Hacker News new | past | comments | ask | show | jobs | submit login
Launch HN: Circleback (YC W24) – Tooling to make meetings more efficient
90 points by alihaghani 6 months ago | hide | past | favorite | 91 comments
Hey HN! We’re Ali and Kevin from Circleback (https://circleback.ai), an AI-powered product to help teams make more efficient use of meetings. Circleback automatically writes notes and assigns action items, as well as extract things you care about after every meeting. Here’s a demo: https://www.youtube.com/watch?v=13NX0QxG5hI&t=10s.

Meetings can suck (https://paulgraham.com/makersschedule.html), but we think better tooling can make them suck less. With Circleback, you don’t have to jot down notes/action items, review past calls to extract what was said, tediously update other sources (i.e. CRMs, issue trackers), or forget where you left off last time.

Ever had to hop on a 30-min call with someone to get unblocked on something you're working on? You go off and do what you need to do, but the outcomes/learnings of that call aren’t documented anywhere. Next time someone wants to do something similar, they end up having a very similar 30-min call. This is a common pattern across organizations, especially medium-to-large ones, and it’s just one example of the vast inefficiency of meetings.

Needless to say, the best meetings are the ones you never attend in the first place. Really good notes let you skip more meetings and catch up with what you need later. In fact, some teams are using Circleback precisely to avoid having unnecessary attendance in meetings. That’s the holy grail as far as we’re concerned!

This space is a good fit for LLMs because while they can’t do everything, they excel at processing unstructured data like a transcript. To get rid of even 20% of busywork around meetings is already a massive win—and we think the potential is a lot higher than that.

For a realistic example, I imported one of GitLab’s meetings from their YouTube channel (they famously publish them!) into Circleback. The original video is here https://www.youtube.com/watch?v=1dwzE5j-IQw (though you won’t want to watch the whole thing) and you can view the notes Circleback wrote for it here: https://app.circleback.ai/view/lt93jwzdg3hdzcdnxmm.

You can create automations in Circleback for tasks that come up repeatedly. For example, you can create a workflow to identify feature requests that come up in customer interviews and create tasks for them in your issue tracker and post an update to Slack with the notes from the meeting.

Some of the ways people currently use Circleback include: remote teams gathering context from meetings they didn't attend; sales teams automatically updating their CRM and keeping track of what they last talked about with a client; and executive assistants sharing meeting minutes with the rest of the team.

For engineers, past meetings turn into a knowledge base, so you can search for anything that came up in a meeting before—e.g. some obscure quirk about a sequence of API calls, or how you figured out some bug 6 months ago. If you had a meeting about how to run a service, you can use search to find that meeting and watch the exact moment it was shown. Also, some engineers appreciate having issues be automatically created for tasks that come up during standups. That may not be how everyone likes to work, but it beats doing it manually.

With regards to privacy/security, we use industry-leading practices for handling customer data (i.e. secured at-rest and in-transit) and we're in the process of getting our SOC 2 type II certification. https://security.circleback.ai has more on how data is handled. We also immediately and irreversibly delete all associated data when a meeting or account is deleted and by default don't store any recordings of meetings.

Signup requires an email and name. Normally we require credit card information but we’re disabling that for HN to make it easier to try out the product. After signing up, you can: 1) connect your calendar to have Circleback join your meetings, 2) add Circleback by pasting in a meeting link, 3) record an in-person meeting from your phone or laptop, or 4) import the audio/video of a meeting you’ve previously recorded (this is what I did with the GitLab meeting).

The best way to see how Circleback works is to try it out in one of your own meetings. We have a free trial and it takes about 2 minutes to get started. We’d love to get your feedback and look forward to your comments!




A few notes:

# your pitch above targets the wrong audience. People on a maker schedule need to eliminate meetings, not have better transcripts. People on a manager schedule are the ones that need help, and "meetings suck" isn't talking to them.

# The places that will be really interested are places with lots of meetings. I.e. mid-to-large enterprise. Neither your pricing nor your marketing targets them.

# way too verbatim. Most meetings don't require that level of detail.

# You might want to link notes into the transcript/video for the parts where people want more detail.


Appreciate the feedback.

