Definitely seems like it could be useful, but I'd be worried with giving AI write access to emails.
Is there a good audit trail of exactly what actions it takes at each step? I'd personally be worried about leaking proprietary or otherwise private information this way, or having it hallucinate information when it sends out emails potentially causing catastrophic issues.
Valid concern - April does not write emails for you unless you specifically ask for it. Users usually dictate what they want to reply.
But do you think a 'safe mode' - where April does only non destructive operation like read/summarize/draft/move emails to a folder would help you build trust?
It's in our pipeline - we can prioritize it to mitigate that fear.
I started building basically April last week. I have a "safety" toggle in my app. If it's on, there's a "Review Actions" tab that any write or destructive actions go to. Then when I'm done dictating/commuting/whatever, I open the Review tab and go through the actions (add this calendar event, send this text message, reply to this email, etc) one by one - it sort of works like a checklist.
Feel free to take the idea, if it's helpful. No credit/rights necessary. Y'all are much farther along than I am and if you come out with an Android app I'll probably end up a customer!
> April does not write emails for you unless you specifically ask for it.
What if it thinks you asked for it?
Feels pretty easy to mitigate against. If a user deselects "allow email sending", then you can just remove that as a possible tool-call so it becomes impossible.
Absolutely, having the AI agent write out a draft and leave it there, or better yet grant it read-only access to my email and have it draft email responses and store it somewhere else where I can retrieve it would be fantastic.
AI is still not at the point where I am comfortable letting it run free with my email, but a draft that I can read over and make changes to before sending it out is a game changer.
Yes, a safe mode would be great. I think it's a "nice to have" for a lot of early adopter (type of people who read HN), but it will be a "must have" more corporate types (a much bigger market).
> April does not write emails for you unless you specifically ask for it.
> But do you think a 'safe mode' - where April does only non destructive operation like read/summarize/draft/move emails to a folder would help you build trust?
> It's in our pipeline
Wat
Means April will not send emails even if you dictate the email and ask it to send it. In safe mode, it will not have access to tool calls which are related to send email, move to trash.
> April does not write emails for you unless you specifically ask for it. Users usually dictate what they want to reply.
> Send replies that I dictate (it handles the formatting and tone)
How does it handle the tone without editing your dictation?
Yes, think this needs to be way up on your priority list.
Point taken - Safe mode goes out this week.
Safe mode is absolutely necessary. I'd never let an LLM do things for me. They repeatedly prove that they categorically can't be jailed or trusted.
I am building just such a thing, with an overall limitation that it will only interact with emails that only have our team on them. It’s fun
I like the idea. I also think you may need a mechanism to detect adverse actions before they are executed. This becomes important because an email cannot be unsent, and if I dont review the text, the 1 in 100 chance of the email sounding weird would freak me out. There is also the basic corner cases against AI prompt injection and all those spam and phishing emails that are rampant and more and more plausible sounding. Wonder if you have ideas around how to deal with those?
Absolutely. We will be adding a safe mode where April can perform only read, summarize emails & calendar schedule, create drafts but cannot send or delete emails.
Maybe reading out the draft to confirm before sending could be a nice middle ground? Could help with peace of mind about exactly what's being sent, and you could go back and forth on the message if it's not quite right. Once people use it for awhile and trust it more, they could then enable auto-send.
Congrats on the launch btw—cool stuff!
That happens now - before Send/Delete it will ask for confirmation.
Oh nice. Does it read you the text of the draft? Didn’t think I saw that in the demo, but maybe I missed it.
Yeah, It does. We mentioned only few of the things in the demo or else it would have been very long. Apart from hard delete, create /edit labels - all operations can be done through April.
Create/edit/delete draft are very common use cases as people would like to read before sending.
I love the idea (also wondering when Google would build this)
But the situation where emails are backing upload as you drive to work and back to back meetings sounds like a mismanaged workplace.
The real impact (not a startup idea really) is fixing whatever makes the workplace like that. Usually everyone needs to be involved in everything and bad meeting management. Could be bad prioritisation and taking on too much work. Could be busywork.
If AI could solve those problems or help it might be good.
Thank you. Appreciate you sharing your thoughts.
There is a category of users who have to deal with emails and meetings as a primary part of their job. For instance our power user is a Head of Sales who uses April to just get a rundown of his day and get context about his customers before the meeting. It's his typical workday and wouldn't be a mismanaged workplace.
I think I watched you guys get into the batch via the mcp hackathon yc had. Congratulations and best of luck with the startup.
Yes Yes! The MCP hackathon was our way in. Thank you, really appreciate the support.
yes :) thank you for the support.
