The QAI platform
QAI is the data and cloud layer under agentic AI products: one Postgres carrying records, documents, spatial indexes and vector columns, an agent runtime with retrieval and conversation memory, and per-product credit metering. It is built and operated by QAI Cloud, and four QAI products run on it today.
The layer is not sold as a standalone product today. It is the substrate underneath QAI's own products, documented here because what it does — and does not do — decides what those products can honestly claim.
Four layers
Each layer has one job, and each is documented on its own page.
QAI Data
One governed Postgres for records, documents and vectors
Relational records, documents, spatial indexes and vector columns in a single Postgres schema, under one permission model and one migration lineage.
QAI Agentic AI
The agent runtime: retrieval, memory and metered model calls
Persistent chats, replayed conversation history, and per-message model and token accounting — so an agent retrieves across the same database it writes to, and every call is attributable.
QAI Cloud
Delivery, edge and tenancy
The delivery layer in front of every QAI product — CDN and edge routing, verified-bot handling, rate limiting, and org-scoped tenancy with per-product credit metering.
QAI Infra
The AWS substrate, entirely in Terraform
Every environment is declared in Terraform and shipped through a pipeline with approval gates. There is no manual console change in the path to production.
What runs on it
Four products in production, on the same schema and the same Terraform stacks.
Who builds it
The platform is built and operated by QAI Cloud. Its research arm, QAI Lab, works on the agentic-systems research the products are built from — retrieval, memory, tool use and evaluation.