WorldatWork AI: HR Assistant
An AI assistant that answers HR and total-rewards questions from WorldatWork's own content and shows its sources. The WorldatWork team tracks usage, content gaps and costs from its admin dashboard.



Platforms
- Web
- iOS
- Android
Overview
WorldatWork has a large library of research, articles and courses on HR and total rewards. We built WorldatWork AI so members can simply ask. It answers from that library, cites its sources, and suggests courses, webinars or research worth looking at next. Member-only content stays with members. It runs as a web chat app and as a tab inside the WorldatWork GO app. We also built the admin dashboard behind it. The WorldatWork team uses it to see what members ask, how they rate the answers, where content is missing, what it costs and whether the content pipeline is healthy.
Project details
- Client
- WorldatWork (Total Rewards Association)
- Industry
- Professional association: HR, compensation, benefits, total rewards
- Market
- United States
- Engagement
- Feb 2026 – present
- Our role
- Mobile + AI product partner
- Platform
- Web chat app + native tab in the mobile app + web admin dashboard
What we built
The assistant
- Streaming answers with tables, charts and formulas
- Inline source citations and a sources panel
- Product recommendation cards (courses, webinars, certifications, events, research)
- Hybrid search (vector + keyword, RRF fusion) with Cohere reranking
- Tools for catalog search, safe data queries and exact calculations
- Member tiers: free users see free content only; member-only content stays protected
- Answer survives page reload and continues on another device
- Free-tier quota, spend limits and guardrails (no legal advice, on-topic only)
- Expert Review Mode: HR experts grade answers to improve quality
- Knowledge base fed by 20+ sources (articles, journals, webinars, events, courses, research reports, scanned PDFs) with automatic incremental updates
AI insights and admin dashboard
- KPIs: users, retention, engagement, satisfaction (CSAT), thumbs up / down
- Content gaps: questions members ask that WorldatWork content doesn't cover yet
- Trending topics and "sources behind bad answers", with flag-to-content-team
- Cost controls: daily spend caps, automatic pause, manual block / release
- AI model picker and release-notes editor (feeds "What's new" in web + app)
- Content pipeline: run, monitor and debug ingestion jobs
Inside the product
















New chat. Suggested questions and a member's full chat history
Technology
Tech stack
- Python
- FastAPI
- pydantic-ai
- PostgreSQL + pgvector
- Azure OpenAI
- Cohere Rerank
- Next.js
- Vercel AI SDK
- TanStack Query
- Recharts
- Tailwind
- Azure



