Platform Feature

The Knowledge Vault — every piece of verified research your AI team can access, instantly.

Annabelle doesn't guess. She reads from a growing library of pre-verified market research, integration docs, and platform knowledge — loaded fresh at the start of every session.

Three categories. All verified.

Integration Intelligence

API status, auth models, rate limits, and partnership requirements for every platform we've researched. ServiceTitan, QuickBooks, BuilderTrend, and more.

Market Landscape

Pool industry context: who the players are, what software they run, and where Stinger fits — so Annabelle can brief your team without generic AI hallucination.

Platform Capabilities

What Annabelle can and can't do, kept current. She knows her own abilities because they're documented here — not because she's guessing from training data.

Ground truth on demand.

1

Research gets verified from primary sources

Not summarized from AI output. Not inferred from documentation summaries someone else wrote. Every entry in the vault was checked against the authoritative source — the vendor's developer docs, the actual API response, the real rate limit header.

2

Filed to the vault with citations

Every entry links to its source. The date of verification is recorded. When something changes — a vendor deprecates an endpoint, a rate limit drops — the entry gets updated and re-dated, so you always know exactly how fresh the information is.

3

Loaded at session start

Every agent, every conversation, reads the same ground truth. Annabelle's sub-agents, the Teams room, and Claude sessions all draw from the same vault index — so there's no drift between what one agent thinks a platform can do and what another one says.

AI that cites its sources.

Why this matters

Most AI assistants hallucinate integration docs. They describe APIs that were deprecated two versions ago, suggest OAuth flows that don't match the current SDK, and fabricate partner program details. The vault exists to prevent that. When Annabelle says "ServiceTitan has a 60 req/sec rate limit," it's because we verified it from their developer documentation — not because a language model estimated it.

Current vault entries

Integrations
  • Built QuickBooks Online— Full OAuth 2.0 sync, invoice push on job completion, zero per-call cost
  • Built ServiceTitan— Export API v2, 60 req/sec rate limit, customer/job/location import live
  • Research ProEdge Build— No public API; Fluidra/iON partnership required for real integration
Platform
  • Current Annabelle Capabilities— What the platform can and cannot do, verified against the deployed codebase
  • Current Model Roster— Which models are in the platform, their roles, and routing rules
Market
  • Current Pool Industry Landscape— Construction vs. service verticals, software map, Treasure Coast ICP context