AI Agents as Financial Co-Pilots | AI-Driven Strategy & Decision Making
summary
Claims that agentic systems add reflection and planning plus tool access to LLMs, enabling conditional, multi-step workflows rather than single-prompt outputs. Describes a working prototype that pulls market feeds, macro releases and internal reports, computes portfolio P&L attribution and factor sensitivities, multiplies sensitivities by current moves to forecast contributions, then backtests that method to produce confidence bounds. Notes a live session audience of ≈800 and argues plain LLMs would fail this use case.
AI-written summary · about
chapters (9)
- 0:00AI agents vs LLMs
- 2:56Agentic AI capabilities
- 6:36Financial strategy challenges
- 9:43PNL explain analysis
- 12:36Market sensitivities
- 14:36AI agents in finance
- 16:21Practical agent use case
- 17:30Agent methodology
- 20:47Benefits and Q&A
related talks
34mAI Agents: Transforming Autonomous Decision-Making
29mAgentic AI: What It Is and Why It Matters
44mPannel Discussion | Agentic Automation: Are AI Agents The Future of Digital Work
41mBuilding LLM Agents – Challenges and Learnings
26mAI agents 101
20mFrom Copilot to Colleague: Trustworthy Agents for High-Stakes
36mLLMs and AI agents demystified
22mAgentic AI for Engineering Leaders | Strategy & Execution Guide