Scheduling is a constraint satisfaction problem disguised as email! It’s easy when it’s two people, one timezone, one channel. But it becomes a constraint satisfaction problem when inputs are unstructured natural language across multiple communication channels, constraints change mid-solve, and the objective function includes social dynamics that don't exist formally anywhere.
What if scheduling just happened? For example: a recruiter sends one message, and every interview across five candidates, three hiring managers, and two time zones gets booked, confirmed, and updated automatically. No links, no back-and-forth, no one spending hours with 20 emails. Everyone just gets the right invite at the right time, on whatever channel they actually use. That's what we built Vela to do.
You loop in Vela into your emails, SMS, WhatsApp, Slack, phone or integrate into an ATS etc and it takes over: reads context, checks calendars, proposes times, follows up when people ghost, and rebooks when things shift.
One of our first customers is a staffing firm that searched for a scheduling solution for almost eight years. Their coordinators manage hundreds of candidate-client interviews where each side needs separate email threads, separate Zoom accounts to avoid double-booking links, and calendar invites connecting parties who never directly communicate. A client reschedules one interview and it cascades into four others. A candidate responds on SMS to a thread that started on email. Vela solved this in just 10 minutes of onboarding.
The hardest part has been the data problem. Scheduling behavior varies enormously across populations. C-suite folks respond to email within hours and expect formal 3-option proposals. Truck drivers applying for logistics roles respond to SMS at odd hours from shared devices with "y tm wrks." The failure mode isn't parsing -- it's applying the wrong interaction pattern for the wrong segment and watching the conversation die. We've been building behavioral datasets from thousands of real interactions: response latency by role, channel preference by demographic, follow-up timing curves, how many options to propose before you hit decision paralysis. This data doesn't exist anywhere.
The core agent challenge is state across channels. When someone responds on SMS to a thread that started in email, Vela needs to unify identity, merge context, and continue without losing information. Phone numbers don't map cleanly to emails, people use nicknames on text, shared devices mean the responder might not be who you reached out to. Temporal NLU is its own problem -- "next Friday" means different things on Monday versus Thursday. We extract structured constraints from natural language and resolve against calendar state. When ambiguity can't be resolved, Vela asks -- but deciding when to ask versus infer depends on the stakes of getting it wrong.
We're live with paying enterprise customers and every client still surfaces edge cases that surprise us. Case studies on our site (https://tryvela.ai/case-studies/). You can check out a demo here: https://www.youtube.com/watch?v=MzUOjSG5Uvw.
We'd love feedback from anyone who's worked on multi-agent coordination, conversational AI across channels, or constraint satisfaction in messy real-world domains. Looking forward to your comments!
A lot of similar solutions came up in the early chatbot era, when Facebook published Ducking and it became trivial to parse dates from natural language. I also looked into building such a product in the time, but ultimately found it hard to find an entry to the market: Most people that actually need something like this do have secretaries (who will also schedule a lot of other things in regards to the meeting) and most other people that have a less severe form of that problem rarely want to actually pay for such a product.
[0]: https://claralabs.com
How is this better than spending 2-5 mins making a poll and letting people vote?
https://doodle.com has been around forever and doesn’t cost anything.
One is friction on the other side. With Doodle you're asking someone to click a link, open a UI, parse a grid of times, check boxes, and sometimes connect an account. That's a real ask, especially for someone external who has no relationship with the tool. With Vela they just reply "Tuesday works" in the thread they are already in.
But beyond reducing friction, Vela is also doing the actual coordination work: herding people, following up with non responders, suggesting specific times that work best (not just available ones), handling rescheduling, and closing the loop. It's closer to what a human coordinator does than what a poll does.
Our customers are mostly folks coordinating 30+ meetings a week across multiple people. For them, time spent compounds significantly.
Doodle is great too btw, but it really only works well when the people involved already know each other and at a small scale. Vela is built for the more complicated scenarios where companies have tried everything and decided nothing works but putting a team member on the job.
Do they have to click a link, open a tool, make an account, and work out where to type and what they’re allowed to say / what the chat bot will understand? And THEN say Thursday works?
Still trying to be polite but frankly a little surprised by your blind spots.
Then the recipients can reply to the email thread with "Thursday works".
Not affiliated with vela - just what I understand from their site and the comments on this page.
My very strong advice would be to pick one of these use cases and niche hard. Multi channel, multi party scheduling isnt a problem anyone thinks they have (even if they actually do). They wake up thinking they have 40 truck driver shifts to fill tomorrow.
Deputy cleaned up by going after rota scheduling for independent coffee shops. Logistics sounds like a great shout. Each have messy edge cases which you can develop a strong solution around but you'll get crushed trying to go horizontal in this space. Best of luck!
Was actually chatting with a large industrial staffing firm and they were saying the same thing that it was super painful to schedule 1000s of workers for drug tests and then shifts too!
Created a problem statement and then solved it with Gurobi, repo here: (https://github.com/aleda145/interview-scheduling-kontaktsamt...)
Agents feel like the perfect fit for the whole rescheduling loop that happens in the real world!
Have you had to use an optimization solver yet? If so, which one?
The only other alternative is a booking link but this, slows down business, doesnt work in many many real life situations and more :)
On the LLM point - agreed that context window alone doesn't cut it. The coordination and state management layer sits outside the model. We learned that the hard way early on.
generally when i give someone my calendar link, i'm pretty happy for them to just choose whatever time within those constraints. i like the future where everyone opts in ("i will meet as long as my preferences are considered") & there doesn't need to be any manual clicking/coordination whatsoever.
as a tidbit of feedback: are you explicitly targeting b2b? i would like to just sign up, but i'll book a demo if that's the only option :)
edit: after reading a bit more of description looks like yall are taking a similar approach, kudos!
[0] https://github.com/r33drichards/minizinc-mcp
[1] https://github.com/r33drichards/bocce-scheduler
We do not have a skill if thats what you meant?
Appreciate the note on the slogan, definetly thinking of revamping our landing page in the near future to speak more directly to our audience.