Case study / Education & coaching
AI coaching that
remembers context.
A coaching network with 25 years of in-person centres across Germany.
The difference it made
Value you can see.
A coaching assistant people come back to.
Engagement
Higher engagement.
Users return to an assistant that remembers their goals and progress.
Coaches
Less coach effort.
Summaries, nudges and recommendations replace manual follow-up.
Reliability
A dependable engine.
The coaching engine stays available as daily conversations grow.
The solution, at a glance
Personal coaching.
At scale.
The challengeWhat we changed
- Limited coach capacityAI between sessions
- Progress hard to seeGoals & summaries
- Manual follow-upsPersonal next steps
- ConversationUser history
- ContextRAG retrieval
- AI coachOpenAI models
- Next stepsGoals & activities
Remembers context across conversations
Engineering details
The challenge
- No way to hold deep, personal conversations at scale
- Users could not see their progress over time
- Daily nudges and insights were manual
The build
- RAG-based coaching assistant on OpenAI models
- Adaptive responses from each user's history
- Conversation summaries and goal tracking
- Recommendation engine for activities and reading
Technology
Python
PostgreSQLRAGOpenAIVector searchRecommendations
Continue exploringContent reporting, automated.
Your next step
Have a similar
problem?
Forty-five minutes on your version of it. You leave with a proposed first step.