Custom AI processing prompts
in progress
C
Curtis Hibbs
Right now there are two built-in AI processing prompts: concise summaries and detailed summaries. We should be able to create additional, custom prompts that are clickable like the built-in ones.
Log In
P
Paul Richards
updated the status to
in progress
Hi all,
We're working on custom AI actions! We've started building this feature and wanted to get your input on how it should work.
Custom actions will be available in the slash menu in the notebook, so you can quickly access your saved prompts alongside other commands.
We're currently deciding how these actions should behave in chat, and we'd love your feedback:
Option A: In-chat: Trigger a custom AI action mid-conversation from options above the chat input, similar to how concise and detailed summaries show today. The response appears inline with your other chat messages, so you can ask follow-up questions and build on the result.
Option B: Standalone: Custom AI actions can only be triggered on new chats so you cannot trigger them inline with an existing conversation. The main pro of this option is to reduce clutter in the chat after you've already started a conversation.
Which would you prefer, and why? Or would you want both? Let us know in the comments.
P
Paul Richards
Merged in a post:
Custom Summary
A
Andrew Porsborg
it would be nice to be able to customize the summarization. currently the consice summary doesn't give much if any detail and the detail summary seems as long as the actual page or document. to be able to set some parameters like summarize a web page in 3 main sections like intro, body, and conclusion with 3 key highlights in each.
P
Paul Richards
Merged in a post:
Choose Summary when Adding content
M
Morten Lindstrom
Allow to choose Summary option when Adding content, and not only as a global setting.
P
Paul Richards
Merged in a post:
Summary Options
d
david
Is there anyway to get a shorter summary option in addition to concise and long?
T
Timothy Coxon
Hi, Just copy/paste from an email I sent in earlier... This is a more appropriate place to submit it.
---
I've really enjoyed using Recall.it for its simplicity; however, this is also becoming an annoyance. You have a few preset prompts accessible via buttons (concise summary, detailed summary, generate connections etc.)
- It would be great to have access to the prompts behind those buttons so I could tweak them...
- It would be even better to have the ability to add my own custom buttons. My current solution is to keep a notepad file open with prewritten prompts that I copy/paste in when needed. e.g. After running a summary I run a custom prompt on all nodes that adds tags to them. It also adds a variant of Tiago's PARA system (just to add more second brain to the system)
- You could take the custom buttons a step further with contextual visibility. e.g. I was recently doing a load of research into neuroscience, so I have custom summary prompts with template built into them based on the particular taxonomy of what I am researching; i.e. one for neurotransmitters and a different one for neurological conditions. So, perhaps different buttons should appear based on different conditions. For example, if the "Neurotransmitter" tag exists, show the "Neurotransmitter Summary" button?
- As a usability feature, AI assistance will aid in creating these templates. When I say I make "HEAVY" use of NotebookLM. My current workflow for creating prompts in my notepad basically looks like this:
I started in my "Prompt Genius: Genius" notebook which contains the context for creating highly enriched system prompts for other notebooks. Created a system prompt for a new "Prompt Genius: Recall.it" notebook. The system prompt created detects and fills out context and helps me generate various research terms to fill the context of the new notebook. Once that notebook has filled its context, I can iteratively work with it to generate prompts that I can post into my notepad for copying and pasting into recall.it
- Nested prompting. I like to bring my nodes up to a baseline standard...
* Run either Detailed Summary or a specific custom prompt to research and create a detailed Summary.
* Run get connections.
* Run my custom tag-generating prompt.
After that I might manually customize what has been filled out..
It would be really nice to also have "Workflow buttons" where a single prompt can call other prompts..
---
T
Timothy Coxon
Just some example tags I have saved in my notepad:
The "Tags" one:
"Can you create some appropriate nested tags to apply to this source?
If the source has an "imports/*" tag please remove it as well.
If the source has a pre-existing type tag (e.g. "Person", "Corporation", "Web Site", etc) please keep it and if appropriate apply a nested sub-tag.
