From Company Brain to an AI Operating System | by Carlos Chinchilla | Jun, 2026 | MediumSitemapOpen in appSign up<br>Sign in

Medium Logo

Get app<br>Write

Search

Sign up<br>Sign in

From Company Brain to an AI Operating System

Carlos Chinchilla

14 min read·<br>Just now

Listen

Share

Press enter or click to view image in full size

Most founders and company leaders wake up and open four or five tabs. The CRM to check the pipeline. The support inbox. Stripe. Analytics. A spreadsheet someone edited overnight.<br>A few minutes later, they have a sense of how things are going but are left wondering:<br>Are we on track?<br>What changed since yesterday?<br>What needs my attention first?<br>What’s about to go wrong?<br>If companies are already collecting data across different platforms and tools, why can’t we automate the process of organizing it and let AI answer these questions for us?<br>The Company Brain<br>Andrej Karpathy laid the intellectual foundation with his LLM Wiki pattern — markdown knowledge bases that agents maintain and navigate, where “the tedious part of maintaining a knowledge base is not the reading or the thinking — it’s the bookkeeping” [1]. Good answers get “filed back into the wiki as new pages” so knowledge compounds rather than evaporating.<br>Then YC gave the category a name, “The Company Brain,” as one of 15 categories in the Summer 2026 Requests for Startups:<br>“The biggest blocker to AI automation of companies is no longer the models, they just got so good so quickly. Now the blocker is the domain knowledge. Every company has critical know-how scattered everywhere. Some of it lives in people’s heads. Some of it is buried in old email accounts, Slack threads, support tickets, and databases… If we want every company to run on AI automation, we need a new primitive: a company brain… This isn’t a company-wide search or a chatbot over documents. It’s a living map of how a company works… I think every company in the world is going to need one.” [2]

Diana Hu, a YC partner, extended this:<br>“AI should not be a tool your company just uses. It should be the operating system your company runs on. Every important process in your company should be captured by an intelligent closed loop” [3].

Both hint at a similar architecture, and while we drew inspiration from it, we look to layer on top of it to answer the question:<br>What should a founder see at 8 a.m. when they need to know if the company is on track?

The AI Operating System uses the company brain as its memory layer. It pulls every signal into one place, turns raw events into a structured company knowledge base, runs rules and scripts to surface what matters, evaluates progress against company goals, and delivers role-specific briefings with next-best actions.<br>That is the system this post describes — it is what I’ve been working on at Digital Workers. We start by walking through the layers of the AI Operating System, then dive into the sandbox architecture that executes the agentic and non-agentic workflows running on top of the knowledge base.<br>The 5 Layers<br>The AI Operating System is built on a five-layer architecture.<br>Press enter or click to view image in full size

Layer 1: Centralize<br>The foundation is connecting every source. Current connectors include Stripe, Email, HubSpot, Salesforce, Zendesk, Google Analytics, Meta Ads, Google Ads, Google Sheets, call transcripts, social media, databases, and desktop files, among others.<br>Connectors are pull-first. They run on a schedule, poll each source API multiple times per day, and own retry logic, rate limiting, and error handling.<br>Each connector looks back up to 30 days on every run to fill in gaps. Events are stored in raw form into a data lake and never overwritten, so the knowledge base can be rebuilt from scratch if the enrichment logic changes later (more on enrichment in the next section).<br>Layer 2: Organize

Press enter or click to view image in full size

Entity resolution<br>Raw data is less useful if the same real-world entity — a customer, a deal, a company — is named differently across sources. This layer reconciles these scattered records into a single entity.<br>Schema normalization<br>Once records are reconciled, data is normalized: dates to ISO 8601, phone numbers to E.164, addresses to a consistent structure.<br>Enrichment<br>Where raw data is incomplete, we fill gaps — OCRing receipts and screenshots, extracting entities and summarizing transcriptions, resolving postal codes to geographic regions, and calling external APIs (Google Knowledge Graph, AlphaSense) to expand context.<br>Pre-computed metrics<br>Time-series snapshots and aggregations are derived from the processed data, making precomputed views — yesterday, last week, last month, sliced by geography, customer-journey stage, and any other metric that matters day-to-day — available to the downstream layers.<br>The resulting data is stored in the data lake as virtual or derived tables. Virtual tables provide a query-time view of raw records without duplicating storage, while...