---
type: glossary
audience: new-member
tags:
  - onboarding
  - glossary
---

# Glossary

Common terms used in this workspace.

---

## Workspace Terms

- `core`: reusable project-independent AI workspace logic.
- `profile`: project-specific configuration and assumptions layered on top of the core.
- `operational memory`: curated file-based memory that helps future AI sessions reason accurately.
- `daily log`: same-day evidence and evolving findings in `ai/logs/`.
- `state`: near-term active work and priorities in `ai/state/`.
- `work item`: canonical memory for a ticket, story, task, or investigation in `ai/work-items/`.
- `stable context`: durable project knowledge under `ai/context/`.
- `inbox`: raw or lightly processed communication evidence under `ai/inbox/`.
- `promotion`: moving high-confidence evidence into canonical memory.
- `tooling behavior`: reusable behavior encoded in commands, prompts, skills, agents, or knowledge rules.

---

## Fidelity Terms

- `Fid4`: main Fidelity consumer iOS app and key validation environment.
- `XFlowSDK`: backend-driven UI engine that renders flows from service-provided configuration.
- `XFlowViewMaker`: adapter layer historically involved in integration and release propagation.
- `FTFrameworks`: feature modules such as account opening or transfer flows that can mediate XFlow adoption.
- `AO`: account opening context; many reports require careful reproduction and scope validation.
- `Discourse`: external issue/report source; treat reports as external until confirmed.
- `REST migration`: migration away from GraphQL/Apollo toward REST, with REST behind a feature flag unless confirmed otherwise.
- `authenticated flow`: behavior reproduced while signed in; often differs from non-authenticated behavior.
- `entry point`: the path used to reach a flow, which can affect backend-driven behavior.
- `Cogstore`: flow-configuration publishing and version-comparison platform.

---

## Communication Terms

- `external report`: issue reported externally before regression status is confirmed.
- `regression`: behavior confirmed to be newly broken relative to a known baseline.
- `scope`: the exact affected flow, platform, auth state, environment, and ownership boundary.
- `reproducibility`: whether the behavior can be repeated with known steps and context.
- `manager-ready`: concise, explicit, natural professional English that can be sent without rewriting.