Onboarding to the Rewards Assistant Platform

The high-level “what is this platform and how do its pieces fit together” walkthrough for a team integrating with the Rewards Assistant for the first time.

What the platform is

The Rewards Assistant is an agentic AI system that answers user shopping and rewards questions and proactively sends direct messages (DMs). It is not a single service — it is a platform of six repositories that hand work to one another. See the Platform Index for the full map.

How to read the specs

Platform work is specified before it is built. Specs are organized into four stacks, each owned by one repo:

• Chat (PC-*) — how the agent is composed and how it executes. Start at PC-1 — Agent Composition.
• DM (PD-*) — how proactive DMs are scheduled, delivered, and registered.
• Services (PS-*) — the context and connector layer.
• Foundation (PF-*) — cross-cutting platform conventions, including PF-1 — Sub-Agent Lifecycle.

The Platform Index is the cross-repo table of contents; the Platform Spec Lab on Confluence is the authoritative roster.

A typical integration path

1. Read this guide and the Platform Index.
2. Read PC-1 to understand agent composition (skills, connectors, models) — most integrations add a skill or a connector.
3. If you need new context data, read the Services specs in consumer-context-service.
4. If you need a proactive DM, read the DM stack specs in consumer-graph-worker.
5. Follow PF-1 to promote your sub-agent through dev → test → prod.

Getting help

• Platform questions: the Pilot team and the Platform Spec Lab.
• This docs site (build failures, content issues): the Rewards Assistant platform team — this site is owned by the platform, deployed independently via SST + cfa-workflows, and does not depend on the shared tech-docs portal.