoid using proxy

  • Description: For local sites, or where you know there is no CORS issue
  • Source: Tana


  • Description: Define supertags
  • Source: Tana

Image size

  • Description: The size of the generated images. Must be one of 256x256, 512x512, or 1024x1024 for dall-e-2. Must be one of 1024x1024, 1792x1024, or 1024x1792 for dall-e-3 models.
  • Source: OpenAI

Number of images to generate

  • Description: The number of images to generate. Must be between 1 and 10. For dall-e-3, only n=1 is supported.
  • Source: OpenAI

Metaprompt to enhance prompt with GPT-3

  • Description: n/a
  • Source: Tana

Number of groups

  • Description: Defaults to 3
  • Source: OpenAI

Transcription Language

  • Description: The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency.
  • Source: OpenAI

View definition

  • Description: View definition to apply to node
  • Source: Tana

View type

  • Description: Set view type by picking from dropdown.
  • Source: Tana

Fields to set

  • Description: Fields to set, and optionally values
  • Source: Tana


  • Description: Commands to execute
  • Source: Tana

Tag candidates

  • Description: Define supertags that become candidates
  • Source: Tana

Fields to remove

  • Description: Define fields that, if present, will be removed.
  • Source: Tana

Move node target

  • Description: Define node to be moved. Reference to a specific node, field or a dropdown option
  • Source: Tana

Remove reference after moving node

  • Description: Will remove the reference after moving node
  • Source: Tana

Move original node

  • Description: By default, if you run the command on a reference, the reference will be moved. This option can force the original node to be moved.
  • Source: Tana

Done status to set

  • Description: Gives you done state options to set. There are four options to choose from:
    • Node has no checkbox
    • Done
    • Not done
    • Toggle done status
  • Source: Tana

Command to run

  • Description: Write out the commands you want to run.
    • If you're uncertain about how a command is written out, navigate to it through the command line, create a custom shortcut, and go to Settings > Private keyboard shortcuts to the shortcut you just made and expand it. You'll find the command written out in a node.
  • Source: Tana

Look for children in field

  • Description: Looks for children in a specific field, instead of the node. Add reference to field definition.
  • Source: Tana

Relative date string

  • Description: Write out a date string like this week, in two months, etc. Interpreted with prompt expressions.
  • Source: Tana

Reference date

  • Description: Either a date, or use Lookup field to reference a field. If reference date is May 1, and relative date is in two weeks, the output will be May 15th.
  • Source: Tana

Date/time granularity

  • Description: Allows you to specify the granularity of the date object. Use the dropdown to set year, month, week, day, hour, minute, second, or millisecond.
  • Source: Tana

Set only start or end of date

  • Description: Allows you to specify whether you want to set a Start or End date/time.
  • Source: Tana

Related release notes

  • improvedInsert relative date now supports system date fields in the prompt, such as ${sys:dateFromDayNode} ()
  • improvedSlash in the beginning of node filter no longer triggers the slash menu (making it easier to enter a regular expression) ()
  • improvedAny fields inserted from command nodes, which are optional fields, will now be inserted at top of the node. ()
  • improvedWHAT HAPPENED? -> We are now showing more details whenever a command node fails to run. ()
  • fixedWe fixed an issue with command nodes that may contain commands that live external to the current workspace. ()
  • fixedFixed bugs with 'Make API request' expression expansion not working if they contained dates or inline references. ()

Related FAQs

  • Can a command move the current node to a field of a new node?

    Yes, you can. Make a new command node, and use the command Insert Tana Paste with the following prompt:

    - ${name} #note
    - Based on:: [[^${sys:nodeId}]]

    The first line is the new node. It uses the name of the current node to inform the name of the new node by using the title expression ${name}. The supertag #note can be enough for Tana to find the right tag to use, but you can specify it more precisely by adding the ^nodeID to it. See the Tana Paste doc for more info on this convention. To retrieve the nodeID of a supertag, run the command Copy link (HTML formatted) on a supertag definition and paste the results. It will paste with the nodeID written out:

    The second line is the field. After the name of the field and the double-colon :: is a reference to the current node that the command is being run on, which it is able to target by retrieving the nodeID of the current node using the title expression ${sys:nodeId}.

    This is what the command node should look like:

    Special thanks to Navigator Emmanuel Galanos for this clever solution!

    Related docs:

  • How can I extract the start date of a range using Commands?

    Use Insert relative date command, here's an example:

    Related docs:

  • How do I share a supertag from my private workspace to a shared one?
    Currently, the easiest and most foolproof way to do this is to not share it but instead build the supertag, with its fields and anything else necessary for the supertag to work, from the ground up in the new space.

    That said, if you still want to move a supertag over that exists only in your private workspace, the main work is to ensure that there's nothing in the supertag that references something in your private workspace, otherwise it will appear as broken to others once it's moved.

    It's like packaging up a zip file. You can't just zip up a bunch of shortcuts, you need the real files in there or the recipient will only see broken shortcuts.

    You'll also have to remember to move over other things like field options, commands, and ensure that no saved view options contain elements from your workspace. Basically, you must ensure that nothing you're moving over from your workspace contains references from your workspace.

    To bring all nodes (except system nodes) into the supertags, fields and commands you want to move, use the command "Bring referenced node here". Alternatively, you can move each necessary node separately too if you foe example want the field definition to exist outside the supertag. But the key is that everything that is connected to what you're sending over gets sent over too, otherwise there will be missing pieces.

    Related docs:

  • How do I use the Autofill command to enrich URL nodes?

    The Autofill command can generate a new node title and description based on the URL.

    To set up the command

    • Create a new command node
    • Add the Autofill fields command
    • Add and check off Autofill title and Autofill description parameters to change both
    • Add Model to use to control which model you prefer. If left empty, Tana will pick the one that returns the answer with best quality and consistency

    To run the command

    • Run the command on a URL node using the command line
    • Put this command node in the Commands section of a supertag you use for URLs. Press the button to run the command.

    Related docs:

  • How does the "Set view definition" command work?

    There is a command called Set view definition. It can set the Group, Sort and Display settings of a node view.

    There is no good UX for this at the moment, so the instructions are not conventional nor friendly for beginners. But right now, this is one way of doing it:

    • Mock up a node that will have sample child nodes representing the data you'll be applying this command on
    • Then, create the exact view settings you want with Group, Sort and Display.
    • Go Cmd/Ctrl+K > Debug Node on the parent node and look at Views for node:
    • Clone the fields over to the command node so it looks like this:

    When you run this command on a node, this should change the view settings according to your configuration.

    Related docs:

  • In the command line, Set [field] -> [value] doesn't show all my fields, why?

    Set [field] command only works on field types Option, Instance, User and Checkbox.

    Related docs: