Skip to content
Agentic Levels

Everything starts here.

GuestLocal progress only
PreferencesSign in
01Start with one taskBest first move for beginners.02Check your LevelMeasure where you are.03Score an AI resultFind the habit to practice first.04Return to Your WorkScores, links, and checkpoints.
Start here

Begin

HomeThe main entry point.New to AIStart with one useful task.
Know where you are

Measure

Check your LevelUse this after you have tried AI.Fluency ScoreScore an AI result you can review.
Build the habit

Learn

LevelsLessonsTracks
Find the reference

Library

PromptsReferenceResourcesCompare Tools
Turn it into work

Apply

Your Next MoveChoose what AI should change next.Tool SetupGet the tools ready.
Come back later

Return

Your WorkScores, links, and checkpoints.My PathContinue from your level.Updates
Site

Site

PricingAboutFAQ & FeedbackPreferences

© 2026 Fuentes Studio

Privacy·Terms
yourCouncil
Ready to help
✦

What do you want to understand?

Ask anything about what you're learning.

Tracks›AI, Law and Compliance
L0Lesson 1Free

What AI genuinely does for legal work (and the one check that keeps it safe)

AI drafts fast and invents confidently. The skill is knowing which is which.

After this, you'll be able to sort legal tasks into where AI genuinely helps and where its raw output is risky, and you'll run every answer through one human verification step before it leaves your desk.

The idea

If you suspect AI is overhyped and cannot handle real legal work, start here: it already turns a forty-page contract into one clear page in about a minute, and it drafts a first-pass memo while you are still finding the file. That is not a demo trick. It is boring, billable work it takes off your desk today, which is the honest reason to keep reading.

Here is the other half, the part the headlines got right: the same tool will invent a court case that never existed and hand it to you with total confidence. Both are true at once, and the whole skill, the one this track keeps coming back to, is telling them apart before anything goes out the door.

Start with what it does well. AI is a fast first-pass drafter and summarizer. It can turn a blank page into a rough memo, condense a long contract into plain English, or take a stack of documents and pull out the parts you asked about, in minutes instead of hours.

Those are first-draft tasks, where you already know enough to judge the result. That is the safe zone, because you are the expert checking the work, not a beginner trusting it.

The dangerous zone is anything you cannot personally check. Here is the failure that has ended up in court filings: AI invents legal authority. It produces a hallucination (a confident, made-up answer that looks real) in the shape of a real case, with a plausible name, a plausible court, and a plausible quote, none of which exist.

It does this because a model (the AI system behind tools like ChatGPT or Claude, also called an LLM, a large language model) predicts text that fits the pattern of real law, not text it has verified. A fake citation matches the form of a real one perfectly, which is exactly why you cannot catch it by reading.

This is not theoretical. Lawyers have faced sanctions (formal punishment from a court, such as fines or a public reprimand) for filing briefs that cited cases the AI made up. In the widely reported Mata v. Avianca matter (2023, in the Southern District of New York), attorneys submitted fabricated cases that opposing counsel and the judge could not find, because the cases did not exist. Filing fabricated authority is how routine AI use becomes malpractice (a professional failure serious enough to expose you to liability).

Here is the before and after: in the risky version, you ask AI for cases supporting your position, paste its answer into a brief, and file it. In the safe version, AI writes the draft, then you open each cited case yourself, confirm it exists and says what the AI claimed, and only then does a qualified human sign off and file.

The one check before you trust an AI answerA confident, real-looking citation is not a verified one. The only valid check is opening the actual source yourself.
  1. 1AI hands you a draftIt looks finished and cites a case, with a name, a court, and a quote.
  2. 2Did you open the source?Not skimmed the cite, actually opened the case or statute yourself. Reading the cite is not verifying it.no→Open the real sourceyes→Says what the AI claimed?
  3. 3Open the real sourcePull the case or statute from the court site or an official database. A fake cite has no real source to open.only if no↻ then run the check again
  4. 4Says what the AI claimed?The real source confirms the holding or wording the AI put in your mouth.no→Cut it or fix the claimyes→A human signs off
  5. 5Cut it or fix the claimIf the source does not back the claim, the claim does not go in the filing.only if no↻ then run the check again
  6. 6A human signs offA qualified person takes responsibility for every verified claim before it goes out.
  7. 7File or send itOnly confirmed, signed-off work reaches a court, a client, or a colleague.
noyesnoyesrun it again
AI hands you a draftIt looks finished and cites a case, with a name, a court, and a quote.
1Did you open the source?Not skimmed the cite, actually opened the case or statute yourself. Reading the cite is not verifying it.
2Says what the AI claimed?The real source confirms the holding or wording the AI put in your mouth.
A human signs offA qualified person takes responsibility for every verified claim before it goes out.
File or send itOnly confirmed, signed-off work reaches a court, a client, or a colleague.
Open the real sourcePull the case or statute from the court site or an official database. A fake cite has no real source to open.
Cut it or fix the claimIf the source does not back the claim, the claim does not go in the filing.

That safe version is not extra steps bolted on. It is a short, repeatable pipeline you run on every AI answer before it leaves your desk.

The four moves that make AI safeEvery safe use of AI runs the same short pipeline: draft, list the claims, verify each against a real source, then a human signs off.
  1. 1
    AI writes the draftFast first pass on a task you already know enough to judge.
  2. 2
    List every claimPull out each case, citation, deadline, and rule the draft states as fact.
  3. 3
    Check each sourceOpen the actual case or statute and confirm it exists and says what the draft claims.
  4. 4
    A human signs offA qualified person verifies and takes responsibility before it is filed or sent.

The pattern that makes AI safe is the same every time. AI drafts, a qualified human verifies and signs off, always.

Get that habit down here, because the next lesson adds the rule that protects your client before you even hit send: what privilege is, and the single careless paste that can quietly waive it.

AI is safe on first-draft tasks you can check yourself, and dangerous on anything you cannot. Either way, a human verifies and signs off.
Safe zone (you can check it)Danger zone (you cannot check it)
Best forFirst drafts, plain-English summaries, first-pass reviewInventing cases, citations, holdings, or exact clause wording
WhyYou are the expert judging a rough draftThe AI predicts plausible text, so fabrications look real
How to catch errorsRead it the way you would review a junior's draftYou cannot, by reading; you must open the primary source
Before it leaves your deskA qualified human verifies and signs offA qualified human verifies and signs off

The rule is the same in both columns. AI drafts, a qualified human verifies and signs off, always.

Try it (16 min)

Watch out for

  • Treating a confident tone as a truth signal. The AI sounds exactly as sure when it is wrong as when it is right, so confidence tells you nothing about accuracy
  • Asking AI for 'cases that support my argument' and pasting the result into a filing. This is the single move behind the sanctioned filings; if you did not open and read each case yourself, you have not verified it
  • Using AI for a task you cannot personally check. If you would not be able to catch a wrong answer, you are not in a position to trust the right-looking one
  • Assuming a citation is real because it looks perfect. A fabricated cite copies the exact format of a real one, which is why reading it is not verification; opening the source is
  • Letting AI output skip the sign-off because it is 'just a draft.' A qualified human reviews and signs off before anything is filed or sent, every time, no exceptions

Paste this into Claude

Pick a small, low-stakes legal task you already understand well, so you can judge the result yourself. Good examples: "summarize this publicly available statute in plain English," or "draft a short, generic client-update email about a filing deadline." Do NOT use anything client-confidential for this first run. Setting up a safe tool and protecting client data is the very next two lessons; for now you stay on public, non-client text on purpose, so you can focus on the one habit this lesson teaches, verifying the output.

Paste this into your AI tool (ChatGPT, Claude, or your firm's approved tool):

"You are helping a lawyer with a first draft only. I will verify everything before it is used.

Task: [paste your task, e.g. 'Summarize the attached public statute in plain English for a non-lawyer client.']

Rules:
1. If you state any rule, deadline, case, or citation, list each one separately at the end under a heading 'CLAIMS TO VERIFY'.
2. For anything you are not certain about, say so plainly instead of guessing.
3. Do not invent case names, citation numbers, or quotes."

When the answer comes back, take the 'CLAIMS TO VERIFY' list and check each item against a real source (the actual statute, the court's website, or an official database). Mark each one confirmed or wrong.

Created by potrace 1.16, written by Peter Selinger 2001-2019 What good looks like

  • You chose a task you know well enough to judge the output yourself, with nothing client-confidential in the prompt
  • The AI returned a usable first draft plus a separate 'CLAIMS TO VERIFY' list
  • You checked every item on that list against a real, primary source
  • You can point to at least one thing the AI got right and state whether anything was wrong, vague, or unverifiable
  • Nothing reached a client, a court, or a colleague until you personally verified it

When this breaks

  • "AI is bad at law so I should not use it" breaks because it is genuinely strong at first-pass drafting and summarizing; the real rule is task selection plus verification, not avoidance
  • "I will use AI for the hard research and check the easy parts myself" breaks because it is exactly the hard, checkable-only-by-an-expert claims (the citations, the holdings, the doses of legal authority) that it fabricates most convincingly; verify the hardest claims first, not last

Created by potrace 1.16, written by Peter Selinger 2001-2019 You can now

✓

Run a real (non-confidential) legal task through AI, get a draft plus a list of every factual claim, and verify each claim against a primary source before using any of it. If you find yourself trusting a citation because it looks right rather than because you opened it, that is the one thing that is wrong: a fabricated cite is built to look right, so the only valid check is opening the actual source and reading it yourself.

Key takeaways

AI is a fast first-pass drafter and a confident fabricator at the same time. It helps most on tasks you can personally check, and it is dangerous on anything you cannot. The fix never changes: AI drafts, a qualified human verifies and signs off. Next, the rule that protects your client before you even hit send: privilege, and the one paste that waives it.

  1. 1AI genuinely helps with drafting, summarizing, and first-pass review, the tasks where you are the expert checking the work
  2. 2AI fabricates legal authority: it invents cases, citations, and quotes that match the form of real law perfectly but do not exist
  3. 3You cannot catch a fabricated citation by reading it; a fake cite copies the exact format of a real one, so verification means opening the source
  4. 4Lawyers have been sanctioned for filing AI-invented cases (the widely reported Mata v. Avianca pattern); filing fabricated authority is how AI use becomes malpractice
  5. 5The safe pattern is always the same: AI drafts, a qualified human verifies every claim against a primary source, and a human signs off before anything is filed or sent

Was this helpful?

Up nextPrivilege and confidentiality 101: what breaks them when you use AI→
← Back to AI, Law and Compliance