Check incoming NDAs against your playbook
An incoming NDA is compared with your standard positions: term, definition of confidential information, residuals, governing law and more. Acceptable ones are returned with a short note. Deviations are marked with your fallback wording for a lawyer to decide. For legal teams reviewing the same document all week.
Function: Legal and compliance · Industry: Any industry
Check incoming NDAs against your playbook
6 steps
At a glance
- Trigger
- An NDA is received from a counterparty or a business user.
- Typical inputs
- Counterparty NDA drafts
- Your NDA playbook with fallback clauses
- Template NDA
- Requester and counterparty details
- Systems it usually connects to
- Ironclad
- DocuSign
- Gmail
- Slack
- How the work splits
3 rules, 2 model, 1 person steps
How it runs, step by step
6 steps, each tagged by what does the work. Rules are fixed logic, a model reads or drafts, and a person decides.
- Rules Fixed logic in code
- Model AI reads or drafts, with a confidence score
- Person A named person decides
- 1
Read the document
ModelA model identifies each clause and maps it to the playbook items: term, scope, exclusions, return of information, remedies and law.
- 2
Compare with the playbook
RulesEach clause is rated as acceptable, negotiable or outside the playbook by rules built from your positions.
- 3
Propose redlines
ModelFor deviations, a model suggests wording from your fallback clauses, citing the playbook entry.
- 4
Review and decide
PersonA lawyer reviews the findings and redlines, and decides what to accept, change or escalate.
- 5
Return and track
RulesThe marked-up document goes back to the counterparty, and the status is tracked until signature.
- 6
File the signed copy
RulesThe executed NDA is stored and its key terms are extracted to the repository.
Where people approve
The decisions that stay with your team, whatever the confidence score says.
- A lawyer approves every redline before it is sent.
- NDAs outside the playbook go to a senior lawyer.
- Signature follows your delegation of authority.
KPIs to track
What to measure, before and after. Targets come from your own baseline.
- 01Hours from receipt to first response
- 02NDAs accepted without changes
- 03Lawyer time per NDA
- 04Redlines the lawyer changed
Questions about this workflow
Does it sign or send automatically?
Not by default. Acceptable NDAs can be returned with a pre-approved note once your legal team is comfortable, but redlines are sent by a lawyer. That boundary is set during rollout.
What about other contract types?
NDAs are a good first target because they are short and the playbook is clear. Longer agreements need a deeper playbook, and the extraction work above is a better first step.
Which steps use rules, a model and a person?
Rules: compare with the playbook; return and track; file the signed copy. Model: read the document; propose redlines. Person: review and decide. Rules are fixed logic in code. A model reads or drafts and reports its confidence. A named person decides.
What do we need to start?
Typically: counterparty NDA drafts; your NDA playbook with fallback clauses; template NDA; requester and counterparty details. You also need read access to Ironclad, DocuSign, Gmail and Slack, or the equivalents you use. A workflow audit measures your volumes and past cases first, then gives a fixed price for the build, so you can decide with real numbers.
