Consequential Flowers: AI Mentor Platform (Client Project)

Client project. Built by Van Data Team for Consequential Flowers, AI-native software that turns a partner's content library into a white-label AI mentor for adults aged 18+. Live product: consequentialflowers.ai

Universities, associations and coaches hold years of material their members never see when they need it, and a generic chatbot cannot answer in the partner's own voice or from the partner's own content.

PRIM, the AI mentor companion, and SeedVision, which breaks a partner's library into AI-ready Seeds, one teachable idea each

Anthropic Claude and GPT-4 with LangChain on Google Cloud

A 200K-token input and 64K-token output budget with responses in about five seconds

Answers below a 60% confidence threshold are held back

A partner's content library turned into AI-ready Seeds within 24 hours

Responses in about 5 seconds on a 200K-input, 64K-output token budget

Deployed white-label as each partner's own PRIM

Content is broken into single-idea Seeds rather than retrieved as raw documents, so each answer stays tied to one teachable idea the partner wrote.

Stack: Claude, GPT-4, LangChain, RAG, Google Cloud.

Full case study: vandatateam.com/portfolio