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

{
  "author": "fchishtie",
  "hn_item_id": 48280729,
  "external_url": "https://www.minicor.com/"
}

{
  "by": "fchishtie",
  "id": 48280729,
  "url": "https://www.minicor.com/",
  "kids": [
    48281424,
    48284931,
    48285501,
    48283589,
    48282234,
    48283086,
    48282874,
    48281927,
    48283417,
    48281030,
    48282098,
    48283380,
    48285080,
    48281995,
    48282859,
    48286456,
    48284275,
    48281031,
    48282322
  ],
  "text": "Hey we’re Faiz and Saheed and we built Minicor so AI companies who need to integrate to desktop systems with no API can quickly build scalable desktop RPAs. Demo: <a href=\"https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=MD0GHZIJ1cw\" rel=\"nofollow\">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=MD0GHZIJ1cw</a><p>We were working on non-RPA integrations when a customer promised to sign a deal in 2 days if we could unblock a sale of theirs that involved integrating with a clinic’s Windows based medical record system. We didn’t know it at the time but it turns out that building desktop RPAs at scale is extremely difficult because scripting is hard (learning the system, defining the automation, UIs changing constantly), orchestration is hard (is the VM up? queuing, parallelizing) and debugging is hard (zero observability, false positives, cascading failures). 30%+ failure rates are not uncommon. At scale we’ve seen cases of failed RPAs leading to thousands of support tickets a month.<p>To solve the problems we were facing, we built an MCP that Claude Code&#x2F;Codex can use to navigate a virtual machine running desktop software with Python to create RPA workflows. The RPA workflows run as Python scripts for speed, cost, and determinism. These workflows can be triggered by API following any input&#x2F;output schema specified, with video replays and logs stored with each run. The MCP can debug RPAs and make changes to the underlying code, all of which are version controlled. We also built tools for cloning VMs for parallelizing RPAs, and handling 2FA&#x2F;OTP challenges. Plus since workflows are code based: we were also able to add triggers for Slack notifications, human-in-the-loop steps, or call an LLM to verify the state of a VM by passing a screenshot.<p>Would love to hear your feedback and if you have any RPA horror stories! (:",
  "time": 1779807447,
  "type": "story",
  "score": 62,
  "title": "Launch HN: Minicor (YC P26) – Windows desktop automations at scale",
  "descendants": 44
}

{
  "id": "7bfa6ba5-d401-4c60-9774-745ee6f3ae2f",
  "daily_ranking_item_id": "9745eac4-6448-4c2f-8d0f-ce49d27041e0",
  "source": "hacker_news",
  "external_id": "48280729",
  "fetched_at": "2026-05-26T22:01:17.261Z",
  "story_raw": {
    "by": "fchishtie",
    "id": 48280729,
    "url": "https://www.minicor.com/",
    "kids": [
      48281424,
      48284931,
      48285501,
      48283589,
      48282234,
      48283086,
      48282874,
      48281927,
      48283417,
      48281030,
      48282098,
      48283380,
      48285080,
      48281995,
      48282859,
      48286456,
      48284275,
      48281031,
      48282322
    ],
    "text": "Hey we’re Faiz and Saheed and we built Minicor so AI companies who need to integrate to desktop systems with no API can quickly build scalable desktop RPAs. Demo: <a href=\"https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=MD0GHZIJ1cw\" rel=\"nofollow\">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=MD0GHZIJ1cw</a><p>We were working on non-RPA integrations when a customer promised to sign a deal in 2 days if we could unblock a sale of theirs that involved integrating with a clinic’s Windows based medical record system. We didn’t know it at the time but it turns out that building desktop RPAs at scale is extremely difficult because scripting is hard (learning the system, defining the automation, UIs changing constantly), orchestration is hard (is the VM up? queuing, parallelizing) and debugging is hard (zero observability, false positives, cascading failures). 30%+ failure rates are not uncommon. At scale we’ve seen cases of failed RPAs leading to thousands of support tickets a month.