We've had some customers request more detailed notes which we've enabled for them on the backend. We have plans to release more self-serve customization around verbosity as there's no one-size-fits-all solution.

Agree on linking notes to the transcript. Citing sources (from the transcript/recording) is something we're introducing to more surface areas in the product.


Congrats on the launch, looks great. How do you compete with the built-in Zoom AI companion Meeting Summary? It works very well, but it's not even about that. Even if your summary were twice as impressive, competing with a tool that's seamlessly integrated into users' workflow by default presents a formidable obstacle.


Thanks! Right now, the delta between Zoom AI summaries and ours is enough to get many to switch.

We've also built (and are continuing to build) functionality that goes beyond summarization:

- Integrations that connect with other apps/CRMs to automatically push relevant data after every meeting.

- We can automatically identify and take action on insights you care about. An example I showed in the linked video (https://youtu.be/13NX0QxG5hI?feature=shared&t=144): I have a workflow to identify the customer's industry after every demo call I do. There are some really cool use cases here, especially when combined with integrations, i.e. automatically updating a field in a CRM with the customer's industry, or create a new row in a Notion database. We'll soon be adding schema support for insights so you can have more control over the structure of the insights generated, too.

- AI-powered search across all your meetings: being able to get an answer to a question using the context of your/your team's meetings (regardless of whether they happened on Zoom, Meet, Slack huddles, or in-person) is quite powerful and something we're working on making much better.


Kudos on launching it, I will be trying in a few meetings to see if it goes well, so far I am finding the UI unresponsive, I click and it marks an action item as completed (optimistic update) then it reverts back to unchecked (failed). I asked the assistant what Synergy meant and it just hanged. I liked the use of a fake meeting as an introduction to the product and the action items as an onboarding checklist, I like that you launched with a delete my account as well, most startups take a long time before implementing the exit path.


Thanks! We have some kinks to work out with the intro meeting and its associated action items. Everything associated with the intro meeting is stored client-side hence why action items being marked as complete don't persist. You shouldn't notice any issues like that with real meetings (let me know if you do).


Show how well it works: embed videos and their diaries in the presence of accents, multiple languages, and technical terms.


Definitely, the GitLab meeting linked (https://app.circleback.ai/view/lt93jwzdg3hdzcdnxmm) is one example. Let me know if any other public meetings come to mind I can import to show this.


If you want to test it with multiple languages, perhaps try all the parliaments of the world? They tend to have public recordings.


Great idea. I imported a Scottish Parliament meeting (https://www.youtube.com/watch?v=b2WPUzr5ieI), you can see the results here: https://app.circleback.ai/view/ltg9d70asxk05j1fyaq.

Right now, speaker identification (and thus everything downstream that depends on that) works better for meetings where Circleback joins the call (compared to those imported) but I wanted to share this anyway.


The summary is very high quality! Thanks for that.

I think the thing I'd like most is if the AI could "cite" its source (i.e. provide a timestamp of when exactly the statement was made that it's summarizing) directly inline in the summary (vs. only in the transcript).

Similarly to how they're used in AI-powered search (e.g. Perplexity), inline citations would help me easily cross-reference statements and gain confidence that the summary is accurate and the information can be relied on.


excellent idea! this could be the litmus test of product fitness


It's kind of weird to transcribe a meeting from someone who isn't your customer and use it in marketing material (this post). Folks who don't have the context would think GitLab is a customer of yours and you have their permission for using their stuff in marketing.


I would expect them to showcase their dogfooding of the product. Just use it for every internal meeting and cherry-pick the best result to put on display.


Congrats on the launch! We love using your product at https://www.hellodata.ai!

We actually built some hubspot and slack integrations and you folks released those same integrations soon after. It proves that you listen to your customers and develop meaningful features. Kudos to you!

We’ll keep recommending you over any of your competitors because your output is so much better!

Wish you the best and good luck!


Thank you! Glad to hear the integrations have been valuable.


This is really cool! I’ve been looking for something to process local government meeting recordings put online to look for actionable information for following up with muckrock.com FOIA requests to dig deeper. Thanks for sharing.


