Writing
Technical writing on computer use agents, self-healing RPA, and healthcare EHR automation. From the team building Laminar.
Platform
Why Computer Use Agents Are the Future of Enterprise Desktop Automation
Enterprise desktop automation is shifting from brittle scripts to intelligent agents. Computer use agents will replace traditional RPA within five years.
One Engineer, Fifty Automations: Why Computer Use Agents Scale Better
Traditional RPA needs one engineer per three to five bots. With computer use agents that self-heal and learn, one engineer manages fifty or more. Here is why.
Production RPA Observability: Beyond Dashboards and Log Files
When a desktop automation fails, you need to see what happened on screen. Log files are not enough. Visual replay changes how fast you resolve issues.
The Bottleneck Is Not AI Capability. It Is Legacy System Deployment.
AI models work. The problem is getting their output into legacy systems never designed for programmatic access. Deployment is the real bottleneck.
Going from Zero to Production in Three Weeks
Our customers go live in three weeks, not three months. Here is what that timeline actually looks like and what makes it possible.
Observability for Desktop Automation: Why Logs Are Not Enough
When a desktop automation fails, you need to see what the screen looked like, not read a log file. Visual replay changes how fast you can investigate and resolve issues.
The Long Game: From Integration Layer to Something Bigger
Every workflow automated captures data about how legacy systems actually work. Over time, that understanding compounds into something more valuable than the integrations themselves.
Industry
Automating Insurance Claims Processing on Legacy Desktop Systems
Insurance claims run through legacy Windows applications with no API. Computer use agents automate these workflows without replacing the underlying system.
The ROI of Switching from Traditional RPA to Computer Use Agents
Companies switching from traditional RPA to computer use agents see faster deployment and lower maintenance. Here is how the ROI breaks down.
Why Your RPA Total Cost of Ownership Is Higher Than You Think
License fees are the beginning. Factor in maintenance, failed runs, and downtime. The true cost of traditional RPA is three to five times the sticker price.
Automating Legacy ERP Systems Without Touching the Source Code
Legacy ERP systems like SAP GUI and Oracle Forms were never built for automation. Computer use agents interact through the GUI, no source code access required.
The RPA Engineer Shortage Is a Scaling Problem, Not a Hiring Problem
One RPA engineer maintains three to five bots. That ratio makes scaling impossible. Computer use agents change the math to one engineer for fifty automations.
Why AI Companies Are Replacing RPA with Computer Use Agents
AI startups building on healthcare, logistics, and finance are switching from traditional RPA to computer use agents. The reason is not what you might expect.
The Hidden Cost of Keeping Legacy RPA Bots Running in Production
RPA vendors sell on build time. Nobody talks about the 90% of effort keeping bots alive after deployment. Here is what that maintenance actually costs.
Computer Use Agents vs Traditional RPA: A Practitioner's Comparison
Traditional RPA breaks when UIs change. Computer use agents see the screen and adapt. A side-by-side comparison from someone who has run both in production.
The 10/90 Rule of RPA: Building Is Easy, Maintaining Is Everything
Building an automation takes a week. Keeping it alive over 12 months is where all the time goes. The ratio is roughly 10% build, 90% maintain.
The Compound Failure Math That Makes Click Accuracy Critical
95% per-click accuracy sounds great. On a 20-step workflow, it means two out of three runs will have at least one misclick. Here is why recovery matters more than accuracy alone.
The Three Hardest Things About Production RPA
They have nothing to do with the automation itself. Detection, investigation, and ongoing resilience are what consume your engineering hours.
Silent Failures: When the Automation Runs Fine But the Data Is Wrong
The worst kind of failure is not a crash. It is when the automation completes 'successfully' and puts data in the wrong field. Nobody finds out for hours.
Why Hard-Coded RPA Breaks Every Time the UI Changes
Traditional RPA memorizes element positions and IDs. Computer use agents look at the screen. The difference matters every time a vendor pushes an update.
Infrastructure
Citrix and Remote Desktop Automation with Computer Use Agents
Citrix and RDP environments are common in enterprise. Computer use agents work through the visual interface, making them ideal for remote desktop automation.
Scaling Desktop Automation from Five Bots to Five Hundred
Most RPA deployments stall at a handful of bots. Scaling to hundreds requires orchestration and session management that traditional tools were not built for.
Running RPA at Scale Is a Distributed Systems Problem
You have a pool of Windows VMs. Requests come in through an API. Something needs to route, queue, health-check, and retry. This is not an automation problem. It is an infrastructure problem.
The Hidden Complexity of Windows VM Session Management
Session timeouts, memory leaks, OS updates at 3am, MFA prompts. Your automation can be perfect. The Windows environment will still break it.
Routing Desktop Workflows Across a Pool of VMs
One API call triggers execution. The platform handles routing, session state, and failover. Here is what that orchestration layer actually needs to do.
Architecture
How AI Agents Handle UI Changes That Break Traditional RPA Scripts
A vendor pushes a UI update and every RPA script breaks. Computer use agents that see the screen instead of reading selectors handle changes automatically.
Desktop Automation Without Selectors: How Vision-Based Agents Work
Traditional RPA relies on element selectors that break constantly. Vision-based computer use agents find elements by looking at the screen, like a human does.
Self-Healing Automation: What It Means Beyond the Marketing
Every automation vendor claims self-healing. Here is what actually happens under the hood when a production automation encounters something unexpected.
Why We Dropped the Planner from Our Agent Architecture
Most computer use agents use a planner-executor hierarchy. Modern LLMs are good enough that the extra layers are now overhead. Here is what we learned when we simplified.
Split Reasoning from Grounding: Why Two Models Beat One
Asking one model to both decide what to click and predict where it is on screen is asking it to do two very different jobs at once. We found that splitting them changes everything.
Why Every Action Needs a Verification Step
One missed click without a check cascades into five more bad actions. One missed click with a check gets caught in three seconds. The math is simple.
Your Agent Should Get Faster the More It Runs
The first time an agent navigates a system, it explores. The hundredth time, it should know the path. Most agents do not work this way.
When Clicking Is the Wrong Answer
Some tasks are fundamentally computational. Summing a spreadsheet column, parsing a PDF, renaming files. Clicking through a GUI for these is slow and fragile. The agent should know when to write code instead.
Healthcare
Computer Use Agents for Healthcare: Automating What APIs Cannot Reach
Healthcare runs on EHRs with no APIs. Computer use agents navigate these desktop applications visually, processing thousands of patient interactions daily.
HIPAA Compliant Desktop Automation for Healthcare AI Companies
Desktop automation on patient data requires SOC 2 and HIPAA compliance from day one. Here is what healthcare AI companies need from their automation platform.
EHR Integration Without an API: Solving the Last Mile for Healthcare AI
Most EHR systems have no usable API. Healthcare AI companies need to push data into them anyway. Computer use agents solve this last mile integration problem.
What Makes Healthcare EHR Automation Different
The stakes are different. The UIs are deceptive. Session management is brutal. Here is what you learn when you automate EHRs in production.
Why AI Companies Lose Deals (It Is Not the AI)
The AI works. The model generates the note, processes the invoice, classifies the document. Then the output needs to go into a legacy system with no API. That is where deals die.
Automating Clinical Documentation Without Breaking the Chart
Writing notes into an EHR is not a text-entry problem. It is a navigation and verification problem with text entry in the middle.
The 30-Second Constraint in Clinical Workflows
A doctor finishes a visit. The note needs to be in the chart before the next patient walks in. Most automation architectures cannot hit this window.