Congrats on the launch!! How is privacy handled? I would like to try it but I have emails I don't feel comfortable being consumed by third party. Thx!
We access emails only you request for email actions via April. We do not store email data neither do we use it for training models. More here - https://tryapril.com/privacy
How are you handling the formatting and tone part of the email so that it doesn't sound like AI? I've tried to use AI tools for email multiple times but always end up significantly editing or rewriting the email myself.
Yeah - April learns how you speak/correct your emails - it picks up your writing patterns and keeps evolving. The more you use it, the more it sounds like you rather than generic AI.
Can you explain a bit more about this? Are you building a profile of what I write and who I write it to? Fetching relevant examples and passing that through some (cloud?) LLM when writing the email?
I'm definitely curious on the technicals but there is also a bit of a trust element here - both on trusting that my email (likely some of my most sensitive data) is handled with care and trust that the actual responses are phrased well.
Sounds very cool. Do you have concerns around what’s Google are doing themselves in this space? What will differentiate you from them?
Hope the above doesn’t come across as negative - just interested in how you see this market developing.
(cofounder here) Honestly, we were hoping Gemini would nail this so we wouldn't have to build it ourselves, but here we are. The main difference is we're not bounded by Google's ecosystem - we're starting with Gmail but already working on Outlook and other integrations. Also, the goal is to build an executive assistant, not just a voice client for email and calendar.
Google native AI integration to Gmail and calendar frequently disappoints be it on desktop or phone (Pixel), it's like Apple and Siri. Should be better given resources but way of base when compared to our expectations.
Shortwave has had all this and more for over a year and still nothing in Gmail.
This looks cool. Any chance you could wrap my Claude Code sessions as well? That's the thing I really want to be voice-driven for my commute. (serious question :) )
That would be supercool - but not the focus point right now. Though I totally see myself using it.
[flagged]
No personal attacks, please.
Looks awesome! I downloaded the app and was able to get it connected to my accounts, and it is working.
However, I did notice that connect took around a minute to a minute and a half before the agent was in the call and able to speak. Is this a byproduct of the underlying calling service you're using or the traffic?
Regardless, awesome app, curious to see how it continues to improve!
Sorry for the bad experience. It is because of the sudden traffic. Looking at it.
> Here's a demo: https://www.youtube.com/watch?v=ISKwEyuQQEo#t=50
I felt it was more of a tutoring session!! Wouldn't it be distracted driving if you are using it while on the wheel? If not, then honestly, anyone can do those things faster. Also, if you had organized your inbox, many of those emails shown in the demo wouldn't be there.
Anyway, congratulations on the launch. Looking forward to the next iteration.
> we could solve this dead time problem and start doing things on the go
Interesting idea, but how do you address car safety concerns? Studies consistently show that cognitive distraction, even with voice interfaces, can significantly increase crash risk. Wouldn’t managing emails and calendars while driving still fall into that category?
Phone calls while driving are pretty clearly in the Overton window of 'safe things you can do in a car', and it doesn't seem a priori obvious to me that this is worse. Though I do agree with you that in an ideal world people wouldn't even take phone calls and would instead focus 100% of their effort on not killing me.
(cofounder here) Fair concern - cognitive distraction is real. We see it more like taking a phone call while driving (which people already do). We're purposely keeping interactions simple to make sure features aren't too distracting, and are working on a 'safe mode' that limits you to basic read-only operations while driving. We're actively researching attention management to make it simpler. Safety comes first.
> We see it more like taking a phone call while driving (which people already do).
And which we know is highly unsafe: https://unews.utah.edu/up-to-27-seconds-of-inattention-after...
Maybe you can talk about other "dead time" without safety impact - e.g. doing my laundry involves low mental workload but my hands aren't free!
Got it - makes sense. The laundry example is perfect. Moments where your hands are tied or when you want screen-free time
There are so many times other than driving that voice is the preferred medium here. It feels like just one example. (And as others pointed out, taking a hands-free phone call during a drive is not at all provocative these days, to the point that it feels like an odd thing to fixate on personally.)
Given that they dented their call while doing the demo, it doesn't seem weird to fixate on. I think the criticism is valid, given the framing presented and the pitch used to investors.
Also, audio interfaces incur different amounts of mental load / distraction. I wouldn't be surprised if this was more distracting than just talking to a person.
I think the car dent story originally came from - https://news.ycombinator.com/item?id=45008239. As I clarified there - the dent happened before the April demo, during hackathon stress while taking out the car from parking.
But totally valid criticism about cognitive load - better example could be dog walking, cooking or screen free time.
