Launching today
Latch.ai
Automate complex accounting work without a single prompt
325 followers
Automate complex accounting work without a single prompt
325 followers
Latch is built for accountants buried in click-heavy close work. Instead of writing prompts, you do a task on screen and talk it through, including the parts no SOP captures: the three-day matching window, the rate you always override. Latch asks about the exceptions, then builds a sidekick that runs the task the same way every time, right in the tools you already use. When something doesn't fit, it stops and asks you. Every step is logged for review.
Free Options
Launch Team / Built With
Render Sandboxes: a computer for every agentGive every agent its own machine. Starts in under a second
Promoted
Hi everyone, I'm Sam, head of product and customer success at Latch.
Handing a task to automation is a big ask, especially when it touches your books. So we built a safe place to try Latch first: a sample invoicing sidekick, ready in the app.
It works through a week of orders for a fictional coffee roaster and turns them into invoices. Along the way, it hits a couple of messy situations, the kind real orders always have, and stops to ask you how to handle them. That's the best way to get a feel for working with a sidekick: watching it follow the steps, then checking in with you when a decision is yours to make.
When you try it out, you'll see an Excel sheet with the demo data ready for download, so all you need is access to Excel. No accounting system to connect, no real data to share, and it runs in about a minute.
When you're ready, teach Latch one of your own tasks. If you get stuck, reply here and I'll help.
What would you want to see a sidekick do before trusting it with your real work?
when latch hits an exception it has not seen before and stops to ask, does your answer get saved for the next run?
@neerajnathany Great question. Not automatically yet, but it’s on the roadmap: turning your answer into a rule the sidekick follows next time. The idea is that it proposes the rule and you approve it, so a sidekick’s behavior never changes without you knowing. In the meantime, you can give the sidekick guidance on how to handle a specific exception between runs, and it rebuilds to handle it from then on. Is there a specific exception you’re thinking of?
@sam_voahbst propose-then-approve sounds like the right way to keep behavior from shifting quietly. will the proposed rule show which run it came from?
Does this fit to early-stage companies like @Clocknext where founders manage accounts. No finance person at the moment.
@aaron_pennell Would to see the demo! Will book a call.
In my previous company we spent a ton of time building accounting system integrations, and even after that, many operations required multi-step manual workflows to move CSVs and reports around from one system to another. End of month close and remediating credit balances was a real pain. I'm excited to see some practical application of AI for day to day tasks in the accounting work, where accuracy and auditability are paramount but a lot of the work to achieve that is very repetitive!
@bedejordan Thank you, this really resonates. It’s actually part of Latch’s origin story. When we talked to early customers, the thing they complained about most wasn’t any one tool. It was the layer between their tools: exporting a report, cleaning up a CSV, moving it into the next system, checking it against something else. Integrations rarely cover that layer, so it falls to people. That’s the problem space we chose to build in.
Sidekicks take on that in-between work. You show Latch the steps once, it runs them the same way every time, and every run leaves a step-by-step log you can review, so you keep the accuracy and auditability without doing the repetition yourself.
Remediating credit balances sounds like a great example. What did that process look like at your last company?
Fantastic! Since the time of RPA, we've all been waiting for a simple system that could just watch, listen, and then intelligently reproduce workflows. And it's finally here!
@sean_robinson1 Thanks, Sean! RPA got the “watch” part, but it only ever replayed the clicks. What was missing was the why: the exceptions and judgment calls people explain out loud but never write down. That’s what the narration captures, and it’s why a sidekick can stop and ask when something doesn’t fit instead of breaking.
Congratulations to the Latch team! I’ve done manual data entry for my accounting coursework, so I get why this matters. This seems like a great tool for improving efficiency, and I would love to try it!
@megan_hunyadi Thanks Megan! Freeing people from tedious work like data entry is one of the things that drives our team. One of our beta customers used to work all weekend to get the month-end close done. Now they have their weekends back. If you’d like to try it, there’s a sample invoicing sidekick in the app that runs on demo data, so you can see how it works without connecting anything of your own. Let us know what you think!
See it learn from someone doing a demo and emphasizing exceptions to take into account made the idea make sense. Seems like a super great tool.