Tackly
Map your thoughts in real time with AI.
123 followers
Map your thoughts in real time with AI.
123 followers
Most AI notetakers hand you a transcript with a summary bolted on 💅 Tackly maps what you say into one of 20 nodes, live and in realtime — from meetings, solo voice notes, or a pasted transcript — so you get structure you can always come back to, not just silly old black and white text. I struggle with ADHD on a day-to-day and this has made me feel a ton more productive, I never lose my thoughts. AI notetakers are boring, tackle them with Tackly. Try it for free at tackly.co
the "transcript with a summary bolted on" line is so accurate lol, that's exactly what's wrong with most of these.
quick question, when you export to MD and feed it to Claude, is that a one-off thing or are you building context across sessions? feels like that loop could get addictive once you're a few weeks in.
one small thing, it asked me to review after just my first recording.
I hadn't really lived with it long enough yet to have a real opinion, so
it kinda felt premature. might get you better (and more) reviews if that
ask showed up after someone's had a few sessions in.
Tackly
@issadevs It's okay, it's just a local review so I know there wasn't any issues - doesn't get pushed to anywhere.
Tackly
@issadevs Glad you agree! And with the exporting to Claude - I'm building context across sessions - but every session has a local 'TacklyAI' built into it so you can always ask it to break down whats new - whats been added after x and it will tell you exactly whats been changed. You could continue on the same session and keep adding context on separate days, but I love your question because the export hasn't been designed for that. Exporting prints out the entire board, so it would be great if it could be exported based on newly added context. I LOVE THAT
the ADHD framing resonates, that line about never losing a thought is exactly what's missing from tools built by people who don't actually have that problem themselves. curious about contradiction handling though - when you're rambling and go back on something you said 2 minutes earlier, like actually no scratch that, does Tackly catch that as an update to the existing node or does it just add a new one sitting alongside the old take?
Tackly
@omri_ben_shoham1 Hey Omri, good question, and this is all covered by the tri-tier rendering pipeline. When you're rambling, and go back to something you said 2 minutes earlier, or even 30 minutes earlier - if its highly relevant to an existing node (logical to just expand on an existing node rather than creating a new node) Tackly will add onto the summary for that existing node. And if you decide to 'scratch' an in idea from earlier on, or just something you said that you want to correct, Tackly will understand the context of what you want to update, and where that node exists - and simply make the update. I for example had an issue where I saw that something was misconstrued, I saw it on the board (I said Base44 but I later saw that it rendered as Baseball) and I said 'just to confirm, the competition is for Base44' and it updated the node perfectly. So any clarifications deep down into a session (whether its a solo session or a meeting) are logically implemented.
@lorbes the Base44/Baseball example is a great real bug to have caught. does that same correction logic hold across sessions though, not just within one live conversation? like if you misspoke something three days ago in a solo session, it got mapped to a node, and now in today's meeting you say 'actually, going back to what I said about X' - does Tackly reach back into the older node and fix it, or is the real-time matching scoped to whatever session is currently live?
Tackly
@omri_ben_shoham1 Absolutely! That's exactly why I kept that blooper in the video, so happy you noticed it. And for your question, every session keeps context, no matter how long the session goes on for - unless you manually end the session and start final consolidation. My longest session was around 83 minutes, over the course of 3 days - thats 83 minutes of just measured-transcripting (no idling) and context held very well, Tackly knew exactly what to update (previous nodes, connectors e.t.c.)
Thanks! Yeah, traditional summaries just don't cut it. Right now it's a one-off export, but cross-session context is on the radar agree that long-term memory loop would be lethal.
Tackly
@adamkamaneh Absolutely!
Jonathan, this speaks straight to anyone whose head fills up faster than they can write it down. Talking it out and finding it sorted afterward sounds like a small weight lifted.
Tackly
@amine_aziz_alaoui Indeed! Thanks for the feedback 🫶
Tackly
@Base44 @ms_base
Pazi
Such a promising launch—congrats on Tackly! Map your thoughts in real time with AI. is a clever idea. Wishing you a strong Product Hunt day! 🚀
Tackly
@zvonimir_sabljic1 Thanks Zvonimir, that means a lot!