Module 1
What document automation is: assembling documents from templates and data
Lawyers write the same documents over and over: engagement letters, non-disclosure agreements, employment contracts, board minutes, powers of attorney, demand letters. Most of the text is the same each time and a few facts change. Document automation is the practice of capturing what stays the same in a template, capturing what changes as a small set of questions and writing down the rules that decide which text appears. A well-built system produces in minutes a document that would otherwise take an hour, and produces it correctly each time. A badly built one produces confident errors at speed. This module explains what document automation is, where it pays and where it does not, and the shape of the whole course.
Hover over an idea to light up what it connects to, click it for its definition, minimum requirements, an example and the usual trap, press Play to watch the map build step by step, or trace a short case through it.
Simplified teaching map, in general terms. Check the law where you work. On a small screen, scroll the map sideways.
By the end of this module you can
- Explain how a document is assembled from template, data and rules.
- Tell three approaches apart: simple templates, assembly and AI drafting.
- Choose good candidates for automation.
- Name the benefits and risks.
- Describe the life cycle of an automated document.
Part 1. The lecture
Assembly: template, data and rules
A document produced by assembly has three ingredients.
| Ingredient | What it is | Example (engagement letter) |
|---|---|---|
| Template | The text that is fixed, with places marked for what changes. | “Thank you for instructing us in connection with …” |
| Data | The facts for this document, gathered by answering questions. | Client name, matter, fee, whether urgent. |
| Rules | The logic that decides which text appears and how values are shown. | If the client is a company, add the paragraph about authority to instruct. |
Put them together and the result is a finished document. Change only the data and the same template produces a different document; change the rules and the same data produces a different document. All of the skill in document automation lies in writing the template, the questions and the rules so that every combination of answers produces a document that a careful lawyer would be content to sign.
A tiny example
Template: Dear {{client_name}}, our fee is {{currency}}{{fee | money}}.
Data: client_name = Ms Novak; currency = £; fee = 4500
Result: Dear Ms Novak, our fee is £4,500.
The double braces mark a place for data. You will build templates like this in the Template Tester during the course.
Three ways to produce a document
| Approach | How it works | Strength | Weakness |
|---|---|---|---|
| Word processor template | A document with blanks that a person fills in by hand. | Cheap, familiar, flexible. | Slow, easy to miss a blank, no logic: a person must remember which paragraphs to delete. |
| Assembly (automation) | A template with variables and conditional text, filled from answers. | Fast, consistent, testable, with an audit trail. | Takes work to build and maintain; only as good as its rules. |
| AI drafting | A language model writes text from instructions or examples. | Flexible for unusual requests and first drafts. | Not predictable, not guaranteed to follow the rules, must be checked in full. |
These are not rivals. A mature legal team uses all three: assembly for the high-volume documents that must be right every time, a word processor for one-offs, and AI as an assistant that suggests drafts, summarises or helps to write the clause library, always with a lawyer reviewing. The key difference is predictability. An assembly system gives the same output for the same inputs; a language model does not.
- Use assembly when the document is common, the rules are known and a mistake is costly.
- Use a simple template when the volume is low and the document is simple.
- Use AI drafting as support for first drafts and ideas, never as an unreviewed source of a final legal document.
Good candidates
Not every document should be automated. The criteria are close to those for choosing any project in the Foundations course.
| Criterion | A good candidate | A poor candidate |
|---|---|---|
| Volume | Dozens or hundreds a year. | A few a year. |
| Sameness | Most of the text is the same. | Each document is substantially different. |
| Rules | The choices can be written down. | The choices rest on a lawyer’s judgement of the whole situation. |
| Stability | The text changes rarely. | The law or the form changes every few months. |
| Cost of error | Errors are costly, so consistency is valuable. | Errors are trivial. |
| Owners | Someone will keep it up to date. | Nobody will. |
Typical good candidates are engagement letters, NDAs, standard supplier and customer agreements, employment offer letters and contracts, standard notices, board resolutions, powers of attorney, settlement agreements on a common pattern and routine correspondence. Poor candidates include a bespoke acquisition agreement or a complex pleading, where the value is in the lawyer’s judgement about each clause. Even there, a clause library can help, as Module 4 shows.