It should really be made clearer in your post that that the crash was not from speaking with April, as it's a bit unclear. Cool product, good luck!
Oh gosh - good point. Sorry! (I watched the other demo video and didn't see this)
Is my life so boring that this is of no use to me? I don't think I get 30+ emails in a week (various commercial quasi-spam excepted) let alone that many on a 40 minute drive.
I think I represent a typical office employee where I get maybe a dozen emails at work and a few calendar invites. Nothing I can't get through in the first 10 minutes of work in the morning. Usually emails that take time are those that I can't outsource to AI anyway.
Nevertheless congrats on the launch and best of luck.
The only reason I'm not downloading it is because 3 days not enough for me to evaluate it and I don't really want to have to add another reminder to cancel yet another subscription.
I never set reminders. I just cancel right away. 99.9% of the time, it will just end when the trial is over, or if I just want to pay for a month, when that period is over.
Please add text messaging and an Android app too??
Sure - we will add this to our pipeline!
I’ll use email filters which work when I’m not at my inbox.
[flagged]
Please don't cross into personal attack in HN posts.
Huh? What relation does that have to do with setting email filters?
Can we connect our own MCPs? We have a remote server we have for internal tools (running on our gateway).
I’ve always been interested to use voice more with the tools
Not as of now.
Can I use this to sort through my backlog of ~15k unread emails? If so, I will sign up now.
You can - we have seen cases where people have deleted 1600 emails in one voice session. But as the pagination happens - it will be in batches, read/delete everything. We have to limit gmail's rate limits
What does that user experience look like? Could I say "move every unread unimportant email to a folder"? How would I do this work in batches?
How are you handling the attack vector of in-context commands[1]?
[1]: https://guard.io/labs/scamlexity-we-put-agentic-ai-browsers-... (currently on the front page)
I think you could probably solve it for this use case by just including a confirmation step for potentially destructive actions which is isolated from other context.
that's a really interesting one
Your Terms of Use is a white page when I go to it.
Also your website pricing is different than the pricing you mention in this post.
Hey we're running an intro offer with the pricing mentioned here. Updated website to reflect that.
Cool Demo!
thank you :)
great demo - wonder why isnt google just providing this as part of Gemini plans - I would pay money for it, why is Google so far behind on Gemini integration?
Let me just put in a plug here for not trying to fill all of your so-called "dead time" with so-called "productive activity". Mind-wandering times like driving, showering, laundry, coffee-making, etc. can produce some of your most creative moments and may even be essential to your mental health. [0]
[0] https://www.sciencedirect.com/science/article/pii/S089662732...
Don't worry, AI will take over those for you.. /s
The subscription seems high and it doesn't seem practical to me. Goodluck though.
Its always sad/disappointing/curious when non-american engineers choose to use american accents as their voice choice instead of their ethnicity or literally anything else.
ooo prompt injecting with my contacts. sounds like fun.
We are just another month closer into the year 2000.
Isn't this a repost? I swear I just saw this posted and they got ripped for telling people to drive while using it when it made them crash.
The current thread is a Launch HN that I helped the startup prepare (see https://news.ycombinator.com/newsfaq.html or, if you really want details, https://news.ycombinator.com/yli.html).
The other thread (https://news.ycombinator.com/item?id=45008239) appeared by coincidence. It looks like it spent quite a few hours on the frontpage overnight, but I had no idea it existed! In any case the Launch HN was scheduled before that.
(Btw, I don't think that "using it made them crash" is correct - https://news.ycombinator.com/item?id=45010327)
Hmm I don't think use whilst driving should be the first thing they should point market.
[flagged]
> amazing that stuff like this still gets funded. This sounds like a 2 day project
Ai yai yai - you can't dismiss someone's work that way, especially not in launch threads. HN has additional rules when people are sharing their work, because it's particularly important not to be a jerk in such threads. If you'd please review https://news.ycombinator.com/showhn.html as well as https://news.ycombinator.com/newsguidelines.html, we'd appreciate it. Thoughtful criticism is fine, of course, but supercilious dismissals are something we'd really like people to avoid here.
[flagged]
Edit: when I replied to the parent comment, it consisted of the text "she?" and nothing else. (If you're going to edit a comment once it has replies, please do it in a way that allows the replies to preserve their original context. For example, you can always add "Edit" and then post additional text.)
---- original reply: ----
Can you please not post like this? We want substantive, thoughtful discussion on this site.
https://news.ycombinator.com/newsguidelines.html
Edit: the top text had this bit which I've replaced now:
“she” (sorry, I can’t help anthropomorphizing) can