# Firedog

> AI cost accountability for institutional finance — price every AI call and file it under the workflow, model and desk that spent it.

## Docs

- [Attribution](https://docs.firedog.finance/attribution.md): How every AI call gets filed to a desk, workflow and user — the three context fields, the headers they travel on, and how each maps to a dashboard lens.
- [Data processing & residency](https://docs.firedog.finance/data-processing.md): What Firedog processes, where it flows, where it is stored, for how long, and how it is deleted — the basis for your DPA and Article 30 record.
- [How it works](https://docs.firedog.finance/how-it-works.md): The split-plane architecture: a collector that prices every AI call inside your VPC, and a cloud dashboard that only ever sees metadata.
- [Firedog](https://docs.firedog.finance/index.md): AI cost accountability for institutional finance — price every AI call and file it under the workflow, model and desk that spent it.
- [Quality & shadow testing](https://docs.firedog.finance/quality-shadow-testing.md): How Firedog proves a cheaper model holds up — measured cost and quality, without a prompt or response ever leaving your VPC.
- [Quickstart](https://docs.firedog.finance/quickstart.md): Route your first priced, attributed LLM call through the collector in about five minutes.
- [Security & data residency](https://docs.firedog.finance/security.md): Where your data lives, what leaves your network, and how identity and tags are protected. Full prompts, responses, and RAG stay in your VPC; only metadata reaches Firedog cloud.
- [Sensitivity profiles](https://docs.firedog.finance/sensitivity-profiles.md): Choose what the in-VPC collector is allowed to emit as metadata — strict, standard, or open — without ever letting prompt or response content leave your network.