AI product
Compound is an AI platform for buy-side finance teams that provides long-running, proactive deal-agent tasks. Its agents analyze data rooms, filings, and uploaded documents, then produce financial models, memos, and PowerPoint presentations with citations tracing figures to source files, pages, lines, model cells, or filing passages. Agents run tasks asynchronously and in parallel, including across thousands of files, with multiple agents and subagents able to work concurrently. Compound V2 provides multiplayer agents that teammates can share and direct through comments on workbooks and decks, along with browser-based Excel, PowerPoint, and Word editors built for agent-driven work, including formula-compatible spreadsheets and versioned changes. It supports PDFs, Excel files, CSV and TSV data, Word documents, PowerPoint files, images, and other common formats, and orchestrates models from multiple providers for different tasks. The service states that customer data is not used for training by default, is encrypted with AES-256 at rest and in transit, can be deployed in a VPC, and is SOC 2 Type II compliant.
2 uses taken from transcripts — each links to the moment in the video.
A platform of long-running AI analyst agents for buy-side finance institutions. It embeds agents as multiplayer teammates in deal-team email threads, runs tasks in parallel in the background using headless Office engines rebuilt from scratch (Excel, PowerPoint, Word in Rust), and manages huge firm context like data rooms of 15,000+ files using agent swarms with grounded citations.
Autonomous AI analysts for institutional finance. It provides multiplayer agents with built-in inboxes that join deal-team email threads, a headless Office engine rebuilt from scratch (Excel, PowerPoint, and Word replicas written by agent loops) that runs work in parallel with write-render-check-fix loops, and agent swarms that process data rooms of 15,000+ files with cited findings.
2 in the library.