Finally please also apply a nested "PARA" tag. e.g. "PARA/Project", "PARA/Area", "PARA/Research", "PARA/Archive"."
The "Neurotransmitter" one:
Please research the title of this card to the best of your ability. Make sure you do enough research to cover the topics covered in the template below and present your answer in the format of the template.
—-
[[Neurotransmitter Name]]
🧬 Biochemical Ontology
Chemical Class:
Primary Precursor:
Synthesis Enzyme(s):
Degradation Enzyme(s):
🧠 Major Neural Pathways
Origin Nuclei:
(e.g., [[Substantia Nigra]], [[Ventral Tegmental Area]])Primary Projections:
(e.g., [[Striatum]], [[Prefrontal Cortex]])📡 Receptor Subtypes & Signaling
Primary Receptors:
G-Protein Coupling:
(e.g., Gs, Gi/o, Gq)Intracellular Targets & Cascades:
⚙️ Physiological & Behavioral Functions
Central Nervous System (CNS) Roles:
Systemic (Non-CNS) Roles:
⚠️ Clinical Pathology & Pharmacology
Associated Disorders:
(e.g., [[Schizophrenia]], [[Parkinson's Disease]])Notable Agonists/Antagonists:
🔗 Related Entities
J
Jame Healy
My most-used use case is Recall for YouTube summaries. I love the convenience of the extension interface discretely to the side, and it's very quick and easy to select one of the two standard Actions.
However, my ideal is to create my own extended quick Actions, or otherwise modify the standard Action prompts to include enhancements something like "If the YouTube video title or thumbnail is click-baity, emphasize a concise answer to the click-bait question in the very first paragraph of your summary" and/or "if the video title/thumbnail references a list of things, emphasize a summarized and enumerated list of those things in the very first paragraph of the summary".
Among other things, the bottom line is just to get to the bottom line simply by pressing the quick Action link (i.e. not necessarily just in the chat or notebook) ... then I can decide to what degree I want to invest in consuming/reading/watching the rest of the content.
I
Ignacio Poveda
I clearly prefer option A (in chat), because it allows an iterative flow of learning, especially important for generating questions, detecting errors and refining knowledge within the same conversation.
However, the main problem with option A is the clutter in the chat. The ideal solution would be to maintain activation within the chat, but with structured or collapsible results that do not saturate the conversation.
In addition, it would be very useful to be able to directly convert the results into notes or cards, since the actual use is iterative and based on continuous improvement.
s
schroell
Option B (Standalone) would be my go-to, since most use cases I'd have for Custom AI Actions or Slash Commands would start from a fresh chat.
That said, Option A makes sense too — and honestly, where I need it most is inside a card. Like, if I've added a YouTube video to Recall, the transcript is basically already loaded, and when I open that note and go to the note's chat, I want to be able to use Custom Actions with Slash Commands right there too.
P
Pete Bell
Option A: In-chat is non-negotiable. Option B: Standalone is a nice-to-have as a clean-start affordance, not a restriction. The "clutter" concern is better solved with collapsible action outputs or a visual separator, not by killing context continuity.
The bigger design question is what context an action operates on. Real workflows need more than "current message" or "full thread." A long research chat might span multiple topics, and I'd want to run "extract key arguments" against only the relevant cluster of messages, not everything. Even a lightweight "apply to: full chat / recent messages / selected" toggle at trigger time would make a real difference. Potential to turn a saved-prompt shortcut into something people build workflows around, and where Recall could pull ahead of competitors offering canned prompt templates. Just my 2c.
B
Banarescu Crina
Both x
U
Utkarsh Deep
Ideally, it should be a mix of option A and B that you suggested. We should be able to set any of the custom prompts as a default prompt, and also use the other non-default prompts in mid-chat.
If that's not possible and I'd have to choose just between A & B, then I'd prefer option A. We should be able to add more than 1 custom instruction overall. Ideally, the slash command mid-chat would work better.
Load More
→