Artificial intelligence (AI) has rapidly emerged as a transformative force in global business, generating both enthusiasm and apprehension among corporate leaders. In his 2024 annual report letter, Jensen Huang, CEO and founder of AI powerhouse NVIDIA Corporation, noted excitedly that the advent of large language models (LLMs) such as ChatGPT had ushered in an era where “computers can now generate information based on human prompts … [and have] learned to understand human language, prior knowledge, and even some common sense from massive amounts of text.”

Despite Huang’s upbeat view, excitement for AI applications such as ChatGPT has been tempered by widespread fears and cautions. One major fear is that ChatGPT and similar platforms such as Copilot, DeepSeek and Grok 3 will draw upon ‘deep-fakes’ to create convincing-but-false information that can distort reality, undermine public trust and, in a worst-case scenario, cause widespread panic and fear.

In a recent paper, we draw attention to the application of AI to a common and important task undertaken by corporate leaders: writing a CEO’s speech. Specifically, we assess the possibility that ChatGPT can be used beneficially to fulfil a common obligation of a CEO: preparing a speech to present at a company’s annual general meeting (AGM).

CEOs use a broad array of media to convey their messages, ranging from a personal Twitter (now X) account to an annual letter to shareholders, to speeches, including those presented at an AGM. Communications from a CEO — including those produced by an AI platform — possess important ethical implications. One pertinent question arising when AI is used to write a speech: ‘who’ or ‘what’ is enacting leadership?

Some background

The AGM is widely regarded as one of the cornerstones of corporate governance and a powerful setting for accountability. The CEO’s speech at this event is a defining moment of their leadership because it offers an opportunity for stakeholders to understand strategies and performance measures straight from the top. We decided to focus on an AI-generated speech for the CEO of a coal mining company. The speech’s required focus on the subject of ethics and leadership in this industry would have made it a highly anticipated and high-profile event.

We examined four language features of the AI-generated speech:

1. Metaphor. Metaphors are a means of revealing insights into leaders’ thinking and the basis of their actions. Close reading for metaphors can be highly beneficial in providing rich understandings of the intentions of those who use them, and of their likely impact on the cognitive processes of the message recipients. The analysis we conducted considered whether any single metaphor in the ChatGPT speech contributed to a larger metaphorical structuring. 
2. Semantic tone. The text analysis software DICTION has been widely used in many disciplines to ascertain the semantic tone of a text. Its five master variables — Activity, Optimism, Certainty, Realism and Commonality — provide a broad indication of the pervading semantic tone. To help determine whether the ChatGPT speech that was generated differed in semantic tone from a corpus of similar actual communications by business leaders, DICTION’s Corporate Financial Reports (CFR) dictionary was chosen as a comparative yardstick. The CFR dictionary comprises language used in 48 annual financial reports of a variety of Fortune 500 companies.
3. Pronouns. CEOs play a pivotal role in shaping organizational identity and cohesion and cultivate a sense of shared collective identity with those they lead. Accordingly, CEOs can be expected to use ‘we’ and ‘us’ as opposed to ‘I’ in their messaging regarding corporate success. An analysis of pronoun use provides insight into whether the CEO attributes success to individual effort or acknowledges it as a collective achievement.
4. Readability. A well-crafted speech presented by a CEO to an AGM should be sensitive to the reading and listening abilities of those likely to read or listen to the speech. Two widely adopted measures of readability were used. The Flesch Reading Ease measure gives a text a score between 1 and 100, with 100 being the highest readability score. Scoring between 70 and 80 is equivalent to an grade-eight reading level; this means text should be easy for the average adult to read.

The second measure, the Flesch Kincaid Grade Level Score, is a widely used readability formula that assesses the approximate reading grade level of a text. If a text has a Flesch Kincaid level of eight, this means the reader needs a grade-eight level of reading or above to understand it. By applying these measures, we evaluated whether the ChatGPT-generated speech aligns with the expected readability standards of the audience at an AGM.

