In this article, I ask whether Claude, the large language model from Anthropic, should be given a seat in the boardroom. After all, Claude is well-versed in worldly knowledge and is ready to engage on any topic that comes his way. So let's jump in and see what Claude brings to the table.
The story is like this: the treasury wants to widen its ability to place deposits within the banking system, primarily because it believes that the interest paid by bank counterparties is higher than that offered by the Bank of England.
The argument is that given the regulatory environment we currently operate in, the major banks are all safe and offer very little in the way of credit exposure, and therefore, this is more or less a free lunch.
There's little in the way of executive pushback because the perception is that, in the event of a bank running into trouble, the Bank of England will have no choice but to provide support. The proposal goes through without a lot of discussion.
Common enough, but is it sensible?
It depends, and the answer lies more in the way of thinking rather than the decision itself. Let's prompt Claude and see what transpires:
Prompt: The Board of a small Building Society has been asked to approve the extension of credit lines to five banks. Specifically, the credit lines will be for simple deposits with the five largest UK banks, and utilization will be by the Treasury. The proposal is for a maximum of £10m per bank. Currently, the Society holds all its liquidity at the Bank of England. The Society has a balance sheet of £1,000m and capital of £100m, and they are required to maintain a 10% capital ratio. Their calculations show that there is £3m of capital surplus. Focusing only on the credit aspects of this proposal, is it sensible?
Following a lengthy discussion, I asked Claude to summarise things in a way that would be useful for the board, and here it is:
Extending Credit Lines to the Five Largest UK Banks: Risk Assessment and Regulatory Considerations
The proposal to extend credit lines to the five largest UK banks appears to be relatively low risk, but there are still some important considerations
The five largest UK banks are generally considered to be financially stable and have strong credit profiles, with high credit ratings from major rating agencies, reflecting their low probability of default.
However, concentration risk remains a concern as the exposure is limited to the banking sector and the five largest players. A systemic issue affecting the UK banking sector could expose the Building Society to increased credit risk.
The proposed credit lines total £50m, representing 5% of the Building Society's balance sheet. While this may seem relatively small, it could become a significant source of stress during a severe crisis.
The Building Society's current capital surplus of £3m above its required 10% capital ratio may not be sufficient to absorb potential losses from the proposed credit lines in a severe stress scenario, especially if losses are incurred simultaneously on other parts of the balance sheet.
Considering the stress scenarios of 1974 and 2008
The 1974 secondary banking crisis suggests that the proposed credit lines to the five largest UK banks could be relatively resilient, as the largest banks were not as severely affected as smaller institutions.
However, the 2008 global financial crisis highlights the potential for significant credit risk in a severe banking crisis. Even large, systemically important banks faced difficulties, with some requiring government support.
Since the 2008 crisis, UK banks have been required to hold more capital and liquidity to improve their resilience to market stress. The regulatory environment has also been strengthened to reduce the likelihood and impact of bank failures, which could help mitigate the potential impact on the Building Society's credit lines in a stress scenario.
The proposed credit lines to the five largest UK banks could potentially lead to a serious strain on the Building Society's capital position, if such severe events were to occur once or twice in a 50-year period
Historical evidence suggests that severe banking crises can occur once or twice in a 50-year period, as seen with the 1974 secondary banking crisis and the 2008 global financial crisis in the UK.
In a crisis similar to 2008, the potential for default by one or more of the five largest UK banks could lead to substantial losses for the Building Society.
The Building Society's current capital buffer of £3m may not be sufficient to absorb the potential losses from the proposed credit lines in a severe stress scenario, especially if losses are incurred on other parts of the balance sheet simultaneously.
Adopting lower limits for the proposed credit lines could be a prudent approach
Lower limits would reduce the Building Society's overall exposure to the five largest UK banks, minimizing potential losses in the event of a default during a crisis.
By reducing the size of the credit lines, the Building Society would be better positioned to preserve its capital buffer.
A phased approach, starting with lower limits and gradually increasing them over time, would allow the Building Society to monitor risks and adjust its strategy as needed.
The Building Society could consider setting initial limits of £5m per bank, resulting in a total exposure of £25m (2.5% of the balance sheet), which would provide some diversification benefits while reducing the potential strain on the capital position in a stress scenario.
Five questions the regulator may ask
How does the Building Society define and quantify its risk appetite for credit risk, specifically in relation to exposures to other financial institutions?
What is the process for setting credit line limits, and how are these limits aligned with the Building Society's risk appetite?
What risk management processes and systems are in place to monitor and control exposures against the established limits?
What is the Board's role in overseeing the risk appetite framework and the setting of credit line limits?
How does the Building Society ensure compliance with regulatory requirements and guidelines related to credit risk management and large exposures?
The really important questions for the Board
How do you ensure that the Building Society's risk appetite for credit risk is properly aligned with its strategic objectives and capital management plan?
As NEDs, how do you challenge and validate the assumptions and methodologies used in setting the credit line limits, and how do you satisfy yourself that these limits are appropriate given the Building Society's risk profile?
What level of oversight and scrutiny does the Board apply to the monitoring and reporting of credit exposures against the established limits, and how do you ensure that any breaches or deviations are promptly brought to your attention?
How do you balance the need to diversify the Building Society's liquidity holdings with the imperative to maintain a prudent and sustainable risk profile?
How have you determined that the proposed credit line limits are consistent with the Building Society's risk appetite and capital management objectives, and what analysis has been performed to support this conclusion?
In conclusion, while the proposal to extend credit lines to the five largest UK banks appears to be relatively low risk, the Board must carefully consider the potential impact of severe stress scenarios on the Building Society's capital position. Adopting lower initial limits and gradually increasing them over time could be a prudent approach to balance diversification benefits with capital preservation. The Board should engage in robust discussions, challenge assumptions, and ensure that the risk appetite framework and credit line limits are properly aligned with the Building Society's strategic objectives and regulatory requirements.
Claude has facilitated high-level thinking, and this is different from the completion of boring, repetitive work that LLMs are considered to be good at. I would venture to say that, with the aid of an LLM, you can work through the key aspects of almost any part of your business without having expert knowledge of the topic. What you do need is an understanding of how to prompt and push the LLM, and this comes with practice.
My venture with Claude has also made me question whether the fear of using LLMs is overdone. There's a lot of talk about the risk of using large language models in the context of proprietary data. That's why many firms are very reluctant to let their employees near these models, fearing that something could go wrong. But what I've shown here is that you can have a very meaningful discussion without providing any proprietary information to the model.
There are a whole host of risks in financial institutions that lend themselves extremely well to this exercise at a high level. Almost every board paper that I have seen can be repurposed into something that could be put into a large language model without disclosing any information that is not already in the public domain.
Senior executives who do not use these models to question and analyse the risks and strategies that their firms are engaged in are missing out on a very powerful advocate.
Should Claude be in the boardroom? Well, not as a voting member of the board, but definitely at the table, discussing strategy and risks, he makes a cheap and efficient consultant.