Throat-clearing phrases are empty openers that delay the presentation of your argument. They slow down sentences, waste space, and frustrate readers. These phrases make the reader dig for the point, and some readers will give up before they find it.

The Illusion and Appeal of LLM Reasoning

Words like reasoning, thinking, and writing are the working tools of the legal profession. But with the rise of large language models, like OpenAI’s GPT, Anthropic’s Claude, and Google’s Gemini, these words are now used in a different way. If we don’t confront their false familiarity, we risk misunderstanding the capabilities of these tools and misplacing our trust in them.

Using Generative AI to Discover What You Don’t Want

Writers often discuss the zero draft—a rough document where they begin shaping their ideas. Anne Lamott calls it the “shitty first draft.” But what if getting to that point feels impossible? Before reaching the zero draft, writers can try something new: the negative draft.

Every generation of senior lawyers complains that junior lawyers can’t write. But becoming a lawyer takes years of post-secondary education and apprenticeship, so it’s not reasonable to interpret this complaint to mean young lawyers are illiterate. So what’s the source of this perennial complaint and how can we address it?

Introduction to the New(ish) Technology Competence

Technology competence is not new, but in the age of generative artificial intelligence (GenAI), it applies in new, more complex ways. Under ABA Model Rule 1.1 and its Comment 8, competent representation includes understanding the benefits and risks associated with relevant technology. When it issued ABA Formal Opinion 512, the ABA reaffirmed that the duty of technology competence applies to GenAI, along with all other ethical duties, including:

I am a fan. An unabashed fan. I admire people openly and I tell them—and everyone within earshot. So if you want my advice on networking, that’s it: Be a fan.

Since generative AI can produce polished text in seconds, it’s tempting to ask: Why write at all? If the end result, like a report, an email, a memo, or a presentation, looks the same whether written by a human or GenAI, why not just let the technology do the work? Because writing isn’t just about producing text. Writing is thinking.

Legal writing often feels formulaic. It follows established patterns and uses predictable structures. But those formulas exist for good reason. Predictable structures help legal readers—judges, lawyers, clerks, and other professionals—quickly understand the argument, locate key facts, and process information. Legal readers rely on them for cognitive shortcuts to handle their caseloads.

To write effectively, you must know your message before you start. Planning your pitch is the first step to writing for your audience. Everything before this stage serves you, not the reader.

Writing isn’t a linear process with a specific set of tools that a writer must use to succeed. It’s more like the messy, disjointed process of putting together a puzzle, where you don’t find the missing pieces until the end. Only after it has taken shape do you see it more clearly. But just because the act of writing is non-linear, doesn’t mean that the process has to be unstructured.