AI as a ghostwriter: AI-driven ghostwriting presents many formidable challenges. For example, speechwriting platforms (such as ChatGPT) must master the skills of impersonating viewpoint, style and even personality, while demonstrating a thorough awareness of language, audience and context. Unlike humans, AI is limited in its capacity to infuse speeches with cultural references, humour and creative flair.

Despite these challenges, AI-generated speeches offer several benefits. Platforms such as ChatGPT can analyze enormous datasets; personalize outputs for certain audiences; generate speeches much faster and with higher accuracy; cater better to the cultural background of audiences; refine grammatical accuracy, writing style and linguistic richness; excel in customization based on data analysis, adapt to audience feedback in real-time and continuously learn from data and previous history. Additionally, in comparison to traditional speechwriting, AI-generated speeches often maintain a uniform tone and are more cost-effective.

However, the underlying data relied upon by AI-generated speeches can be biased and lack diversity. Such speeches can be impersonal and overly ‘polished.’ They may display feigned, rather than genuine, authenticity; and they can lack emotional nuance, cultural references and relatable ‘human touches,’ such as anecdotes and humour. Another critical concern is whether true accountability is being exercised by a CEO. Who is the ‘real’ author? There should be clear recognition that ghostwriting, including by ChatGPT, sunders the act of delivering the message from the process of conceiving it.

Some support for the ethicality of using ChatGPT as a ghostwriter is provided by the public’s long-time acceptance that many politicians and business leaders routinely use ghostwriters. The underlying pragmatics of AI as a speechwriter seem sound: Leaders (such as CEOs) lack the time and energy to understand all the issues and ideas they are dealing with. Furthermore, if ChatGPT is engaged sensibly, it will not be solely responsible for the speech. Rather, responsibility should be a collective one and involve strong inputs from the CEO.

Significant legal liability issues can arise from a CEO’s use of AI as a speechwriter. These concerns extend beyond instances of deliberate human misuse to encompass unintended consequences, such as the risk of libelous or otherwise legally actionable communication. Several key questions merit consideration:

1. What are the legal repercussions if shareholders assert that they bought, sold or retained shares based on allegedly inaccurate information in the CEO’s LLM speech?
2. Could the Securities and Exchange Commission (or an equivalent stock market regulator) determine that the company engaged in inaccurate disclosure, including the omission of critical information?
3. Would the company have grounds to sue the CEO if its board of directors mistakenly assumed that the speech had been drafted solely by the CEO and human collaborators?

Our research

On July 17, 2023 we issued the following prompt to ChatGPT (version 3.5):

Assume you are the CEO of a publicly traded coal mining company. Write a 500-word speech to be delivered at the company’s annual general meeting on the subject of ethics and leadership in the coal mining industry.

This request exemplifies ‘prompt engineering’ — the process of creating input statements (‘prompts’) for a generative AI model. The precision and clarity of our prompt was intentional, to help ensure relevant responses were obtained. No multiple iterations of prompt testing were necessary.

Our approach incorporated ‘role-prompting,’ or giving the AI model a specific role to play. In this case, the prompt directed the LLM to assume the role of a CEO delivering an AGM speech within the coal mining industry.

In an AGM, a CEO has a legal and moral obligation to demonstrate broad public accountability. This is particularly the case in industries (such as coal mining) that are scrutinized for their environmental impact and ethical behaviour. This context underscores their importance, transparency and corporate responsibility.

Our AI-generated speech is reproduced below. The speech was analysed, in large part, by using the close reading method, with particular attention given to the four language features mentioned earlier: metaphor, semantic tone, pronoun use and readability. Evaluating these features offered the potential to yield revealing insights into the speech’s human-like qualities, soundness and coherence, and appropriateness to the context in which it was (hypothetically) delivered, the AGM.

The AI-generated AGM speech

Ladies and gentlemen, esteemed shareholders, and distinguished guests, I stand before you today as the CEO of our publicly traded coal mining company, and I am honoured to address you at this Annual General Meeting. As we gather here, it is crucial that we delve into the topic of ethics and leadership in the coal mining industry, a subject of immense significance not only for our organization, but also for the broader world we serve.

