Riot Haus

Modular AI systems for real environments.

/01 Systems

Most AI systems fail at retrieval.
Not generation.

The model is rarely the problem. Grounding is. Without structured retrieval, outputs drift. Context windows fill with noise. Answers hallucinate.

We build retrieval-first systems. Hybrid search with vector and keyword fusion. Scope-aware queries. Reranking before generation. Architecture designed for accuracy.

Security is structural: JWT authentication, encrypted OAuth tokens, tenant isolation, and scoped permissions. All of it built into the system boundary from the start.

/02 Capability

/03 System 01

System 01 [Oku]

Retrieval Infrastructure

Modular retrieval system with multi-source ingestion, hybrid search, and production-grade infrastructure. Combines vector and keyword retrieval with RRF fusion and cross-encoder reranking. Supports Google Drive, local files, and browser uploads with idempotent sync. Includes OCR for scanned documents, scope-aware queries, and conversational context handling. Multi-tenant architecture with JWT authentication and containerised deployment. Currently undergoing external review prior to public release.

Private system walkthrough available upon request.

Request a private walkthrough →

Architecture Diagram

*
System 01
Oku
Retrieval Infrastructure
01
Google Drive
OAuth + Picker
02
Local Files
Filesystem
03
Browser Upload
Direct ingest
Auth
JWT + Scope
Isolation
Data Sources
Pipeline
Document Processing
Parse / Chunk / Embed / OCR
Vector
Qdrant
Embeddings
FTS
Postgres
Keywords
Ingest
Search
Hybrid
RRF fusion
Rank
Reranker
Cross-encoder
Output
LLM Response
Context assembly + streaming
Retrieve
Modular Retrieval Architecture Rev. 01 — 2026

/04 Constraints

Design for constraints early. Or fix them later at scale.

Infrastructure
Core System
Retrieval + LLM + Response
Latency
Compliance
Permissions
Failure States

/05 Thinking

/06 About

Riot Haus is an independent AI systems studio specialising in retrieval-first architecture. We think most AI projects fail not because of the model, but because the hard stuff gets bolted on later: search, security, failure handling. If you're tired of demos that don't scale, we'd like to hear what you're building.

Get in touch →

Founded in 2025.

London / Remote.