In the **AI Agentic Retrieval Grand Challenge**, participants are tasked with developing systems capable of retrieving the most relevant evidence from raw SEC filings to answer institutional finance questions. The task is structured as a two-stage agentic retrieval problem: **Document-Level Ranking** and **Chunk-Level Ranking**. This two-step design prioritizes accuracy and qualities essential for deploying AI systems in investment research. Participants’ systems will be evaluated on their capacity to reason across both document-type ranking and chunk-level retrieval tasks. *All submissions must include a **reproducible notebook implemented within Databricks Free Edition workspaces**, with the notebook link uploaded in the discussion tab as the standardized evaluation interface. Optional integration with the Upstage API (Solar LLM) is allowed.* ## Task Overview For each **Document-Level Ranking** and **Chunk-Level Ranking** task, you are required to **optimize a system prompt** to rank as follows: 1. **Document-Level Ranking** – Given a financial question, systems must rank candidate document types (10-K, 10-Q, 8-K, DEF-14A, earnings transcripts) by their likelihood of containing the adequate information for answering the question. 2. **Chunk-Level Ranking** – Given a single document, systems must identify and rank the most relevant passages within the provided document, returning a ranked list of candidate chunks that contain the information needed for answering the question.