A redline your client can read: a blueprint for Contract Review

You read other people’s paper for a living. A vendor MSA lands on Monday. That is the master agreement that sets the terms for everything after it. SaaS terms land on Tuesday, and an NDA an hour before a call. You read each one the same way, build the issues list, mark the redline, and write the client a memo that says what matters and what to do. Your playbook, the wording you ask for and the fallbacks you accept for every clause, lives in a Word file you last cleaned up two years ago. The rest lives in your head and in the margin comments of old redlines.

This page is a blueprint for a Flow Playbook that carries that method. It is not built. AI Consulting is a Playbook that exists today, and its launch story is the walkthrough for every step below. This blueprint is yours to take. Build it from your own know-how, put your name on it, and launch it as your Playbook. If you do, I would like to hear about it.

The opportunity

The legal market is large, and contract work is where the value leaks. US law firms bring in about $422 billion a year, and the Bureau of Labor Statistics counts 863,700 lawyers with about 28,700 openings a year through 2035. On the client side, World Commerce and Contracting finds that poor contracting erodes almost 9 percent of annual revenue at the average business. Almost 90 percent of business users find contracts hard or impossible to understand. The memo you write is the part they can understand.

AI arrived in the profession faster than the method to use it. Thomson Reuters found organizations using generative AI went from 22 to 40 percent in a year, and only 18 percent track whether it pays. Among legal organizations, active use went from 14 to 26 percent, and 48 percent of law firms had no formal policy. Clio found only 8 percent of solo practitioners and 4 percent of small firms had adopted AI widely, while over 80 percent of legal professionals expected their use to grow. The tools are in. What most reviewers do not have is their playbook written down where a tool, a client or a new hire can read it.

Clients and regulators are both moving. Almost one-third of corporate legal professionals say they are reconsidering outside firms that cannot show AI-enabled value within a year. The ABA issued Formal Opinion 512 on July 29, 2024, its first ethics opinion on generative AI, and it turns on four old duties. Competence, confidentiality, communication, and reasonable fees. And the custom GPT some reviewers loaded their playbook into retires on December 11, 2026. A Playbook is plain files in your own GitHub. Nobody can retire it.

The signals

Each figure measures something narrower than it sounds. Surveys count who answered. Vendor research counts a vendor’s view. A market estimate is a model. Read them as a direction, not a forecast.

What your Playbook holds

The figure at the top of this page is the folder as it could sit on GitHub. Six Markdown files. Here is what each one does.

The README is the front page. It says who the Playbook is for, what a reader will have at the end, and the order to read the documents in. A stepped figure shows a draft becoming a memo. An isometric figure maps the path.

Issues List Method is the backbone. How you read a draft, in what order, and what earns a place on the issues list before the redline starts. A Workflow Path draws the read, with the draft on the left and the ranked issues list on the right. The list is a table. What you have not confirmed is marked to check, and Flow counts the marks until you clear them.

Clause Library is the method most reviewers keep in their head. For each clause, the wording you ask for, the fallbacks you accept in order, and the point where the client walks. It is a table, one row per clause. An Option Comparison Skill draws the positions side by side when a client needs to see why the second fallback is still fine. A callout holds the walk-away, so nobody misses it.

Redline Memo Guide is the craft. How a finished redline becomes a memo a business owner reads in five minutes. What goes first, what to leave out, and how to say a liability cap is bad without a lecture. A Scorecard Skill draws the risk rating from the clauses that drive it. A stepped figure shows how the memo is built from the issues list. A Decide form lets the client choose accept, push back, or walk, and records the reason beside the memo.

Closing and Obligations Register is what must be true before signatures, and what lives on after them. The closing checklist is an Approval Card. You tick it, type your name, press Sign off, and the record stays with the deal. A Register Skill draws the obligations after signing, with renewal dates, notice windows and who owes what.

Worked Example is a vendor MSA for a made-up client, reviewed end to end, from issues list to signed closing checklist, with the choices explained. A reader learns more from one finished review than from ten rules.

What Flow does for this work

Chat answers from the Clause Library, not from the internet. An empty Chat offers four of the README’s questions as buttons. “What is our fallback on a liability cap?” Chat searches the folder, answers from the passages it finds, and links each answer to the page it came from. When the Clause Library does not say, Chat says so.

A Skill draws the risk rating you already give. Select the memo’s rating section and run Scorecard. It draws the rating from the clauses the text names and nothing else. Option Comparison does the same for the fallbacks on a cap, three positions in one figure a client can hold up.

A Decide form records the client’s call. Under the memo sits a form with one button. The client picks accept, push back, or walk, and types the reason. Flow records the option and the reason beside the memo.

A Job keeps your ethics section current. Bring your bar’s generative AI guidance page in with New from Web Page and choose Follow the source. The Memo Guide holds a short section on what you tell clients about tools and billing, and a Job keeps it current from that source. When the guidance changes, the next run redrafts the section and waits for your review.