Looks interesting, how does this differ from the built in meeting summarization that Zoom AI provides?


The summaries/action items you get with Circleback are better in terms of accuracy and detail than with Zoom AI. Running the two in parallel for a meeting and comparing the outcomes is a great way to test this and how most customers end up switching.


Is there a metric you use for this comparison? Any reason you'd expect Circleback to have context or info that's better then Zoom?


the metric is obviously subjective (because nlp) and the reasons are probably found in the nlp/llm.


There are many (many :)), metrics for NLG and NLP comparison that can be chosen. These are not simply subjective and no way to compare


nlp deals with imprecise languages (e.g. words can have different meanings) idk how it could ever be anything but subjective.


From the post title, I expected some material improvement to how meetings are conducted. Automatically transcribing and summarising the meeting does not seem like any serious improvement or anything novel.

Also, it seems to be focused on what is said in the meeting. But what if the meeting is heavy on the visuals (a PowerPoint presentation, a demo) and the spoken content doesn’t make much sense without seeing the shared content? I imagine the output will not be very useful in that case.


Visual understanding is key to anything that isn’t just talking heads in a discussion and what almost all of these tools are missing, I think because it’s a lot harder then using whisper and OpenAI (or equivalent) and a lot more expensive/complex to ground a conversation in the visually shared data, speaking from experience of building a tool that does understanding of what you’re screen sharing. We focus heavily on this for recorded info, pairing it with data on what’s actually happening on screen (think mouse tracking and action ontology) and find it significantly changes the understood summary and transcript of any more white collar type presentation or share like a developer doing a brownbag (we’re not meeting software, more Loom-like record and share)

Circleback folks, cool product, if you want to add visual/screen shared data as a dimension of understanding for you hit me up (diamond@augmend.com). We’re setting up a service for a few meeting/recording understanding products and would love to help you out here too.


Echoing same thoughts here too and was even going to lay some kudos for any tool looking to provide some improvements to the more mundane day to day aspects that we still have to deal with because of a lack of much innovation.

Meetings, emails, and other mundane stuff like documentation generation and such would be really prime things I'd love to see tackled. Sadly, its not sexy enough to expend resources on unless you throw in some AI or other trendy hook.

Email in particular is the bain of my existence. Our tools around it suck (Outlook), provide no real management features (gmail) or seem to be stuck in the early 2000s (Thunderbird).

Particularly I am desperate for more developer friendly ways to script, automate and manage email correspondence and chains because I feel 80% of my day is wasted just reviewing wtf is in my inbox.


In many cases, if you don't have to worry about jotting down notes and action items during a meeting, the meeting can be conducted more efficiently. While not novel, a well-written meeting summary also makes it easier to quickly get an understanding of what was discussed and needs to be done as a result of the meeting, whether you attended it a few hours/days/months ago or didn't attend at all. Being able to automatically act on the outcomes is the really exciting part.

I agree that there's more that can be done for meetings that heavily rely on visuals. Right now, we save what was screen shared (if recordings are enabled) but the visual component isn't used in generating outcomes. Lots of interesting things that can be done with multimodal models here.


Most if not all of my meetings are around discussing what is shared on a screen. This is rarely a PowerPoint and often a variety of different data sources from ever changing presenters. Looking at 3d models in a review and making notes / Todo would be awesome. So far transcripts of such meetings are rather useless.


Meetings are hard because prople are in different states at all times (clients may not know what they want, teams may not know enough about hiw ti solve certain problems, joe may be lazy and hungry one day...). Human things make meetings annoying so I agree with your sentiment that this may not solve our problems.

However. "meetings rely on visuals sometimes instead of just spoken words" doesn't feel like a fundamental issue that breaks this thing. It just sounds like a feature request.


Interested in this iff it works with non-native english speakers. I've found the other solutions I've tried utterly fail at this


We use a Whisper-based model for transcription which works really well with accents and supports over 100 languages. Would be keen to get your thoughts if you try it out.


How did you just launch yet "100+" teams are already relying on this, considering people are usually wary of new stuff?

