We scan new podcasts and send you the top 5 insights daily.
CPP Investments created a multi-agent AI reviewer called a "memo coach." It analyzes draft investment recommendations through various lenses—logic, risk scenarios, value creation, communication—to identify weaknesses and generate prioritized questions for the team to address before the official review.
Before a diligence meeting, feed AI your viewpoint on a manager or portfolio and instruct it to take the opposing side of the argument. This creates a "red team" debate that helps you anticipate challenges and develop a richer, more nuanced perspective for the actual meeting.
Instead of relying solely on human review, Tubi's CPTO uses AI as a "red team" to critique strategic plans. By prompting an agent to "poke as many holes as you can," he uncovered a major flaw in a new market strategy that his team had overlooked.
Advent's investment committee uses an AI tool trained on all historical memos and meeting questions. The AI highlights inconsistencies between deals, such as different interest rate assumptions, and tracks how a deal's thesis has evolved, enhancing governance and decision-making.
The discipline of writing down your thought process is crucial for decision analysis. AI now amplifies this by creating a searchable, analyzable record of your thinking over time, helping you identify blind spots and get objective feedback on your reasoning.
An investment team intentionally prohibits using AI to draft the core thesis of an investment memo. The act of thinking through and articulating the risks, potential pitfalls, and core bets is a crucial part of the human investment process that should not be outsourced to a machine.
To get robust feedback, create an AI tool that simulates a "war council." It spins up multiple AI sub-agents, each with a specific persona like "Ruthless CFO" or "Contrarian Board Member," to debate a critical decision from all angles.
Advanced AI tools can model an organization's internal investment beliefs and processes. This allows investment committees to use the AI to "red team" proposals by prompting it to generate a memo with a negative stance or to re-evaluate a deal based on a new assumption, like a net-zero mandate.
Advent created an AI trained on its entire investment history, including deals they passed on. This 'IC Robot' analyzes new proposals and flags assumptions—like margin growth—that deviate from historical precedent, serving as a powerful, data-driven check on the investment committee's biases.
Advent built an internal AI tool trained on historical deal memos and investment committee (IC) questions. This non-voting 'robot' prompts the IC with questions, highlights changes in a deal's thesis over time, and flags inconsistent assumptions across different deals.
Define different agents (e.g., Designer, Engineer, Executive) with unique instructions and perspectives, then task them with reviewing a document in parallel. This generates diverse, structured feedback that mimics a real-world team review, surfacing potential issues from multiple viewpoints simultaneously.