Me and My Agents
Unleashing AI Agents on Bank Earnings
In a recent article, a former research analyst recounts their experience navigating earnings season, a time of intense focus and hard work. The analyst describes the grueling schedule, starting early, working late, and the sheer volume of information to digest. They explain the process of communicating findings to internal and institutional clients, updating models, attending calls, and publishing notes.
Despite the challenges, the analyst highlights the importance of earnings releases, noting they account for a significant portion of annual share-price variance. They mention exploiting liquidity around announcements to act on analysis before the market opens or during calls. This week, the six largest US banks reported third-quarter earnings, providing over 250 pages of financial information and eight hours of call explanations.
The analyst mentions having trained AI agents to help parse earnings materials, stating that these agents were instrumental in their analysis.
The article introduces four AI agents: Ernie, Thelma, Mike Mayo, and an earnings modeller. Ernie is described as doing the heavy lifting, building a picture of market expectations and delivering reports. Thelma tracks themes of interest and flags relevant information. Mike Mayo previews questions likely asked during calls, and the earnings modeller updates the analyst's model directly in Excel.
The AI agents, the author claims, outperformed the market in understanding earnings. Interested readers can sign up to receive instructions and outputs from these agents.
Written by urgent.news from Net Interest's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