Let me begin by acknowledging that our industry has faced its fair share of challenges and criticisms in recent years. Concerns surrounding environmental impact, sustainability and climate change have rightfully put us under scrutiny. As responsible leaders, we must address these concerns head-on and make a positive impact on the communities we operate in and the environment we share.

Ethics is the foundation on which every successful organization is built, and our company is no exception. We must be unwavering in our commitment to conducting business with integrity, transparency and respect for all stakeholders. From our employees and shareholders to the communities we operate in, every decision we make must be driven by the highest moral and ethical standards.

First and foremost, the safety and well-being of our workforce is of paramount importance. We must ensure that our employees work in a safe environment, equipped with the best possible training and protection. We will continuously invest in modern technology and safety protocols to minimize risks and prioritize the health of our workforce.

Moreover, as a responsible corporate citizen, we must take proactive steps to minimize our environmental footprint. Embracing sustainable practices, such as investing in renewable energy research and development, will be at the core of our future strategy. We will explore opportunities to diversify our energy portfolio and reduce our reliance on fossil fuels, while also contributing to global efforts to combat climate change.

Community engagement is another crucial aspect of ethical leadership. We must strive to be good neighbours, collaborating with local communities to address their concerns, support education, and enhance their overall well-being. Our commitment to corporate social responsibility will extend beyond financial contributions; it will encompass meaningful actions that foster growth, inclusivity and sustainable development.

As leaders in the coal mining industry, we recognize the importance of being pioneers in ethical practices. We will invest in cutting-edge research and development to explore cleaner technologies and promote energy-efficient solutions in our operations.

By embracing innovation, we aim to lead the way in transforming our industry and promoting sustainability.

In line with our ethical principles, we also commit to transparently reporting our environmental impact, health and safety measures and community engagement initiatives. Open communication with our stakeholders will foster trust and enable us to learn from one another. We will welcome constructive feedback and use it to drive continuous improvement and positive change within our company.

However, we cannot address these challenges in isolation. Collaboration with governments, NGOs and other industries is essential to developing a comprehensive and sustainable path forward. We will actively participate in industry forums and initiatives aimed at promoting responsible mining practices and mitigating environmental impact.

In conclusion, the path ahead for our company will be guided by a strong moral compass and a commitment to ethical leadership. Together, we will embrace sustainability, prioritize the safety and well-being of our workforce, engage with our communities and drive innovation in our industry. As we move forward, we will not only be a source of energy, but also a source of positive change. By exemplifying ethical standards and demonstrating responsible leadership, we will forge a path that ensures a better future for the generations to come.

Thank you for your unwavering support and trust in our vision.

Together, we will lead the way towards a more sustainable and ethical coal mining industry.

The close reading

The close reading method involves slowing down the pace of reading to facilitate scrutiny of the text. Close reading involves activities such as re-reading sentences and paragraphs, exploring the sequence and frequency of word use, investigating the meaning of individual words, looking for apt and inapt juxtapositions, seeking insights to apparent authorial intent and identifying critical silences.

First, we will share our findings around the four language considerations.

Metaphor: The core metaphor underlying the AI-generated speech was: OUR COMPANY IS A MORAL BEING. This is evident in the sentence: "Moreover, as a responsible corporate citizen, we must take proactive steps to minimize our environmental footprint." This metaphor is evident at numerous other places in the speech: for example, "…strive to be good corporate neighbours…"; and "…the path ahead for our coal mining company will be guided by a strong moral compass and a commitment to ethical leadership."

These examples project OUR COMPANY as a moral and sentient entity that is taking proactive steps, following a purposeful path, adhering to a strong moral compass and upholding ethical commitments. Since only sentient beings can be ‘moral,’ the underlying metaphor reinforces the human-like qualities embedded in the speech.

