Triage an Incoming Contract Against Your Standard Positions

Give Claude your standard contract positions, paste an incoming agreement, and get a severity-ranked list of every deviation with quoted text, risks, proposed fixes, and a plain-English note for the business client.

The Workflow

1. 1

   Load your standard positions (your playbook)

   Start the conversation by giving Claude your guardrails. List your key clauses with an acceptable range and an escalation trigger for each. This one-pager is your playbook; paste it here, keep it in a saved Claude Project, or package it as a Skill you reuse for every intake.

   PromptCopy

   <playbook owner="[FIRM / LEGAL DEPARTMENT]" contract_types="[e.g., NDAs, vendor agreements]">
   For each clause: ACCEPTABLE = what I can sign without escalation; ESCALATE = what triggers negotiation or sign-off.
   
   - Limitation of liability: ACCEPTABLE = cap at [12 months' fees]; mutual. ESCALATE = uncapped, super-cap, or one-sided.
   - Indemnification: ACCEPTABLE = mutual, limited to third-party claims. ESCALATE = one-sided or covering first-party or consequential losses.
   - Term and termination: ACCEPTABLE = termination for convenience on [30 days]' notice. ESCALATE = auto-renew with no exit, or for-cause only.
   - Governing law / venue: ACCEPTABLE = [STATE]. ESCALATE = anything else.
   - Confidentiality: ACCEPTABLE = mutual, [2–3]-year term, standard carve-outs (public, independently developed, required by law). ESCALATE = perpetual, one-sided, or no carve-outs.
   - Non-solicit / non-compete: ACCEPTABLE = [none / mutual no-hire of named individuals]. ESCALATE = any non-compete or broad non-solicit.
   - [ADD YOUR OWN CLAUSES AND RANGES]
   </playbook>
   
   I am a lawyer at [FIRM / LEGAL DEPARTMENT] and I triage incoming contracts against the standard positions above. Everything you produce is first-pass triage that I will verify clause by clause, not final advice.
   
   Restate each position in one line so I can confirm you read it correctly, and tell me if any position is ambiguous or internally inconsistent. Do not analyze anything yet; I will paste the incoming contract in my next message.

   What you get: Claude restates your playbook in its own words, confirms the acceptable-vs-escalate logic for each clause, flags anything ambiguous, and waits for the contract.

2. 2

   Paste the incoming contract

   Drop in the full text of the agreement you received, inside <document> tags, then tell Claude what kind of contract it is and which side you represent, so it reads the risk allocation from your client's perspective.

   PromptCopy

   <document type="[NDA / MSA / VENDOR AGREEMENT / SERVICES AGREEMENT]" received_from="[COUNTERPARTY]" date="[DATE]">
   [PASTE FULL CONTRACT TEXT, INCLUDING EXHIBITS AND SCHEDULES]
   </document>
   
   Above is the incoming contract. I represent [OUR CLIENT / COMPANY], which is the [DISCLOSING PARTY / RECEIVING PARTY / BOTH (mutual NDA) / CUSTOMER / VENDOR]. Read it in full against the playbook. Do not summarize yet: confirm the contract type and our role as you understand them, tell me how many clauses you intend to flag as deviations, and note any part of the document that looks incomplete (missing exhibit, cross-reference to a section that doesn't exist).

   What you get: Claude confirms the contract type and your side, gives a count of how many clauses deviate from your standard positions, and flags anything incomplete before producing the full analysis.

3. 3

   Flag every deviation, ranked by severity

   Ask Claude to produce the core triage table: each clause that strays from your standard positions, ranked by severity, with the quoted text, the specific risk to your client, and a concrete proposed fix you could put into a redline.

   PromptCopy

   Now produce the triage. For EVERY clause that deviates from my standard positions, give me a row with:
   1. Clause name and section number
   2. Severity: HIGH (escalation trigger / deal-impacting), MEDIUM (off-market, negotiate), or LOW (cosmetic / nice-to-have)
   3. The exact current language, quoted from the document
   4. Which playbook position it deviates from
   5. The risk to my client in one or two plain sentences
   6. A proposed fix: the specific change or replacement language I could redline
   
   Sort HIGH first, then MEDIUM, then LOW. After the table, list any clauses that are MISSING that my playbook expects (e.g., no termination-for-convenience right). Flag anything ambiguous as "VERIFY" rather than guessing, and list any clause my playbook doesn't cover that you think I should look at.

