Launch HN: Minicor (YC P26) – Windows desktop automations at scale

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.

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)?

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.

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 ?

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.)

How does this compare with CyberDesk (also YC)?

Congrats on the launch! Legacy system users are also one of the slowest to adopt AI. How do you navigate that?

So AI companies would install this on their customer (practices) computers?

Could you use this to test new releases of software for bugs? A bit like TDD but for GUI interactions

Computer use agents that run on Windows VMs or in the browser. On-premise, cloud

I think you meant premises.

https://brians.wsu.edu/2016/05/30/premise-premises/

Please make your trust center public if you are focusing on healthcare AI companies…the footer link is dead.

What the deuce is an "RPA"?

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.

Thank you!! Yeah that's a good point - it's been so engrained in our brains, appreciate the feedback

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 ! (:

So AI companies would install this on their customer (practices) computers?

How does this compare with CyberDesk (also YC)?

Yes, more likely on a virtual machine running the legacy software

logs get written in our customers' premises on a bucket of their choosing (: so PHI doesn't leave their VPC

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

Congrats on the launch! Legacy system users are also one of the slowest to adopt AI. How do you navigate that?

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

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.

Please make your trust center public if you are focusing on healthcare AI companies…the footer link is dead.

Thanks for flagging this!

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.

yes good call out - that customer wheel is so overdue for an update

Computer use agents that run on Windows VMs or in the browser. On-premise, cloud

I think you meant premises.

https://brians.wsu.edu/2016/05/30/premise-premises/

I’ve never heard a customer say “on-premises” when talking about servers they run. On-premise is usually the term regardless if it is “correct”.

thank you - good catch (:

Could you use this to test new releases of software for bugs? A bit like TDD but for GUI interactions

Yes! we have customers doing that

What the deuce is an "RPA"?

Its an acronym for Robotic Process Automation. It usually means triggering mouse clicks and key stokes to perform tasks

It's a script that simulates clicks/keystrokes on Desktop/Web

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”

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 ! (:

Yes, more likely on a virtual machine running the legacy software

Thanks. Most practices are not tech savvy. So how would the VM setup work in their own network / machines?

logs get written in our customers' premises on a bucket of their choosing (: so PHI doesn't leave their VPC

Thanks for flagging this!

yes good call out - that customer wheel is so overdue for an update

yes effectively, but we use LLM vision in multiple places - for context, there are multiple ways an RPA can fail:

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

thank you - good catch (:

It's a script that simulates clicks/keystrokes on Desktop/Web

Yes! we have customers doing that

Its an acronym for Robotic Process Automation. It usually means triggering mouse clicks and key stokes to perform tasks

That’s perfect. Is this documented somewhere? Would love a deep dive on security / setup tweaks for data.

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

I’ve never heard a customer say “on-premises” when talking about servers they run. On-premise is usually the term regardless if it is “correct”.

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.

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)?

Thanks. Most practices are not tech savvy. So how would the VM setup work in their own network / machines?

Yeah that’s true - in those cases we’ve either worked with their outsourced IT provider to spin up VMs for us or have had to spin up our own VM and connect through a VPN - IT can be very fun…

That’s perfect. Is this documented somewhere? Would love a deep dive on security / setup tweaks for data.

happy to share more over email! you can reach me at faiz@minicor.com

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

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.

ah for the fake EMR demo I was a bit less strict with claude, it was vision detected likely - our MCP has tools for taking screenshots of the screen and inspecting the windows accessibility tree etc

Yeah that’s true - in those cases we’ve either worked with their outsourced IT provider to spin up VMs for us or have had to spin up our own VM and connect through a VPN - IT can be very fun…

happy to share more over email! you can reach me at faiz@minicor.com

ah for the fake EMR demo I was a bit less strict with claude, it was vision detected likely - our MCP has tools for taking screenshots of the screen and inspecting the windows accessibility tree etc

Go Live With Any Customer

The RPA platform for deploying AI into legacy systems

[

Book a Demo

](https://www.minicor.com/book-demo)

In production with

Build RPA in minutes

Radically reduce error rates with self-healing agents.

Unlock Growth

Minicor builds and maintains desktop automations so your teams can focus on closing deals and shipping product.

Self-Healing Agents

When a UI changes or an unexpected dialog appears, the agent catches it, adapts, and keeps going. A reflection agent verifies every action against what's on screen and self-corrects before the workflow breaks. No more rebuilding scripts every time a vendor ships an update.

Writing RPAs isn't hard. Maintenance is the killer.

Deploy Anywhere

Computer use agents that run on Windows VMs or in the browser. On-premise, cloud, or Citrix. One API call triggers execution.

Same architecture running in production at 25,000 patients/day.

Built-in Observability

Replay full video recordings of every automation run. Get failure notifications directly in Slack. Debug with screenshots and full execution context instead of guessing.

Debug with context, not guesswork.

Under the Hood

How Minicor Works

From API call to desktop automation running on a Windows VM. Here's what happens under the hood.

Ready to Unblock Your Pipeline?

Customers go from zero to production in days. If RPAs are holding you back, let's talk.

Or just email us at connect@minicor.com

Frequently Asked Questions

Minicor is a platform for building and running desktop automations at scale with computer use agents. AI companies selling into healthcare, automotive, logistics, and financial services need to read and write to their customers' systems of record. These are old desktop applications with no APIs. Minicor automates them reliably so companies can go live in weeks.

Most legacy desktop systems like EHRs, ERPs, DMS, and PMS have no writable API and never will. Some vendors are actively restricting third-party API access. The only way to read or write data is to interact with the desktop like a human would. That is the problem Minicor solves.

Building one RPA is not hard. Running hundreds reliably is. UIs change, edge cases pile up, errors cascade. At scale, even small error rates become catastrophic. Engineering teams end up spending all their time maintaining automations instead of building their core product.

Traditional RPA vendors use brittle scripts that break when UIs change. Computer use models work for demos but fall apart in production at 80-85% accuracy because they figure everything out from scratch every time. Minicor stores automation as deterministic code and uses the agent only for recovery and edge cases. Faster and more accurate in production.

Minicor self-heals. A reflection agent verifies every action against what is on screen and self-corrects before mistakes cascade. When a vendor ships a UI update, the automation adapts instead of crashing. 93-96% click accuracy vs 80-85% for other approaches.

Zero to production in weeks. Install our Desktop Client, record a video of a human performing the workflow, and we handle everything after that. Traditional RPA and integration approaches typically take 4 or more months.

Yes. SOC 2 Type II certified and HIPAA compliant. For on-premise deployments, the entire platform is containerized and runs inside your network. No data leaves your perimeter.

Any legacy desktop or web application. Healthcare EMRs like Athena, Epic, Cerner, and PS Suite. Dental PMS like Open Dental and Dental Vision. Automotive DMS like CDK Global. Supply chain systems like SAP and HighJump. Home health systems like Wellsky and Home Care HomeBase. Financial services platforms for claims, banking, and underwriting.

Hacker Times