What kind of marketing trickery is this?

Serious question.


Launch HN != product launch


That's right, and there's a little-known point here that might interest people. The Launch HN format works better if a company is not at the super earliest stage—the startup needs to have ripened a little. This is an exception to the normal YC advice of launching as soon as possible. That advice is valid, including for other kinds of HN post (like Show HN, if you have some kind of tech for people to try), but it's not quite so applicable to the Launch HN format.

We learned this by watching how the community reacts to Launch HN posts. If it feels like the company isn't "ready", the reactions tend to be skeptical and disinterested. "Ready" for a Launch HN can still be early-stage, but the company needs to feel real, there has to be a real product, more than a bare-bones website, should show pricing, something more than "Book a demo" for trying out the product, and so on.

By the time a company has developed enough to check all those boxes, it's natural that it would already have a bunch of users, as Circleback does in this case. In fact, that's the ideal case—the startup should be making something people want, and have users to back that up, before doing a Launch HN. (There are always exceptions, like if you're developing an electric airplane, a cancer therapy, or something else that takes years before users can try it.)

After puzzling over this, I came to the conclusion that the bar is higher for Launch HNs because they have the official stamp of (1) being YC-funded and (2) getting placed on HN's front page. (For background on the latter, see https://news.ycombinator.com/newsfaq.html and https://news.ycombinator.com/yli.html). That raises community expectations, and rightly so!


That actually makes sense. Thanks you!


Never been in YC, but I hear they all use each others products.


> What kind of marketing trickery is this?

it's called the "circleback trick"


I think the basic thought is flawed, I would argue that this is not completely true:

> Needless to say, the best meetings are the ones you never attend in the first place.

The best (avoided) meetings are the ones that are pointless and *are cancelled before they happen*.


That was my silly line that I put in these guys' text to appeal to what I know about how HN feels about meetings.

You've done me one better in this respect, point taken!

Edit: for those curious about how these posts get made—I work with the founders to try to figure out how to talk about their startup in a way that might appeal to HN. See https://news.ycombinator.com/yli.html for the instructions I send to YC founders.

It's not possible to get this perfect, but we can usually avoid obvious pitfalls. With a startup like Circleback, for example, I felt it would be important that the text not feel like it was written primarily for managers. Hence the pg essay link as well. (I might have pushed this too far, though, because https://news.ycombinator.com/item?id=39621356 makes some good points.)

It's not a question of making anything up, of course—the most important thing is that everything be true. But that still leaves a lot of range about what points to emphasize, and there I try to be useful to founders, especially founders who haven't spent countless hours on HN and thus don't have an instinct for the culture here.


It will be difficult to differentiate from Otter, Fireflies, Sembly, Noty, Krisp, Tl;Dv, Supernormal, Spinach, Fathom, Airgram, Noota, Tactiq, Vowel, Jamie, and whatever's built in to Zoom, Google Meet, and Teams already.

I evaluated many of these for my company and ultimately found that they were pretty much all bad due to lack of customizability. I would suggest anyone here looking for an AI meeting note taker to write their own:

1. Pull down the raw recording (using built-in recording or Recall.ai).

2. Run it through Whisper or Deepgram with a custom prompt and custom vocabulary.

3. Run it through a basic LLM to correct common transcription errors specific to your company's vocabulary and remove filler words.

4. Run that through GPT-4 or your favorite powerful LLM to generate notes, iterating on the prompt to tailor it to your industry and meeting style.

All of my coworkers agreed that the custom solution (which took me a day to slap together and is close to free) is dramatically better than any of the off-the-shelf meeting note takers we have used, no contest. Being able to customize the transcription to capture industry-specific terms, acronyms, or internal codenames, is an absolute must.


We provide a compelling alternative to those considering building vs. buying in this space but there's nothing more customizable than building your own solution.

Right now, we provide the following customization levers: custom vocabulary (configurable from Settings → Account) and custom prompts (via insights you can define in workflows). We're also working on adding more control over the verbosity of the notes.