Bring In All reads a model clause set in one go. When a trade body publishes its model clauses chapter by chapter, Flow offers Bring In All and reads them into a new folder with a README in the author’s order. Your Clause Library can then cite the model wording by page.

A client’s Word or PDF comes in with a checklist beside it. The vendor’s MSA arrives in Word. Bring it in and its tables stay tables. The Sources tab lists what to settle before you rely on it. Walk Through with Chat takes the items one at a time.

Sources and Change Summary show the client what the memo was made from. A memo built from the Clause Library, the issues list and the client’s draft carries a Sources element that lists all three and marks any that changed since. A Change Summary shows what moved on the second turn, who changed it and which day. The client sees the method behind the memo.

How you build it in Flow

The AI Consulting story walks every one of these steps on a real screen. Follow it with your own material.

1. Add an empty folder and choose it. Chat answers from the folder before any document exists. The walkthrough shows it at an empty folder, and Chat already in it.
2. Ask Chat for the README. Describe who the Playbook is for and what you want a reader to have at the end. Chat writes it in your voice and marks every claim it cannot stand behind. See a front page, in the author’s voice.
3. Bring in what you already have. The playbook Word file from two years ago, a past redline memo with the client’s name changed, the bar guidance page you cite in engagement letters. New from Web Page turns a page or a shared AI chat into a document with its links kept. See an old AI chat became a reference.
4. Let Ideas pick a Skill. Press Suggest on your Issues List Method. Ideas reads the sections and names a Skill for each, a Workflow Path for the read, a Register for the obligations after signing. A figure or a form waits in Review Changes until you keep it.

5. Ask Chat for the next document with your own pages as sources. The Redline Memo Guide can be written from your Clause Library and three past memos. Repeat until the path is done. See the next document, from his own pages.
6. Review every change. When you merge two fallbacks or rename a document, every page that pointed at it follows. See Review changed the plan, and the source followed.

Apply it to a client job

A Playbook is for using, not only reading. Larkspur Robotics, a made-up client, sends you a vendor’s MSA. Start a folder for Larkspur in the Playbook and bring the Word file in. Ask Chat to read it against the Clause Library and draft the issues list the way the Issues List Method says, with every clause it is unsure about marked to check. Run Option Comparison on the liability cap, draft the memo from the Redline Memo Guide, run Scorecard on the rating, and add the Decide form. Larkspur picks push back, with the reason. After the third turn the cap lands on your second fallback, the closing checklist gets signed, and the Register holds the renewal date and the notice window.

Then the lesson goes back into the Playbook. The vendor’s wording on breach notice was better than your fallback, so the Clause Library gets a row. A new associate can read the Method and the Clause Library on their first day and review their first NDA the way you would. That is the training problem answered one person at a time.

Vendor MSA, imported.mdIssues list.mdRedline memo.mdRedline memo.mdRedline memo.mdClosing checklist.md Imported · 3 to check2 claims to check1 change to reviewKeptDecision recordedSigned off

Larkspur Robotics

Vendor MSA, imported

Proposed

Folder

Imported · 3 to check

Larkspur Robotics

Issues list

Proposed

Diff

2 claims to check

Larkspur Robotics

Redline memo

Proposed

Option Comparison

1 change to review

Larkspur Robotics

Redline memo

Proposed

Scorecard

Kept

Larkspur Robotics

Redline memo

Proposed

Form · Decide

Decide

Decision recorded

Larkspur Robotics

Closing checklist

Proposed

Approval Card · Sign off

Sign off

Signed off

01Start the client folder02Ask for the issues list03Compare the fallbacks04Rate the risk and keep05Client decides06Sign off the closing

Publish it, and keep it current

When the folder is ready, choose Publish and then GitHub Repository. Flow sends the files and nothing else. A reader brings the Playbook in with File, then New from GitHub, and the folder’s address. Check the repository’s visibility first. Your method can be public while every client’s draft, redline and memo stays in their own folder on your Mac.

When a rule changes and you publish again, every reader’s copy shows the update as a change they review. They keep their own edits. Nothing is replaced behind their back.

The same source can also become a GitHub Pages site, a PDF, an EPUB, or Word and Excel files for a client’s team. Chat on the Playbook, and the figures a reader steps through, stay in Flow.

What it costs

Bringing any Playbook into Flow is free on Base. Writing with Chat, and Chat on a Playbook, need Flow Pro at $10 a month. Publishing to GitHub needs the Publish add-on too, another $10 a month. There is no fee per Playbook, so publish one or twenty for the same price. Any AI you connect follows the terms of that service. Publishing does not bring clients on its own. It gives the clients you earn a living copy of your method.

Start here

Read the walkthrough once, end to end. Then add an empty folder in Flow, name it, and describe how you review a contract to Chat in three sentences. What you read first, what goes on the issues list, and what the memo must say. The README it writes is the first document of your Playbook. If you want to talk it through first, the Playbooks page has one email address and four questions.