How Prompting Claude Changed: The 2024 Playbook vs. What Works Now

Every Era's Advice Was Right, Then Wrong

If you learned to prompt AI from a 2024 CLE, a LinkedIn carousel, or a prompt pack for lawyers, you learned techniques that, in many users' experience, produced real improvements. Role-play framing seemed to help 2023-era models hold a professional register. Step-by-step instructions seemed to keep 2024-era models from skipping steps. "Think step by step" deepened reasoning on models that would not reason deeply on their own.

The uncomfortable part: every one of those techniques compensated for a specific model weakness, many of those weaknesses faded as models improved, and the compensations did not become harmless leftovers. They became costs. A prompt built for the model you learned on can actively degrade the model you use now. This post is the story of how that happened and what replaced it, because understanding why the old advice existed is the fastest way to stop paying for it.

The Incantation Era (2023 to Mid-2024)

Early chat models were brilliant and unreliable in equal measure, and users discovered that certain phrases shifted the odds. "You are an expert attorney" nudged the register upward. "Think step by step" (a technique from an actual research paper) elicited visible reasoning that improved answers. "Take a deep breath" measurably helped one leading model on math problems, which tells you how strange this era was. Prompting looked like spellcasting because, functionally, it was: nobody fully knew why the phrases worked, only that they did.

The legal profession translated this into templates. Prompt packs sold role preambles, output scaffolds, and magic closers ("be thorough, cite your sources, do not hallucinate"), and they were worth using at the time.

The Framework Era (Mid-2024 to 2025)

As models steadied, the advice matured into acronym frameworks: role, context, task, format, and their many cousins. We taught one ourselves in our CRAFT framework guide. Frameworks were a real upgrade over incantations because most of their content was not magic at all: they forced you to state the facts, the audience, and the deliverable, which is simply briefing the work properly.

But the frameworks smuggled the incantation era forward inside them. The R in every acronym was role-play. The step-by-step choreography stayed. The verification commands multiplied ("double-check every citation before responding"). Templates grew because adding a rule always felt safer than deleting one, and it was easy for a legal prompt template to grow into pages of accumulated compensations wrapped around a few lines of actual substance.

The Turn (2026)

Then the model builders started deleting their own instructions. Anthropic removed more than 80 percent of Claude Code's system prompt for its Claude 5 generation models with no measurable loss on its coding evaluations, moving functions such as verification into separate skills the model calls when needed. Boris Cherny, the creator of Claude Code, began giving Claude Code users advice that would have sounded reckless two years earlier: every six months, delete your CLAUDE.md file and your skills. That advice was aimed at coding, but the same logic applies by analogy to a lawyer's prompt templates. In the same talk, Cherny's advice for current models was to describe the task, the guardrails, and the exit criteria, and then let the model cook.

The reasoning is not mystical. Current models do much of what those instructions used to force. Anthropic's prompting guide says a general instruction like "think thoroughly" often produces better reasoning than a hand-written step-by-step plan, and that Claude Opus 5 verifies its own work well without being told to. Instructions that force last year's workarounds onto this year's model rarely add safety and can override better judgment. Your twelve-step contract-review script makes the model follow your twelve steps instead of a plan that may well be better. Your "double-check everything" line may mostly add cost: the same guide warns that verification instructions carried over to Claude Opus 5 can cause over-verification, adding tokens and latency. (None of this replaces checking citations yourself; more on that below.) Your elaborate role preamble can shrink to a single sentence; Anthropic's prompting guide says even one sentence of role in the system prompt makes a difference. We covered the deletion side of this shift in depth in Stop Over-Prompting Claude; what follows is the constructive side.

What Works Now: Context Over Incantations

The current method fits in one sentence: state the goal and the constraints that matter, supply the context only you have, and let the model find the path. In practice, a strong legal prompt today has five ingredients, none of them magic:

• The facts of the matter. Generosity here has always helped and still does. Two pages of relevant facts with one sentence of instruction beats one paragraph of facts wrapped in two pages of rules.
• Jurisdiction and governing law. "Under Florida law" changes the answer. No model generation has made this optional.
• Audience. A memo for a partner, a letter to opposing counsel, and an email to an anxious client are three different documents from the same facts. Say who reads it. This is what the old role-play was groping toward; if you still want a role, one sentence is enough.
• Your actual constraints. Length limits, the client's authorized range, positions your firm will not take, citation style. Constraints are the load-bearing part of a professional prompt; they survived every purge.
• Output format. Table, numbered issues, letterhead-ready letter. Cheap to specify, expensive to retrofit.

Compare the eras on the same task. The 2024 version: "You are a senior insurance-defense partner with 20 years of experience. Think step by step. First, review the demand letter. Second, identify each claim..." and ten more steps. The 2026 version: "Draft a response to this demand letter that positions us for the mediation. Facts and the letter attached; Ohio law; audience is opposing counsel who overreached and knows it; two pages; firm but door-open." The second prompt is shorter, and it gives a current model what it actually needs: the goal, the facts, the law, the audience, and the constraints.

What Survived Every Era

Three things never stopped being true, and they separate minimal prompting from lazy prompting:

• Exact requirements stay exact. Court-mandated formats, citation form, filing procedures: where only one sequence is acceptable, spell it out precisely, every time. Guidelines loosen; requirements never do.
• Verification is a workflow, not a prompt line. "Cite your sources" never made citations real, and a public database now tracks more than 2,000 court decisions dealing with AI-hallucinated material to prove it. Every citation gets confirmed in a real database before it enters a filing, in every era, under every prompting philosophy.
• Iteration is the actual skill. The first prompt is a draft. "Tighten this," "more formal," "now a client version" have always been where the quality comes from, and conversation is cheaper than the perfect mega-prompt in every model generation.

If You Have a Template Folder, Do This

Do not delete it; retune it. Save a copy, strip each template down to the five ingredients above (trim the role-play to a sentence, cut the step choreography, the scripted step-by-step reasoning plans, the verification theater), run old and new on the same closed matter, and keep whatever the comparison proves. Often the minimal version holds up, and some deleted lines turn out to have been costing quality; occasionally a line turns out to be load-bearing context in disguise, and it earns its way back in as one plain sentence. Put the exercise on a six-month cycle, because the model under your templates will change again.

The deeper lesson of the whole arc: prompting advice has a shelf life, and the only durable skills are the ones that were never model-specific: knowing your facts, your audience, your constraints, and your duty to verify. Those were lawyering skills before they were prompting skills. They will outlast whatever comes after this era, too. For the working library that applies all of this, our Claude prompts for lawyers collection and the prompt library are maintained against the current models.