AI Assistant for Resource Directories.
Callie, a prototype conversational assistant, helps families find the right community resources with natural language, multilingual support, and answers grounded in vetted directory data.
The challenge.
Families often abandon resource directories after failed searches or confusing terminology. Information is frequently outdated or incomplete, leading to poor matches and diminished trust.
The build.
Through user discovery, we prototyped Callie, an AI assistant that:
- Understands natural language requests instead of requiring the “right” search terms
- Offers 24/7 multilingual support
- Uses Retrieval Augmented Generation to ground answers in vetted resource data
- Integrates with Model Context Protocol for real-time updates
Stack.
Python · OpenAI API · Google Cloud Storage · Pinecone · AI image + animation · HTML/JS/CSS
Results.
- Conversational AI shows potential to reduce directory abandonment
- Early prototypes indicate time savings for families and staff
- Nonprofits can unlock insights into trending needs and service gaps
Related engagement: Broker Directory & API, another build where governed data pipelines feed a public search experience.
OUTCOME: Working prototype indicating reduced search abandonment and time savings for families and staff, with directory insight into trending needs and service gaps.
Ready before
the agents arrive.
Tell us what you want to build, we respond within one business day.