If you're looking to have full control over the outcomes generated, I would also suggest building your solution if the building/maintenance costs make sense. We're focused on providing an out-of-the-box solution that works really well with minimal setup (with customizations available for power users) and providing value beyond just summarization with search, workflow automation, and collaboration features (i.e. sharing, commenting) for teams.

If you do decide to try out Circleback, I'd love to get your thoughts as someone who's very well-informed about this space!


Is this satire? It really reads like that one infamous post on the Dropbox HN announcement...

https://news.ycombinator.com/item?id=9224

For every one person who'd want to do it the better DIY way, there are 10000s that can't (or won't), but would still find value in the service.


For the record I sync my files using a method similar to that user, rather than using Dropbox. I imagine plenty of HN users do the same. I'm making this recommendation to other hackers on here who don't mind getting their hands dirty.


"the dropbox comment" is noteworthy because it mischaracterized the business value of a more accessible solution.

nonetheless, there are ppl whose needs do not exceed their skills


For what it's worth, the new "Meet" add-in from Microsoft for Teams is remarkably pragmatic, pulling together transcription, speaker tagging, semantic content timeline, meeting assistant notes, more, into a common workspace for the meeting.

People are just discovering it this past quarter or so, but when they see the scope and utility of what it can do, they start recording everything.


Looks like you're talking about this one. Do you know if it is available to everyone or if admins have to it on?

https://support.microsoft.com/en-us/office/stay-on-top-of-me...


> which took me a day to slap together and is close to free

An engineer who can slap together a good meeting transcriber in a day is probably paid $2,000 a day or more. The opportunity cost of having them work on a random project is far more than the cost of their salary. The ongoing maintenance cost of the custom meeting transcriber is probably 5-10 engineer days over its lifetime. The added utility from slightly-better meeting transcripts does not compensate for the staggering engineering cost of the custom solution.

Circleback and other meeting transcribers will surely get better and surpass the quality of the custom transcriber. Then the team must spend more time switching to Circleback and deleting the custom transcriber.


I'm tending to agree with you... you have better data security, and nothing beats the best Whisper model.

However there's lots of manual steps here and it would definitely be more convenient to have a tool that just does all that straight away. Also, Whisper unfortunately does not (yet?) support diarisation (identifying which speaker is talking).


Totally agree on the baseline. We’ve found that adding multimodal data like what was onscreen to be a big help to improve over this, which is a little more complex. Helps more to add action data to like who was typing in what, where the mouse was, etc.

I’ve also been playing with pulling in knowledge base context or reading relevant web pages for unique words to create that initial prompt and custom vocab automatically.


Gotta add facial recognition too so the notes can include "Bob rolled his eyes slightly when Alice mentioned the new reporting procedures."


Lol. I should add that as an option you can toggle


Can you elaborate on the custom prompting? As in "You are a scribe attending a meeting of engineers discussing how to implement ElasticSearch. Please take this recording and create detailed notes of the discussion?"


Depending on your use-case it might include things like, "be sure to highlight the contributions and points of view of each participant", or "come up with a list of action items and who's assigned to each one", or "ensure the summary doesn't include confidential details about our new product".


> 3. Run it through a basic LLM to correct common transcription errors specific to your company's vocabulary and remove filler words.

Do you just include a list of common errors in the prompt? Or have you trained a model for this?


I would love to train a model, but no, it's just common errors that I've encountered. It can also fix it in context. For example if you're talking about the AI 'Groq' but the transcription always says 'grok', then you can, in this step, ask the LLM to fix that error if the context is appropriate (i.e. it's being used as a noun).


I do this with just a prompt setting context of the meeting if we have it, explaining this is a spoken meeting between n people, and asking to correct based on the entire context, acutally works decently out of the box.


Damn, I just tried this with ChatGPT (warning: contrived example) and it works surprisingly well:

PROMPT:

The following is a partial transcription of a meeting at a tech company. Please correct any transcription errors, using clues from context as well as the fact that this is a technical meeting.

Person A: we shouldn't use a sequel database to store this data, we probably want to use something Callum nor instead since it's more efficient than row-based storage. Something like a patchy park or arrow.

Person B: What's park, eh?