   What you get: A severity-sorted table of deviations, each with section, quoted language, the playbook position at issue, plain-English risk, and a proposed fix, followed by missing clauses, VERIFY items, and anything outside the playbook worth a look.

4. 4

   Draft the redline summary and the client note

   Turn the triage into two deliverables in one go: an internal redline-ready summary you can work from, and a short plain-English note for the business client explaining what needs to change and why.

   PromptCopy

   Using the triage above, produce two things:
   
   A) REDLINE-READY SUMMARY (for me): a numbered list of the changes I will mark up, each as "Section X: [change] ([one-line rationale])", ordered by severity. Keep it tight enough to work from while editing the document.
   
   B) NOTE TO THE BUSINESS CLIENT (plain English, no legalese): 4–6 sentences explaining the handful of issues that matter, what I'm asking the other side to change, and which points are must-haves vs. nice-to-haves. Frame it so a non-lawyer can decide how hard to push. Do not overstate certainty; note that I'm still confirming the details.

   What you get: Two outputs: an internal change list keyed to section numbers with one-line rationales, and a short, non-legalese client note that separates must-haves from nice-to-haves and stays appropriately hedged.

5. 5

   Verify every flag against the actual text

   Before you send anything, read the contract yourself against Claude's output. Confirm each flagged section number and quote is accurate, check the VERIFY items, make sure no clause was missed, and adjust severity and fixes to fit the specific deal and client. The triage is your starting checklist; the positions you take are yours.

   What you get: A reviewed, corrected triage you trust: every section reference and quote confirmed against the document, ambiguous items resolved, severities and fixes adjusted to the real deal, and any AI miss or invented clause caught before it reaches the redline or the client.

Example Output

Illustrative example — names, facts, and figures are fictional.

CONTRACT TRIAGE: One-way NDA (received from [Counterparty A], fictional)
Contract type: NDA · Our client: [Company B], the disclosing party (we share roadmap and pricing; they disclose nothing) · Deviations flagged: 4 (1 HIGH, 2 MEDIUM, 1 LOW)

[HIGH] Confidentiality Term, §5
Current: "The obligations of the Recipient shall expire one (1) year after the date of disclosure."
Playbook: 2–3-year term.
Risk: Our roadmap and pricing stay sensitive well past 12 months; a 1-year tail leaves later-disclosed material unprotected.
Fix: Extend to 3 years from disclosure; trade secrets remain protected as long as they qualify.

[MEDIUM] Definition of Confidential Information, §1
Current: "...information marked 'Confidential' at the time of disclosure."
Risk: Oral disclosures and unmarked documents fall outside the definition.
Fix: Add oral and visual disclosures and a catch-all for information a reasonable person would treat as confidential.

[MEDIUM] Governing Law, §11
Current: "...governed by the laws of the State of Delaware."
Playbook: [Home State].
Risk: Off our standard; adds out-of-state counsel cost on any dispute.
Fix: Change to [Home State].

[LOW] Notice, §12
Current: "...by certified mail only."
Fix: Add email notice with confirmation. Cosmetic; do not hold up signature.

MISSING: No equitable-remedies clause. VERIFY: §7 return-vs-destroy language is ambiguous on backups.

NOTE TO CLIENT: This NDA is close to signable, with one issue that matters: confidentiality only lasts a year, which is too short for our roadmap. I'm asking for three years plus trade-secret protection. Two smaller cleanups (what counts as confidential, and governing law) are worth raising but not dealbreakers. I'm still confirming a couple of points in the return-of-information section before we send it back.

Tips

• •Save your standard positions in a Claude Project so every new intake starts pre-loaded: paste the contract and go.
• •Once the playbook is stable, package it as a Claude Skill so the procedure and positions load whenever you triage a contract, and can be shared across a Team workspace (see Claude Skills for Legal Work).
• •Tighten your ranges over time: when you accept or reject a deviation in a real negotiation, fold that decision back into the playbook so the triage tracks how you actually negotiate.
• •Always tell Claude which side you represent, and for a mutual NDA, say that both parties disclose. The same clause can be a HIGH risk for a recipient and a non-issue for a discloser.
• •Treat every section number and quoted clause as something to confirm against the document. AI can mis-cite a section or flag a clause that isn't there.

Frequently Asked Questions

Prompts used in this workflow

Related Reading

• AI Contract Review: How to Use Claude for Due Diligence
• Claude Skills for Legal Work: Build the Playbook Once
• Claude for Contract Law
• Claude for Corporate Law