Skip to content
Jacob NolletteCloud & software engineer
Path · Agents & AI

AI that takes on real work, and shows its work.

Teams of specialist agents with their own memory, a shared knowledge base, and guardrails, running where your data should live.

Sound familiar?

Where these projects usually start.

We tried a chatbot. It was a novelty, not a coworker.

What we know is scattered across a dozen cloud apps.

We can’t send our data to someone else’s model.

What I build

Agents & AI, start to finish.

Agent personas

Specialists for administrative, financial, facilities management, security analysis, maintenance, and health & wellness work.

Shared knowledge

Curated knowledge bases the whole fleet reads, kept in sync in real time. What one agent learns, the next already knows.

Flattened context

Secure, self-hosted connectors into mail, documents, project boards and the books, without handing over every key.

Private AI compute

Language, speech and vision models on your own hardware, with work split across GPUs and shared by Kubernetes time-slicing.

The trail

How the pieces fit

Your systemsmail, docs, booksConnectorssecure, self-hostedShared knowledgecurated, syncedSpecialist agentsone job eachYoupreview & approve
  1. Your systemsmail, docs, books
  2. Connectorssecure, self-hosted
  3. Shared knowledgecurated, synced
  4. Specialist agentsone job each
  5. Youpreview & approve
How we’d start

No price list. A conversation first.

  1. A conversationThirty minutes about what you’re trying to build or fix, and whether I’m the right fit.
  2. ScopingA written plan with an estimate and an architecture sketch.
  3. The buildA fixed-scope project or ongoing hours, with progress you can see.
  4. Ongoing supportHosting, maintenance and on-call, or a clean handover.
Next step

Put an agent to work.

Tell me what you’re working on. I’ll tell you honestly whether I’m the right fit and what a first step looks like.