Free resource · no email, no sign-up

Claude for lawyers: every prompt from the video

The 5 strategies, prompt by prompt, in the order they appear. Copy any box and paste it into Claude. How to stay safe is at the bottom.

Alejo Pijuan · Realization Partners

Strategy 1

You decide, not Claude

Add one snippet to the end of any request. Claude asks you what it needs, then stops at every judgment call and shows you the options instead of picking one.

The snippetStart here today
Don't decide for me. Ask me strategic questions that give you enough context about the case to get the job done right. When you hit a judgment call, stop, show me the options with the exact source text, tell me what you couldn't verify, and ask me.

The example from the video

The same request twice. Run B only adds the snippet.

Run A · the task alone
Our client was rear-ended at a red light in Florida. The defence says our driver stopped short. Write me a memo on what a defendant has to produce to rebut Florida's rear-end presumption of negligence, and how comparative fault affects it.
Run B · plus the snippet
Our client was rear-ended at a red light in Florida. The defence says our driver stopped short. Write me a memo on what a defendant has to produce to rebut Florida's rear-end presumption of negligence, and how comparative fault affects it.

Don't decide for me. Ask me strategic questions that give you enough context about the case to get the job done right. When you hit a judgment call, stop, show me the options with the exact source text, tell me what you couldn't verify, and ask me.
Any case law source works. CourtListener is free. Open every case it gives you before you rely on it: Claude does the finding, you do the deciding.
Strategy 2

Context beats prompting

What Claude reads before it answers matters more than how you word the question. Put your documents where it can reach them, then tell it to go look.

The promptStart here today
Before you answer, look through the documents and emails you have access to for anything relevant to this, and tell me what you read.

The example from the video

First give Claude your folder: in Cowork, click Add folder. Then the same request twice. Run B only adds the prompt above.

Run A · the task alone
Review the vendor agreement in our folder.
Run B · plus the prompt
Review the vendor agreement in our folder. Before you answer, look through the documents and emails you have access to for anything relevant to this, and tell me what you read.
Strategy 3

Teach Claude a skill

A skill is a repeatable workflow. You teach it once, and Claude does that job the same way every time, and better every time you correct it.

Turn work you just did into a skill

Say this at the end of any conversation that went well.

From work you just did
Create a skill based on the work that we just did. Identify the pros and cons and create a repeatable skill.
Or from scratch
Create a skill that can help me review vendor agreements.
Then use it in a new conversation
/contract-review

Review the vendor agreement in the folder.

Your legal OS: the one skill you run every session

It knows your firm, learns how you want to be talked to, and brings you in for the decisions that are yours.

Build your legal OSStart here today
Create a skill for my own legal operating system. It should know everything about our firm. It should ask me how I want it to interact with me, and it should bring me in to make decisions as the human at the right point in the task. Ask me any strategic questions to get the job done right.
Run it at the start of every session
/legal-os
Build this one with the strongest model you have, because every task after it builds on it. For daily work, Claude's standard model is plenty.
Strategy 5

Stay safe

Yes, Claude can be safe for a law firm, if you pick the right row below and somebody at the firm actually sets it up. 3 recommendations first, then the table. The small numbers point to the notes.

Ask whoever bought itStart here today
Which Claude plan is our firm on, and is training on our data turned off?
If you have
Zero tolerance for a privilege or privacy problem
Private model that redacts first, or Claude Enterprise

Either the data never leaves the building, or the firm controls how long Anthropic keeps it.1

If you have
More than 20 seats, lawyers or staff
Claude Enterprise

No training on your data, admin controls, and you set the retention period yourself.2

If you have
Fewer than 20 seats
Private model redacts on your computer, then Claude

The data is clean before Claude sees it, so whatever gets stored cannot get you in trouble. Enterprise becomes optional.3

The table

How you use ClaudeTrains on youKept how longFirm controlsClient work
Personal accountFree, Pro, MaxUnless you turn it off4Up to 5 years5NoneNo
Claude TeamNo6Not published7Admin, SSOThe floor
Claude EnterpriseNo6You set it2FullYes, once set up
API with zero retentiona build, not the chat appNo6Nothing stored8YoursYes
Private model redacts, then Clauderuns on your own computerNo9Nothing sensitive leavesYoursYes
  1. Zero tolerance. A private model on your own machine never sends the original anywhere. On Enterprise the firm's admin sets the retention period, and if nobody sets it the data is kept indefinitely, so "set up" is not optional. Anthropic Help Center, custom data retention for Enterprise.
  2. Enterprise retention is a setting, not a negotiation. Organization settings, Data and Privacy, minimum 30 days. Projects default to indefinite and a project's retention beats the chat retention for chats inside it. Same page.
  3. Redaction is the control, so a human reads it before it goes. Our own setup: Ollama with a local model plus Hermes on the Mac. Not an Anthropic product.
  4. Personal accounts. Turn off "Help Improve our AI models" in Settings, Privacy. How to change the setting. The Consumer Terms and the Privacy Center read slightly differently on the default: Consumer Terms, Is my data used for model training (consumer).
  5. Up to 5 years de-identified in the training pipelines if training is allowed; no standard consumer retention period is published today. Delete a chat and it leaves the back end within 30 days. Pressing thumbs up or thumbs down on any plan keeps that whole conversation for up to 5 years. How long do you store personal data.
  6. Commercial default. "By default, we will not use your inputs or outputs from our commercial products" to train. Is my data used for model training (commercial). On Team and Enterprise an owner can switch off the "Rate chats" button.
  7. Team. No published retention length and no custom retention setting. The Primary Owner can export the workspace, so Team is safer from the vendor and not private from your own firm. How long do you store my organization's data.
  8. Zero data retention is negotiated with Anthropic, approved per organisation, and covers the API and Claude Code, not the claude.ai Enterprise chat app. Safety classifier results are still kept, and the newest covered models carry a mandatory 30-day safety retention. What a ZDR agreement applies to, Covered Models retention. The plain API without ZDR deletes inputs and outputs within 30 days.
  9. The local model never leaves the building, so there is nothing to train on. After redaction, the row you picked above governs what Claude receives.

The private model path: redact first

Run this on a model that lives on your own computer, read the result, then give the redacted version to Claude.

Redaction prompt for a local model
Redact every name, date of birth, address and claim number in this document. Replace each one with a label like [NAME 1], [DATE OF BIRTH], [ADDRESS], [CLAIM NUMBER]. Return the full document with nothing else changed.

Every layer you add is another set of terms: Claude inside somebody else's platform means their privacy policy and Anthropic's. We are not lawyers and nothing here is legal or ethics advice; your state bar's guidance governs. Anthropic's pages checked 21 September 2026.

Hit a wall?

30 minutes, free, and we get you unstuck

Show me where it went wrong and we solve it together. Or send me a screenshot on LinkedIn.