Benefits and risks
The benefits are real, but the risks are the reason for most of this course.
| Benefits | Risks |
|---|---|
| Speed: minutes instead of an hour. | Silent errors: a wrong rule produces wrong documents in volume. |
| Consistency: the same words every time. | Stale text: the law changes and the template does not. |
| Fewer mistakes: no missed blanks or stale names. | Over-reliance: users stop reading the output. |
| Self-service: the business can produce routine documents safely. | Unauthorised use: a document produced for one context is used in another. |
| Audit trail: who made what, from which version. | Confidential data kept in the wrong place. |
| Lawyers freed for judgement. | A template nobody owns, which becomes a hazard. |
The central discipline
Every automated document must have an owner, a version, a review date and a test set. A template that nobody is responsible for is worse than no template, because people trust it.
The life of an automated document
- Request or trigger: a person needs the document, or an event (a new client) calls for it.
- Questions: the user answers a short questionnaire. The system checks the answers.
- Assembly: the template, the answers and the rules produce a draft.
- Review: a person reads the draft, with a lawyer checking where the rules require.
- Signature or sending: the document is signed, filed or sent.
- Storage and record: the document and the answers that produced it are stored together, with the version of the template.
- Maintenance: the template is reviewed, tested and updated when the law, policy or business changes.
The course follows this life cycle. You will learn to write templates (Module 2), put logic in them (Module 3), build a library of clauses (Module 4), design the questions (Module 5), test (Module 6) and run the system (Module 7). The capstone has you build and test a complete document pack.
Part 2. Lab: Good Candidate?
Decide whether each document is a good candidate for automation.
Situation 1 of 6
The engagement letter, used 300 times a year with a few variations.
Where does this belong?
Part 3. Lab: Which Approach?
Choose the best approach for each situation.
Situation 1 of 2
A sales team requests an NDA from legal about twice a day. The terms follow a playbook, and a wrong clause could create real exposure.
Which approach?
Part 4. Check your understanding
Ten questions drawn from a larger pool. Sign in to have your score saved towards your certificate.
You have finished the free module
Here is what you can do now, and where the course goes next
Module 1 gave you
- Explain how a document is assembled from template, data and rules.
- Tell three approaches apart: simple templates, assembly and AI drafting.
- Choose good candidates for automation.
- Name the benefits and risks.
- Describe the life cycle of an automated document.
Next, 6 more modules and a capstone
- Module 2: The anatomy of a template: fixed text, variables, types and the data dictionaryYou will learn to separate fixed text from variables and choices.
- Module 3: Conditions and logic: text that appears only when it shouldYou will learn to write if and else blocks in a template.
- Module 4: Clause libraries and playbooks: standard text, fallbacks and who decidesYou will learn to build a clause record that others can use.
- Module 5: Designing the questionnaire: asking for the facts, once, in plain wordsYou will learn to ask only what is needed, once.
- Module 6: Testing and quality: proving that every document comes out right
- Module 7: Running the system: ownership, access, security, rollout and measurement
- Capstone: Capstone: build and test an automated employment offer letter
Each module has its own practice labs and a graded quiz, and a Certificate of Completion follows when you pass them all. The whole course is $15 once, or included in an All-Access Membership.
Two Ways In
Introductory PriceDocument Automation: buy it on its own, or get it with All-Access
Unlock all of Document Automation on its own with a one-time purchase, or get it as part of an All-Access Membership, which also covers every course and the other paid tools. A member never needs to buy it separately.
This is an early, introductory price for a brand-new product — it’s expected to rise as we add more content. Buy now and it’s yours at today’s rate, forever.
No account needed: you pay, and we email you a one-click sign-in.
All-Access is $19.99 a month or $149 a year, and covers every course and most tools, this one included. Create a free account to subscribe.
Look first, then buy. Free previews on every product page. Secure payment by Stripe. Pay once, keep it forever. Details
See what is included in All-Access →Not ready to buy? Create a free account to save your quiz scores and your place in this course, and to get the printable reports from the practice rooms.
General education on legal document automation, using invented organisations, documents and figures. It is not legal advice. Clauses and letters are illustrations of structure, not recommended wording: real documents must follow the law that applies and be checked by a lawyer.
Teaching? Share this with your class
Free to use in class. The free parts open for everyone, no account needed.