Document Processing · Enterprise Knowledge Search
RBC Capital Markets needed to speed up document-heavy research and banking workflows so analysts and bankers could deliver faster insights, prepare client materials more efficiently, and answer complex questions without hours of manual review.
Reported impact
RBC increased document processing capacity by 10x, cut Research QuickTakes generation time by up to 60 percent, moved complex client queries to near-real-time answers, and expanded the Aiden platform to more than 8,000 users across capital-markets teams.
RBC Capital Markets expanded its Aiden AI platform with NVIDIA AI Enterprise so specialized agents could automate research and banking workflows without replacing expert judgment. The AidenResearch Platform uses AI agents to generate earnings content, summarize calls, surface insights from data catalogs, and provide real-time access to filings for the Global Research division. RBC is extending the same pattern into AidenBanker, where agents automate pitchbook creation, pre-meeting preparation, and note-taking for bankers. NVIDIA NeMo and NIM are part of the platform stack for model customization and serving, while NVIDIA RAPIDS supports higher-throughput data processing underneath the agent workflows. Together these layers create a reusable agentic platform that sits between capital-markets data sources and end users, reducing manual effort while keeping outputs tied to line-of-business workflows.
Filings, call transcripts, research catalogs, and banker notes are processed through the Aiden platform, where customized models and agent workflows summarize, generate, and surface relevant insights. Those outputs are then delivered into analyst and banker experiences for report generation, pitchbook creation, pre-meeting preparation, and question answering.
Building on this success, RBC is developing AidenBanker-a unified platform for bankers that connects essential functions like automated pitchbook creation, pre-meeting preparation, and comprehensive note-taking.
Document processing capacity has increased 10x, with improved accuracy.
RBC Capital Markets developed the AidenResearch Platform-a suite of specialized AI agents tailored for its Global Research division.
Research QuickTakes Report generation time is up to 60% faster.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
MongoDB Sample Oct 8, 2026 Navisio AI Rapid adoption of Navisio AI's platform triggered severe latency spikes, elevated CPU and RAM consumption, and costly vertical scaling. As it prepares to scale to 1,000 by the end of the year, and eventually toward 5,000 users, the team is… MongoDB Atlas · MongoDB Atlas Vector Search 
Google Cloud Sample Archived · Sep 27, 2026 SIGNAL IDUNA SIGNAL IDUNA needed to spread AI safely across a large insurance workforce, make a century of internal policy knowledge searchable, and let teams build their own agents without creating a fragmented, insecure shadow-AI… 80% weekly active adoption rate with a +45 NPS in first five months Document AI · Gemini · Gemini Enterprise Agent Platform 
OpenAI Sample Jul 31, 2026 Univé Univé needed to build organization-wide AI capability across insurance operations so employees could safely redesign their own work instead of waiting for centralized software projects or isolated AI pilots. 85% of licensed users active every week ChatGPT Enterprise · Custom GPTs · Workspace Agents 
