I gave the company a brain.

My role

Director — architected and built the system, founder-led adoption

The problem

Institutional knowledge trapped in individuals; answers took days of asking around and had no traceable source

What I did

Built a connected vault network — team vaults feeding a shared world model, with agents pushing external sources in

Outcome

23,521 documents across 18 vaults · 511 agent runs · 100% of answers traceable to a source

Most companies have knowledge somewhere. This one has it connected. I architected a nine-layer system where every business surface — sales pipeline, dev tickets, support history, meeting transcripts, the CEO's strategic priorities — feeds into a single intelligence layer that any team can ask questions of, without ever seeing raw data they shouldn't see.

The simple version

Imagine every Slack you'd ever sent, every meeting recorded, every customer ticket, every dev sprint — all sitting in separate locked rooms. Now imagine an agent that can read all of them, synthesize what matters, strip anything sensitive, and post a daily briefing anyone in the company can read. That's the system. The hard part is making sure it only writes what should be shared, never leaks personal data, and stays accurate.

What's under the hood

Beneath the vault network sits the rest of the architecture: schema standards that act as the contract between layers, a path for the CEO's strategic intent to enter the system without exposing private board prep, an agent memory layer (built on Microsoft Foundry) with proper decay and supersession rules, and the twelve enforcement mechanisms that make this an architected platform instead of a wiki.

See the full 9-layer architecture — all 12 enforcement mechanisms →

Answers used to take days of asking around. Now every one of them traces back to a document you can open.

What people did with it

Once the architecture was up, the pull was real. Adoption stayed founder-led — I onboarded the first users myself, growing the active base from one to four in nine weeks — but the interest came unprompted: ten-plus colleagues across sales, engineering and design surfaced their own use cases, engineers asked to adopt the agent patterns, and the CRO wrote, in a Teams DM, "I think it's brilliant." That opened a conversation about an internal sales-enablement product built on the system. We shipped a POC: an AI deck generator that pulls scraped competitor intel, product knowledge and real sales-call transcripts into branded pitch decks via conversation. Six to ten hours saved per deck.

"I think it's brilliant." — CRO · Teams DM, May 2026

The tell is that it kept running without me. A fleet of 13 agents and 10 reusable skills — meeting capture, decision logging, doc updates, world-model sync — has logged 500+ production runs across 18 vaults and 23,500+ documents, and every answer it returns traces back to a source. The system I built to remember for the company doesn't need me in the room to do it.

Why this case is in the portfolio

Most designers who claim AI on their resume mean "I use ChatGPT." This is a different claim. This is designing the AI system at the org-architecture level — vaults, agents, memory, security, authority handling, decay rules. It's the line between someone who's curious about AI and someone you'd trust with platform decisions.