Skip to content
Vol. XI · No. 289Toronto, Friday, October 16, 2026Toronto weather…

Inside: AI agents, a 76KB calendar, and one slop fork

The Wania Dispatch

Late edition · Free, though email is appreciated

“All the code that’s fit to ship”

Care Tech

Local Engineer Builds AI Agents to Help Match Patients With Caregivers

Caribou’s Senior Staff Engineer pairs voice agents with a memory module of his own design. Sources confirm he also writes.

By our staff reporter · Toronto

TORONTO — Zain Wania, a Senior Staff Engineer at Caribou, spends his days building AI agents that help care coordinators match patients with caregivers. The work runs on Vapi voice agents, the AI SDK, and an agent-memory module he designed and built himself.

Before Caribou, Wania spent six years at ContactMonkey, where he led the frontend platform team, drove design system adoption, co-architected an AI email checker, and built an internal knowledge-base agent and MCP server on his own.

He writes about what AI changes about the craft of building software, and what it doesn’t. Readers with questions may write to the editor below, or to zain@wania.dev.

Continued on About, Page A2

DispatchesAll writing →

From the WiresThe latest from the labs, refreshed every half hour

Anthropic wireAll posts ↗

OpenAI wireAll posts ↗

In BriefFull record →

  • Agent memory for care coordination

    Caribou, 2026 — A memory module for Caribou’s care-coordination agents, which run on Vapi and the AI SDK. I designed and built it.

    Case study in progress

  • Replacing a 15MB calendar with 76KB of our own

    ContactMonkey, 2026 — Ripped out Bryntum Calendar for an in-house component, with a rough internal Claude plugin doing a lot of the migration work.

    Full story in Dispatches

  • Knowledge-base agent and MCP server

    ContactMonkey, 2024–26 — Designed and built on my own: an internal agent over the company’s knowledge base, plus an MCP server so other tools could use it.

    Internal

  • AI email checker

    ContactMonkey, 2024–26 — Co-architected the AI email checker as Staff Engineer for a ~20-person engineering organization.

    Internal

  • Frontend platform and design system

    ContactMonkey, 2022–24 — Led the frontend platform team and drove design system adoption across the product.

    Internal

  • Mdow

    Side project, 2026 — A calm desktop reader for markdown folders, with an AI companion that cites its sources.

    Case study inside

  • zstack ↗

    Wania Labs, 2026 — An opinionated TypeScript product starter: Cloudflare-first, TanStack Start, and Alchemy.

    Source available

Classifieds

  • Seeking: Creating a design system. Building cohesive, scalable component libraries that unify your product experience.Reply: zain@wania.dev
  • Available: AI for engineers and beyond. Introducing AI-powered workflows for engineering teams and the broader organization.Reply: zain@wania.dev
  • Wanted: An internal AI knowledge base. Making your team’s collective knowledge accessible and searchable through AI.Reply: zain@wania.dev