Mustafa

Internal knowledge assistant for professional-services firms

A multi-agent RAG system that answers employees' questions from the firm's own handbooks - HR, leave, travel, expenses and tax - scaled to large document sets with better reranking, and deployed for a global asset manager, a top-10 accounting firm and an AmLaw 50 law firm.

Agno
Multi-agent
Agentic RAG
Reranking
Vector DBs
Text-to-SQL

Client project, deployed for three firms. I improved retrieval at scale, reranking and database support.

Private repository - described here, code not public

  1. Employee asks
    • How many leave days do I have?
    • Can I book this flight?
    • Which hotels are allowed?
  2. CoordinatorRoutes the question
    • Plans the search
    • Picks the right specialist
  3. Specialist agents
    • Handbooks and HR
    • Travel and expenses
    • Tax
    • Notion and wikis
    • PDFs and documents
    • SQL for structured data
  4. Answer
    • Grounded in the policy
    • Points to the source
Each specialist runs agentic search and full RAG over its own knowledge base, so retrieval stays precise as the documents grow.
Everything is already in the documents - the job is retrieving the right part, every time.

The problem: every large firm has the answers in its handbooks - leave, travel, expenses, tax, HR rules - but nobody can find them, so the same questions land in HR’s inbox again and again.

What it does

  • Employees ask in plain English: “How many leave days do I have?”, “I’m flying from New York to Chicago next week - can I book this flight, and which hotels can I use?”
  • A multi-agent system: a coordinator routes each question to specialized agents, each running on its own slice of company knowledge - handbooks, HR guidelines, travel and expense policy, tax documents, Notion pages and PDFs.
  • Each specialist retrieves with Agno’s knowledge features - agentic search and full RAG over the document embeddings - and a reasoning SQL agent handles structured data like leave balances.
  • Answers stay grounded in the firm’s own policy and point back to the source, instead of guessing.

What I improved

  • RAG at scale: made retrieval hold up across large, growing document sets, so answers stay precise as each firm adds more policies.
  • Reranking: better reranking of what search pulls back, so the most relevant passage reaches the agent first.
  • More databases: added support for more vector databases and regular databases, so each firm could run it on the infrastructure it already had.

Where it ran: a global asset manager, a top-10 accounting firm and an AmLaw 50 law firm.

Back to Projects