https://oyyo.ai/_app/immutable/nodes/10.rUseVAfr.js

1import{a,f as i}from"../chunks/BgHNIxWW.js";import"../chunks/DfEZSoL_.js";import{e as o,$ as s,n as h}from"../chunks/DMfyJkED.js";import{h as l}from"../chunks/k245tRMQ.js";import{B as d}from"../chunks/Bj8kLrSs.js";var m=i(`<meta name="description" content="What if an AI agent wasn't a background script, but a coworker editing the same document at the same time? That's how Oyyo works."/>`),u=i(`<p>Here's a scenario that happens dozens of times a day at Oyyo-powered MGAs: An email arrives from a broker. The AI Organizer immediately starts reading the attachments. While the AI processes page 3 of the loss run, the underwriter opens the email body and starts reading the broker's notes. The AI updates field after field in real-time. The underwriter spots something the AI missed — a handwritten note about a prior claim — and types it into the same form. The AI immediately incorporates that correction into its premium calculation.</p> <p>No handoffs. No "wait for the AI to finish." No separate screens. Humans and AI agents work on the same document, at the same time, seeing each other's changes in real-time.</p> <h2>The Technical Challenge: CRDTs and AI</h2> <p>Making this work requires solving a hard computer science problem: how do you let an LLM rapidly update structured data while a human simultaneously edits the same fields, without conflicts or data loss?</p> <p>We use Yjs, a CRDT (Conflict-free Replicated Data Type) implementation, as the synchronization layer. Every field in an Oyyo form is a Yjs document. When the AI extraction agent writes "Insured Name: Acme Corp" and the human simultaneously types "FEIN: 12-3456789", both changes merge seamlessly.</p> <p>The key insight: AI agents don't need special treatment. They're just another cursor in the multiplayer document. The same conflict resolution that handles two human editors handles a human and an AI editing simultaneously.</p> <h2>Why This Changes Underwriting Speed</h2> <p>Traditional underwriting software is sequential: the AI runs, then the human reviews, then the AI runs again. Each handoff adds minutes. Over hundreds of submissions per month, those minutes become weeks.</p> <p>In Oyyo's multiplayer model, the handoff time is zero. The underwriter starts working before the AI finishes. They're reviewing field 1 while the AI is still extracting field 42. By the time the AI completes, the underwriter has already validated and corrected half the output.</p> <p>This is why Oyyo submissions take 8 minutes instead of 45. It's not just faster extraction — it's parallel processing between human judgment and AI capability.</p> <h2>The Journal: A Shared Timeline</h2> <p>Every action — human or AI — appears in the Journal, a unified timeline for each submission. You can see exactly what happened, when, and by whom:</p> <ul><li><strong>2:14:00 PM</strong> — AI: Email received from broker, 3 attachments detected</li> <li><strong>2:14:03 PM</strong> — AI: Started extraction on ACORD 125</li> <li><strong>2:14:08 PM</strong> — Human: Opened email, reading broker notes</li> <li><strong>2:14:15 PM</strong> — AI: Extracted 38 of 42 fields, 4 flagged for review</li> <li><strong>2:14:22 PM</strong> — Human: Corrected FEIN field, added prior carrier note</li> <li><strong>2:14:25 PM</strong> — AI: Incorporated correction, recalculated premium</li></ul> <p>This isn't a log. It's a living document that both humans and AI contribute to continuously. When a second underwriter opens the same submission, they see the complete story — every decision, every correction, every AI action — without asking a single question.</p> <h2>Building for Both Audiences</h2> <p>The hardest part of multiplayer AI isn't the CRDT implementation. It's the UX. How do you make an AI agent's rapid-fire updates not overwhelming to the human? How do you make human corrections visible to the AI without breaking its processing flow?</p> <p>Our answer: presence awareness. Just like Google Docs shows colored cursors for each collaborator, Oyyo shows which fields the AI is currently processing (with a 

1subtle animation) and which fields the human is editing (with their cursor). The underwriter intuitively knows: "The AI is working on the left side of the form. I'll start reviewing the right side."</p> <p>That's what multiplayer underwriting looks like. Not sequential. Not parallel in separate windows. Truly simultaneous, in the same workspace, with full mutual awareness.</p>`,1);function w(n){l("12tr07",e=>{var t=m();o(()=>{s.title="Multiplayer Underwriting: Building a Real-Time Workspace for Humans and AI — Oyyo Blog"}),a(e,t)}),d(n,{title:"Multiplayer Underwriting: Building a Real-Time Workspace for Humans and AI",date:"Mar 30, 2026",author:"Oyyo Engineering",category:"Architecture",children:(e,t)=>{var r=u();h(34),a(e,r)}})}export{w as component};