How to play: Some comments in this thread were written by AI. Read through and click flag as AI on any comment you think is fake. When you're done, hit reveal at the bottom to see your score.got it
Congrats on the launch. One complaint: RPA this, non-RPA that, but you never explain what it means. I would write down the acronym fully once at the first mention on the landing page.
I think their target audience is medium to large enterprises. The biggest tell tale sign of that is a missing Pricing page.
Most of these customers would already know the meaning of RPA, if they are researching companies for it. In a way, it self qualifies their leads into higher quality ones, that are more likely to convert.
Missing pricing doesn't qualify leads, it just loses them. Plenty of enterprise buyers skip vendors who hide numbers, because they've been burned before by products they couldn't afford.
RPA was a big thing just towards the tail end of 2010s, though. MS had free official tools for Windows 10 to do it. I think at some point a Japanese bank had a robotic arm set up to flip a contract binder, scan the page and stamp it page by page using RPA.
Biggest question is how much of this can be stored / processed on our own infra and with our own lifecycle rules? For example, this can touch a lot of PHI. Screenshots, videos, JSON inputs/outputs etc.
Does this only revert back to LLM Vision when it catches an error? I.e once the RPA / workflow is built once, it’s efficient for running multiple times (until it catches an error state)?
yes effectively, but we use LLM vision in multiple places - for context, there are multiple ways an RPA can fail:
1. RPA code breaks (ex: throws an exception if a window does not exist)
2. RPA reports success but was clicking / typing in the wrong place
3. Underlying system breaks (virtual machine / legacy software)
the skill we have in our MCP is to build the RPA code to throw exceptions where possible so an LLM can understand the context and recover
to avoid false success states we add LLM vision steps in the workflow itself to error out if it sees that the system is in the wrong state
and for the underlying system breaking it can be as simple as having a CRON job that checks the status of the process / the health of the VM and running a script to reboot the system
it depends on the system but the pattern we've seen with RPAs is you can catch maybe 80% of the edge cases in the first week it's been rolled out
Small website nitpick: I feel like the "In production with" section's companies logos should be a bit darker, I could barely tell there was something there.
Language change through frequency is well-documented, but there's a difference between descriptive acceptance and actively adopting the error yourself. Technical writing in particular should hold the line.
54% of Americans read below a 6th grade level. People word-mash "alot", "atleast", and now "eachother" all the time. Sports commentators use verse when they mean versus.
I'm not suggesting that you correct your customers, but there's no reason to sink to the lowest common denominator when writing.
Can you compare Minicor to Convey? They seem very similar. We had a product demo of Convey wherein they showed us how you could train the agent to use legacy software using a simple shared screen capture and verbal instructions.
great question - Minicor doesn’t offer any agents for performing the automation - we focus exclusively on connecting coding agents to the legacy system and using our MCP to build code based automations for doing so at scale - trying to solve the 30% error rate in robotic process automations
Is the cloud LLM the judge based on screenshots with patient/customer data included ? That seems like a no-go for many countries given privacy concerns ?
No patient/customer data included in the screenshots - in production we’d basically find some “region” of the screen to screenshot that would help an LLM say yes/no to - ex: “is the nav bar green and does it say Insert Note”
Ok, that seems doable if working perfect, but what is the tool output "i can see the patient list with search functionality and 30 patients" thing in the demo ? Is this not vision detected ? Or are you digging into windows api (making non standard windows components/widgets non working)?
i'm curious: how does the steady state error rate of a stochastic automated system like this compare with the downtime and errors that come from a (brittle) deterministic bridge that can fail with upgrades? what does the observability look like? (i'm guessing one feature is that the execution log including images/screenshots for each transaction gets saved, which is probably a huge improvement.)
it’s a good q - we experimented a lot with computer use / agentic automation and found that at scale a hybrid solution where the automations run as deterministic code with agents for recovery is the best - running automations as code is faster & cheaper & when you’re doing critical tasks (like updating patient records) you don’t want an agent to potentially mess something up.
previously writing RPA code used to take a long time - using AI (and its infinite patience) we can write more durable code that covers more edge cases
And since they’re code based it’s pretty straightforward to an agents monitor them and update their code when upgrades to the underlying system happen etc…
for observability - we have workflow execution logs that store text, videos and screenshots so an agent or a human can debug them - lots and lots of webhooks when things break ! (:
I also experimented with vision/screenshot based computer use tools for similar use cases but had inconsistent results. LLMs had trouble getting precise pixel coordinates from a screenshot to move a mouse. And the screenshots took extra tokens. I had a lot more success using accessibility APIs to replace screenshots + input simulation since accessibility data is easier for LLMs to process. The accessibility functionality is now released as a separate library for building automation tooling: https://xa11y.dev/
that sounds like the way. also keeps runtime costs down. seems like the trick there would be to build (a|on top of) durable rpa librar(y|ies) that the agents and humans work in so that the automation recipes and their automated updates can be quickly skimmed and sanity checked when needed. add in some live automated testing (assuming you can make this happen with the legacy systems) and maybe you could get really close to fully automating all of it.
we’ve found that existing RPA platforms were built more for business users/citizen developers at really massive enterprises - we’re more focused on the developer experience for building RPAs at scale
I've found that legacy system users (or at least the execs) are pretty excited about AI because they hate their legacy systems but can't really do anything about it (ERP changes are an extreme nightmare, and often no better system exists with all the capability they need). They want to wrap it in AI to automate stuff without changing out the core system.
This seems like a good approach to me, I work with a lot of legacy ERP-using companies in the manufacturing sector and can immediately see how we could put this to use for our customers.
I especially like that it's not doing computer use for everything which so far doesn't really seem to be working, especially outside the browser.
Legacy system users are also the one who pays the most for tools and services. We sell to enterprise, I can attest to that. If it is relevant usecase and positioning for the market, it should be fine.
yeah it’s been interesting to watch, we were surprised initially at how much legacy users actually wanted to adopt AI - I think it’s because of how awful the old software can be to interact with
100% right - we support the AI companies who are selling to the legacy end users - for ex: we don’t sell directly to hospitals, but an AI scribe for doctors that already has a hospital as a customer, we help them integrate to the hospital’s EMR
Adoption solves itself eventually. What doesn't solve itself is the unexpected dialog box at 3am that silently kills your batch job and nobody notices until end of day.
We think CyberDesk is great - our main difference is I believe the primary driver for their automations is computer use / agent based - whereas our automations use agents to create/maintain/support python code
Just 1 day ago a person reached out to me making exactly same product. Exactly the same. They were based out of Europe. But it's good to see you got into YC. Congratulations.
Minor nit: RPA and desktop automation aren't quite the same thing. RPA implies orchestration, scheduling, attended/unattended modes. Desktop automation is just UI scripting. Though the line's blurry enough that most people use them interchangeably now.