<p>To solve the problems we were facing, we built an MCP that Claude Code&#x2F;Codex can use to navigate a virtual machine running desktop software with Python to create RPA workflows. The RPA workflows run as Python scripts for speed, cost, and determinism. These workflows can be triggered by API following any input&#x2F;output schema specified, with video replays and logs stored with each run. The MCP can debug RPAs and make changes to the underlying code, all of which are version controlled. We also built tools for cloning VMs for parallelizing RPAs, and handling 2FA&#x2F;OTP challenges. Plus since workflows are code based: we were also able to add triggers for Slack notifications, human-in-the-loop steps, or call an LLM to verify the state of a VM by passing a screenshot.<p>Would love to hear your feedback and if you have any RPA horror stories! (:",
    "time": 1779807447,
    "type": "story",
    "score": 62,
    "title": "Launch HN: Minicor (YC P26) – Windows desktop automations at scale",
    "descendants": 44
  },
  "stats_raw": {
    "time": 1779807447,
    "score": 62,
    "descendants": 44
  },
  "aux_raw": {
    "external_url": "https://www.minicor.com/",
    "hn_comment_url": "https://news.ycombinator.com/item?id=48280729",
    "normalized_text": "Hey we’re Faiz and Saheed and we built Minicor so AI companies who need to integrate to desktop systems with no API can quickly build scalable desktop RPAs. Demo: https://www.youtube.com/watch?v=MD0GHZIJ1cw We were working on non-RPA integrations when a customer promised to sign a deal in 2 days if we could unblock a sale of theirs that involved integrating with a clinic’s Windows based medical record system. We didn’t know it at the time but it turns out that building desktop RPAs at scale is extremely difficult because scripting is hard (learning the system, defining the automation, UIs changing constantly), orchestration is hard (is the VM up? queuing, parallelizing) and debugging is hard (zero observability, false positives, cascading failures). 30%+ failure rates are not uncommon. At scale we’ve seen cases of failed RPAs leading to thousands of support tickets a month. To solve the problems we were facing, we built an MCP that Claude Code/Codex can use to navigate a virtual machine running desktop software with Python to create RPA workflows. The RPA workflows run as Python scripts for speed, cost, and determinism. These workflows can be triggered by API following any input/output schema specified, with video replays and logs stored with each run. The MCP can debug RPAs and make changes to the underlying code, all of which are version controlled. We also built tools for cloning VMs for parallelizing RPAs, and handling 2FA/OTP challenges. Plus since workflows are code based: we were also able to add triggers for Slack notifications, human-in-the-loop steps, or call an LLM to verify the state of a VM by passing a screenshot. Would love to hear your feedback and if you have any RPA horror stories! (:",
    "external_article": {
      "title": "Minicor | Scalable Desktop Automations",
      "excerpt": "The RPA platform for deploying AI into legacy systems\n\nRadically reduce error rates with self-healing agents.\n\nWhen 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.\n\nWriting RPAs isn't hard. Maintenance is the killer.\n\nComputer use agents that run on Windows VMs or in the browser. On-premise, cloud, or Citrix. One API call triggers execution.\n\nSame architecture running in production at 25,000 patients/day.\n\nReplay full video recordings of every automation run. Get failure notifications directly in Slack. Debug with screenshots and full execution context instead of guessing.\n\nFrom API call to desktop automation running on a Windows VM. Here's what happens under the hood.\n\nOne API call triggers a full desktop workflow. Send the workflow ID and data, get structured JSON back. No SDK, no browser extension.\n\nOne API call triggers a full desktop workflow. Send the workflow ID and data, get structured JSON back. No SDK, no browser extension.\n\nCustomers go from zero to prod",
      "final_url": "https://www.minicor.com/",
      "fetched_at": "2026-05-26T22:01:10.009Z",
      "description": "Deploy self-healing computer use agents that adapt when UIs change. Zero to production in hours."
