Minicor

Competitive Intelligence & Product Roadmap

Self-healing desktop automation for legacy systems.

Company Overview

Minicor is a desktop automation platform that wraps legacy Windows and browser workflows in API-callable, self-healing runs. Serving AI and B2B software teams selling into healthcare, automotive, logistics, and finance where write APIs are missing.

Latest Intel

Zeitgeist tracks private signals to determine where the company is heading strategically.

New Intel: Minicor is using agents as a recovery layer around deterministic desktop workflows. That makes UiPath, Browserbase, Anthropic, and OpenAI all relevant comparables, but the buyer pays for completed writeback, not model access.

May 18, 2026

Deployment Bottleneck

Confidence:

Medium

New Intel: Minicor is building customer-facing deployment capacity around legacy desktop automation. That opens regulated and operational markets, but it also reveals the margin risk: every ugly Windows workflow may need expert handling.

What They're Building

The company's public product roadmap & what they're committed to building.

MCP Server per Workspace

Minicor plans workspace-level MCP support so coding agents and developer tools can trigger desktop workflows through a standard interface.

AI-Powered RPA Testing

The company plans testing tools for desktop workflows, a logical extension of its trace, replay, and recovery system.

Git Integration

Planned Git support would make workflow definitions easier to version, review, and manage like application code.

OpenAPI Spec Generation

OpenAPI generation would turn legacy desktop workflows into cleaner API surfaces for software teams.

Visual Diff Viewer

A planned visual diff viewer would help teams inspect UI changes that break or alter desktop automations.

Founder and Key Execs

Faizaan Chishtie

Co-Founder and CEO (former early engineer at YC companies, worked on system integrations)

Saheed Akinbile

Co-Founder and CTO (infra, RPA, QuickBooks, Sage, Citrix, and browser automation experience)

Founder Force Multiplier

Faizaan Chishtie brings early YC engineering and integration experience, while Saheed Akinbile brings infra and RPA depth across desktop and browser systems. That mix fits a product where reliability depends on both customer workflow knowledge and execution infrastructure.

Funding History

2026 | Backed by Y Combinator Spring/P26
Unknown | Prior pre-seed or seed backing from NOMO Ventures investors Rahul Prakash and Kate Rohacz, amount not found

Notable Open Roles

Forward Deployed Engineer

This points to a deployment model where customer-specific workflow setup, production rollout, and exception handling are core to revenue quality.

Product Engineer

This suggests the platform still needs builders who can turn repeated implementation patterns into reusable product surfaces.

Competitors

UiPath:

UiPath is the established RPA platform Minicor contrasts against by arguing that selector-driven automation breaks under UI changes.

Anthropic:

Anthropic provides computer-use models, while Minicor packages agent recovery around deterministic desktop workflows.

OpenAI:

OpenAI offers general model capability, while Minicor focuses on production execution inside legacy Windows and browser environments.

Browserbase:

Browserbase focuses on browser automation, while Minicor also targets native desktop apps, Citrix, and RDP workflows.

Minicor

's Moat:

Candidate moat is workflow switching costs: each deployed desktop run creates customer-specific scripts, traces, and recovery memory that become painful to replace if reliability holds.

How They're Leveraging AI

Agentic Recovery for Desktop Workflows

Minicor uses agents to recover from broken or uncertain desktop automation steps in legacy Windows, browser, Citrix, and RDP environments. The user-facing value is completed writeback into systems that were never designed for API access.

Two-Model Visual Grounding for Click Accuracy

Minicor separates reasoning from visual grounding so desktop agents can decide what to do and then click the right thing on screen. That matters in legacy UI environments where selectors are brittle or missing.

Retrieved Memory for Repeated Automation Runs

Minicor stores successful task trajectories and retrieves similar prior runs to make repeated workflows faster and less error-prone. The strongest data advantage is customer-specific workflow memory.

AI Use Overview:

Minicor keeps automations deterministic and uses agents for recovery, with a reasoning model choosing actions, a vision model grounding clicks, and embedding memory retrieving prior trajectories.

Personal AI, Desktop Agents, and Consumer AI

Discord

Real-time voice, video, and text chat platform built around persistent community servers.

The deepest engagement metrics in consumer social (94 minutes per day) combined with a pre-IPO path and untapped advertising plus developer monetization surface area.

Button Computer

A privacy-first wearable AI that only listens when pressed, no always-on mic or cloud needed.

Humane and Rabbit tried always-on AI wearables and both failed on privacy and form factor. Button only listens when physically pressed, which is a better privacy model, and two ex-Apple Vision Pro engineers know how to ship hardware that people actually wear.

Carrot Labs

Keeps production AI agents reliable by continuously fine-tuning against business metrics.

Most AI agent teams monitor in production and fine-tune separately. Carrot Labs closes the loop: it evaluates agent performance against business metrics and selectively retrains, which means the agent improves without a human deciding what to fix.

Glue

A visual canvas for designing, debugging, and collaborating on AI agent workflows.

Figma does not understand agent logic. LangChain does not have a visual canvas. Glue sits at the intersection: a drag-and-drop interface for designing, debugging, and collaborating on AI agent workflows with reasoning visualization built in.

Back To All Companies >