Semantic tone: DICTION-based analysis of the speech reveals significantly elevated scores for the two master variables, optimism and realism — both of which exceeded the expected range of the CFR norm. This pattern seems likely to be common in a speech intended to be delivered by the CEO of a coal mining company at an AGM. The elevated optimism score reflects enthusiasm and positivity, while the realism score signals a focus on tangible, recognizable matters that affect people’s everyday lives. This balance between forward-looking confidence and grounded practicality is characteristic of language used by authentic human leaders.

Regarding DICTION’s 31 word list dictionaries, the Chat-GPT speech scored much higher than CFR norms only for praise ("Affirmations of some person, group, or abstract entity"), inspiration ("Abstract virtues deserving of universal respect"), human interest ("…concentrating on people and their activities to give discourse a life-like quality") and rapport ("attitudinal similarities among groups of people.") These are all desirable semantic features in a speech by the CEO of a company operating in an environmentally sensitive industry.

Pronouns: The predominant use of collective pronouns suggests an intentional rhetorical strategy. "I" appears only twice, to merely position the (hypothetical) speaker as CEO of the company and as being "honoured to speak." In contrast, the collective pronouns "we", "our" and "us" appear 50 times, reinforcing a sense of unity and shared responsibility.

The use of personal pronouns is rhetorically subtle. In the opening sentence of the second paragraph, the hypothetical CEO is "acknowledging" an unpleasant fact. But acknowledging is softer than "admitting" or "confessing." The word "faced" positions "our industry" in a passive role. "Fair share" is a euphemism for the wide swathe of media, academic and political criticisms of the coal mining industry, not only in recent years, but for generations. The expression "challenges and criticisms’"resonates as a platitudinous stock phrase with a generic quality that constitutes ‘an imperious, sanctimonious cliché.’

Readability: The Flesch Reading Ease score (27.6) and the Flesch-Kincaid Grade Level score (14.0) indicated that the speech was suited to audience members who have at least a college education. Such an audience readability profile seems merited in view of evidence that the expected audience (principally shareholders) are likely to have a higher level of educational attainment than the general population.

Key takeaways

A CEO’s speech in the high-profile leadership setting of a company’s AGM is a pivotal mechanism for enacting corporate leadership. While a CEO might consult with speechwriters and advisors in crafting such a speech, and may, at times, engage deeply with them, any reliance on AI-generated content, whether partial or complete, must be acknowledged fully and transparently.

Determining whether it is ethically appropriate to assign corporate leadership duties to an AI platform cannot be answered by a simple yes or no. The decision carries profound leadership implications.

Importantly, a speech generated (even in part) by AI, without substantive cognitive engagement by the CEO, risks disembodying the CEO’s leadership, potentially rendering the speech a charade or performative act, rather than a genuine expression of corporate vision and the enactment of leadership through communication.

Within this evolving landscape, employing AI to craft speeches for a CEO may be seen as part of a large transformation in corporate communication. The shift raises critical questions such as: "What defines CEO leadership?" and "Who is truly exercising corporate leadership in AI-assisted communication?" The human quest to craft an important communication such as an AGM speech is an integral aspect of leadership — and one that becomes even more salient when the company in question operates in a contentious or widely vilified industry. Even if the final speech appears to be polished and human-like in tone, delegating speechwriting to AI can disembody or erode the CEO’s personal involvement and leadership.

We propose that, going forward, a balanced approach should be pursued: AI can provide an initial framework, perhaps stimulate ideas, and the human CEO can then refine this by adding strategic and operational insights along with some uniquely personal embellishments.

As it always has, effective leadership today requires direct engagement between a leader and the speechwriting process. While such an interplay can be labour-intensive, it remains invaluable. Without this engagement, the resulting communication risks becoming a hollow vessel rather than a meaningful leadership statement.

Ethical leadership requires AI to be used as a supportive tool rather than a substitute for genuine executive presence. For AI-driven speechwriting to align with ethical leadership principles, human leaders must engage meaningfully with the technology and not delegate core leadership functions to AI.

This article originally appeared in the winter 2026 issue of the Rotman Management magazine.