    },
    "selected_comments": [
      {
        "id": 48281424,
        "raw": {
          "by": "polonbike",
          "id": 48281424,
          "kids": [
            48281546
          ],
          "text": "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.",
          "time": 1779810678,
          "type": "comment",
          "parent": 48280729
        },
        "body": "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.",
        "is_op": false,
        "author": "polonbike",
        "raw_body": "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.",
        "created_at": 1779810678,
        "reply_count": 1
      },
      {
        "id": 48284931,
        "raw": {
          "by": "oveja",
          "id": 48284931,
          "text": "For those confused like I was, RPA stands for Robotic Process Automation.",
          "time": 1779824433,
          "type": "comment",
          "parent": 48280729
        },
        "body": "For those confused like I was, RPA stands for Robotic Process Automation.",
        "is_op": false,
        "author": "oveja",
        "raw_body": "For those confused like I was, RPA stands for Robotic Process Automation.",
        "created_at": 1779824433,
        "reply_count": 0
      },
      {
        "id": 48285501,
        "raw": {
          "by": "nthdesign",
          "id": 48285501,
          "kids": [
            48286120
          ],
          "text": "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.",
          "time": 1779827089,
          "type": "comment",
          "parent": 48280729
        },
        "body": "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.",
        "is_op": false,
        "author": "nthdesign",
        "raw_body": "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.",
        "created_at": 1779827089,
        "reply_count": 1
      },
      {
        "id": 48283589,
        "raw": {
          "by": "throw03172019",
          "id": 48283589,
          "kids": [
            48283653
          ],
          "text": "Biggest question is how much of this can be stored &#x2F; processed on our own infra and with our own lifecycle rules?  For example, this can touch a lot of PHI. Screenshots, videos, JSON inputs&#x2F;outputs etc.",
          "time": 1779819412,
          "type": "comment",
          "parent": 48280729
        },
        "body": "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.",
        "is_op": false,
        "author": "throw03172019",
        "raw_body": "Biggest question is how much of this can be stored &#x2F; processed on our own infra and with our own lifecycle rules?  For example, this can touch a lot of PHI. Screenshots, videos, JSON inputs&#x2F;outputs etc.",
        "created_at": 1779819412,
        "reply_count": 1
      },
      {
        "id": 48282234,
        "raw": {
          "by": "dragonsenseiguy",
          "id": 48282234,
          "kids": [
            48282301
          ],
          "text": "Small website nitpick: I feel like the &quot;In production with&quot; section&#x27;s companies logos should be a bit darker, I could barely tell there was something there.",
          "time": 1779813920,
          "type": "comment",
          "parent": 48280729
        },
        "body": "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_op": false,
        "author": "dragonsenseiguy",
        "raw_body": "Small website nitpick: I feel like the &quot;In production with&quot; section&#x27;s companies logos should be a bit darker, I could barely tell there was something there.",
        "created_at": 1779813920,
        "reply_count": 1
      }
    ],
    "presentation_fields": {
      "title": "Launch HN: Minicor (YC P26) – Windows desktop automations at scale",
      "tagline": "www.minicor.com",
      "website_url": "https://www.minicor.com/",
      "canonical_url": "https://news.ycombinator.com/item?id=48280729"
    },
    "external_url_hostname": "www.minicor.com",
    "selected_comments_raw": [
      {
        "by": "polonbike",
        "id": 48281424,
        "kids": [
          48281546
        ],
        "text": "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.",
        "time": 1779810678,
        "type": "comment",
        "parent": 48280729
      },
      {
        "by": "oveja",
        "id": 48284931,
        "text": "For those confused like I was, RPA stands for Robotic Process Automation.",
        "time": 1779824433,
        "type": "comment",
        "parent": 48280729
      },
      {
        "by": "nthdesign",
        "id": 48285501,
        "kids": [
          48286120
        ],
        "text": "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.",
        "time": 1779827089,
        "type": "comment",
        "parent": 48280729
      },
      {
        "by": "throw03172019",
        "id": 48283589,
        "kids": [
          48283653
        ],
        "text": "Biggest question is how much of this can be stored &#x2F; processed on our own infra and with our own lifecycle rules?  For example, this can touch a lot of PHI. Screenshots, videos, JSON inputs&#x2F;outputs etc.",
        "time": 1779819412,
        "type": "comment",
        "parent": 48280729
      },
      {
        "by": "dragonsenseiguy",
        "id": 48282234,
        "kids": [
          48282301
        ],
        "text": "Small website nitpick: I feel like the &quot;In production with&quot; section&#x27;s companies logos should be a bit darker, I could barely tell there was something there.",
        "time": 1779813920,
        "type": "comment",
        "parent": 48280729
      }
    ]
  },
  "selection_meta": {
    "discussion_depth": "top_comments_v1",
    "external_article": {
      "status": "ok",
      "final_url": "https://www.minicor.com/",
      "status_code": 200,
      "content_type": "text/html; charset=utf-8",
      "failure_reason": null
    },
    "snapshot_version": "hn_story_v3",
    "selected_comments_count": 5,
    "external_article_resolved": true,
    "text_normalization_applied": true
  },
  "created_at": "2026-05-26T22:01:17.511Z",
  "updated_at": "2026-05-26T22:01:17.511Z"
}