Person A: It's just a column-based storage format with efficient Jesus or snappy compression.

RESPONSE:

Person A: "we shouldn't use a SQL database to store this data, we probably want to use something columnar instead since it's more efficient than row-based storage. Something like Apache Parquet or Arrow."

Person B: "What's Parquet?"

Person A: "It's just a column-based storage format with efficient GZIP or Snappy compression."

EDIT: mistral 7B on the other hand botched this terribly, and made up a lot of nonsense unrelated to the transcript.


Yeah it’s pretty neat and can be improved with more context for technical terms. You do risk some hallucinations


Fantastic example.


Congrats on launching, how do y'all differentiate from vowel. We used to use vowel but then they went under and we ended up writing our own tool, kinda like pants2 mentioned



Ahh I see they got acquired by zapier. Sometime last year ceo posted on twitter that they were shutting down due to a pulled term sheet or something


How do you compare the pros/cons of having the summarization built into the call tool, like with Vowel, vs having more control but in separate tools?


More work to build your own and more friction too since we don’t “own” the voice channel like vowel did. We used gmeets transcription but we have to remember to record all meetings, we ended up ditching it tbh


Congrats on the launch. I'm curious about how Circleback connects to Zoom, Teams, Meet, etc. Were you able to use official APIs provided by any of the platforms for this? Did you use a third-party bot service like Recall.ai (already mentioned by another commenter)? Or did you build something in-house that drives the Linux client (where applicable) or a headless browser? No problem if you consider this a trade secret.


Thanks! We currently use Recall.ai.


Congrats on launching. The customer list is impressive.


How does it differ from Otter.ai, or YC funded Cogram?


The main reason our customers have shared for switching from Otter to Circleback is better quality notes and action items as well as ease of use. Some of the automations you can create in Circleback are also not possible in Otter. I can't speak to Cogram as I haven't tried out the product or know much about it.


Or Supernormal?


It doesn't. VC is so inefficient that the same thing has to be funded over and over again in the hope one of them win.


Is any of your customer data used to train your LLM models?


We don't use customer data to train models.


Where is tool name Touchbase lol


I am genuinely confused and can’t tell if circleback is chosen unironically or not. The argument against would be that it’s risky to take an unserious name, although I think it’s an overrated fear. But if it’s serious, how do people not have an instant cringe collapse? Are there people who say circle back without needing a shower afterwards?

Anyways, those are the key takeaways from your data driven thought leader, yours truly.


I own touchba.se and use it to set up meetings/calls. @Circleback team you could take it on the cheap, but I think Circleback makes a lot more sense for your company.


I am so so so sick of these.


Of what, specifically, and why?


I'm guessing it's the creepy "notetaker" that these companies have join and listen in on you. It used to be fun to join a meeting on time and have a random moment with someone else, and discuss something interesting, before the late stakeholders arrive.


So that's a pain point that Circleback is now aware of: you want to be able to go off the record.


FWIW, by default we don't store meeting recordings–only the transcript. Saving meeting recordings is something you can enable from Settings → Account.


The number of my ai notetaker summaries which start with Participant 1 asked Participant 2 about their weekend


I've just seen so many equivalent products that have never caught on in the market, are overpriced for what they offer, and ultimately tantamount to bloat


seems like there is money to be made


Awesome to see you here Ali!

You may or may not remember, but we used to run similar tech YouTube channels as young teenagers and worked on a few videos together. I've been following circleback since you guys were accepted into W24. Congrats on the launch!


No way! It's been so long, would love to catch up.


Honestly kinda crazy that it gets on top on HN. Goes to show the upside of going to YC.


As Kwpolska pointed out, Launch HNs are a different category of post—they get a guaranteed initial placement on HN's front page, though after that they rise or fall with upvotes. They never get placed at the top, though.

Launch HNs are one of the things that HN gives back to YC in exchange for funding it. The other big one is job ads for YC companies. This is in the FAQ: https://news.ycombinator.com/newsfaq.html.


I believe “getting on top of HN” is a given for those Launch HN posts.


This is one of the few products I can say I actually love. Congrats on the launch guys!!


Thank you!




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: