---
id: ai-overview
area: ai
level: 1
title: "AI & Agentic Systems"
claim: "Builds and operates sixteen or more AI pipelines — agent harnesses · model routing and cost control · retrieval over a tagged corpus · and a voice front-end that runs a house."
confidence: running
period: "2020–"
tech: [LangGraph, Prefect, n8n, Qdrant, OmniRoute, Whisper, Piper, MiniMax]
metrics: [{label: "pipelines maintained", value: 16}, {label: "model providers behind one gateway", value: 6}, {label: "audio endpoints for spoken output", value: 8}]
artefacts: [{type: doc, label: "House AI hub — service topology", url: "content/ai/l3/ai-hub-architecture.md"}, {type: doc, label: "Model routing and cost control", url: "content/ai/l3/ai-omniroute-routing.md"}, {type: doc, label: "Voice pipeline — speech in and speech out", url: "content/ai/l3/ai-voice-pipeline.md"}]
public: true
last_verified: 2026-10-26
tags: [ai, agents, routing, retrieval, voice]
---

# AI & Agentic Systems

**Claim.** Sixteen or more AI pipelines are maintained in production — ten or more on n8n, Prefect and LangGraph, six on Paperclip — with one gateway in front of six model providers, retrieval over a metadata-tagged corpus, and a voice front-end that controls the house.

**Status.** Running. Every figure on this page traces to the evidence notes; the verification date is 2026-10-26.

**Why it reads as engineering rather than enthusiasm.** The pipelines run against real obligations — school portals, calendars, email, household audio — and they are operated: routed for cost, guarded before they act, and observed while they run.

**Start here.** [The capability page](ai-systems.md) explains what is actually run and what the trade-offs were. The three chips above resolve to artefacts below it.