Build a Context-Aware Personal Knowledge Agent
This challenge involves building a sophisticated Personal Knowledge Agent. This agent will leverage a multi-modal RAG system to process uploaded documents, emails, and images, creating a deeply personalized understanding of user context. You will design a graph-based agent workflow using LangGraph, enabling extended thinking and adaptive reasoning budgets. The agent should be capable of synthesizing information from diverse sources and performing complex tasks by integrating with simulated external 'enterprise' systems via a robust MCP tool integration layer.
What you are building
The core problem, expected build, and operating context for this challenge.
This challenge involves building a sophisticated Personal Knowledge Agent. This agent will leverage a multi-modal RAG system to process uploaded documents, emails, and images, creating a deeply personalized understanding of user context. You will design a graph-based agent workflow using LangGraph, enabling extended thinking and adaptive reasoning budgets. The agent should be capable of synthesizing information from diverse sources and performing complex tasks by integrating with simulated external 'enterprise' systems via a robust MCP tool integration layer.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
What you should walk away with
Master LangGraph for building stateful DAG agent workflows with persistence and dynamic routing based on user input and extracted context.
Implement a multimodal RAG pipeline using LlamaIndex to ingest and retrieve information from diverse data types (text, PDFs, images) for contextual understanding.
Design MCP-enabled tool integration with Claude Sonnet 4.5 for extracting structured data from documents and emails, facilitating interaction with simulated external APIs.
Build extended thinking pipelines with GPT-5.2 Pro using adaptive reasoning budgets, allowing agents to deep-dive into complex queries when necessary and conserve tokens for simpler ones.
Deploy DSPy to optimize and programmatically prompt agents, ensuring robust and efficient information extraction, summarization, and response generation.
Orchestrate a team of specialized agents (e.g., Document Analyzer, Email Synthesizer, Image Describer, Task Planner) that communicate and collaborate within the LangGraph framework.
Develop strategies for handling ambiguous or incomplete user requests by leveraging the personalized knowledge graph built from uploaded content.
Integrate vector databases (e.g., Qdrant, Milvus) to efficiently store and retrieve embeddings for multimodal RAG.
[ok] Wrote CHALLENGE.md
[ok] Wrote .versalist.json
[ok] Wrote eval/examples.json
Requires VERSALIST_API_KEY. Works with any MCP-aware editor.
DocsAI Research & Mentorship
Participation status
You haven't started this challenge yet
Operating window
Key dates and the organization behind this challenge.
Find another challenge
Jump to a random challenge when you want a fresh benchmark or a different problem space.