CLM Best Practices
Jan 19, 2024

Contract Automation: Where do I start?

Automation of the contracting process, also referred to as contract management (CM) or contract lifecycle management (CLM) is a big topic. There are a lot of tools, articles and books dedicated to this topic, and this article will give you a high-level overview to get you started.

Contract Automation: Where do I start?

Use algorithms to process the image and extract important features from it

Suspendisse sed turpis iaculis sed. In ut ut fringilla enim. Id ultrices neque tincidunt leo varius nulla commodo urna tortor ornare praesent non at nisl erat nunc erat nisl mauris magna dignissim ligula viverra etiam nulla rhoncus dui blandit dolor volutpat lorem viverra turpis et pulvinar vestibulum congue lectus semper arcu diam consequat adipiscing nisl.

  • Lorem ipsum dolor sit amet consectetur  ipsum massa  vulputate.
  • Mauris aliquet faucibus iaculis vitae ullamco turpis nibh feugiat.
  • Ultrices commodo ipsum massa sit vulputate ut arcu turpis.
  • Congue dignissim mauris enim hac enim lacus fermentum ultrices et.

Use machine learning to classify the image into different categories

Leo eu non feugiat adipiscing orci risus amet. Neque etiam purus quisque quis vel. Ipsum nunc justo et amet urna dolor sed et vestibulum risus nam diam dignissim nunc gravida ornare placerat molestie lorem dui lobortis sed massa ac sed laoreet gravida sapien id volutpat elit viverra nisl tortor eu usapien natoque.

Blog Post Image Caption - GPT X Webflow Template
Ultrices commodo ipsum massa sit vulputate justo ut arcu turpis.

Filter the images based on a variety of criteria, such as color, texture, and keywords

Ultrices pellentesque vel vel fermentum molestie enim tellus mauris pretium et egestas lacus senectus mauris enim enim nunc nisl non duis scelerisque massa lectus non aliquam fames ac non orci venenatis quisque turpis viverra elit pretium dignissim nunc vitae in cursus consequat arcu lectus duis arcu feugiat aenean ultrices posuere elementum phasellus pretium a.

  1. Elit nam sagittis et non tincidunt diam et enim aliquet ornare etiam vitae.
  2. Hendrerit aliquam donec phasellus odio diam feugiat ac nisl.
  3. Nibh erat eu urna et ornare ullamcorper aliquam vitae duis massa nunc.
  4. Ac consectetur nam blandit tincidunt elit facilisi arcu quam amet.
Automatically group similar images together and apply a common label across them

Enim tellus mauris pretium et egestas lacus senectus mauris enim enim nunc nisl non duis scelerisque massa lectus non aliquam fames ac non orci venenatis quisque turpis viverra elit pretium dignissim nunc vitae in cursus consequat arcu lectus duis arcu feugiat aenean ultrices posuere elementum phasellus pretium a.

“Nisi consectetur velit bibendum a convallis arcu morbi lectus aecenas ultrices massa vel ut ultricies lectus elit arcu non id mattis libero amet mattis congue ipsum nibh odio in lacinia non”
Convert the extracted features into a vector representation of the image

Enim tellus mauris pretium et egestas lacus senectus mauris enim enim nunc nisl non duis scelerisque massa lectus non aliquam fames ac non orci venenatis quisque turpis viverra elit pretium dignissim nunc vitae in cursus consequat arcu lectus duis arcu feugiat aenean ultrices posuere elementum phasellus pretium a.

99% of all organisations want to reduce contracting costs and 99% of all organisations indicate that they currently do not have the data and technology needed to improve their contracting process according to the latest E&Y Law Survey.

We will break-down the contracting process into the following four stages and review how to get started with automation for each:

  1. Creating the contract
  2. Negotiating the contract
  3. Signing the contract
  4. Managing the contract

Lastly, we will briefly touch on the topic of Artificial Intelligence / Machine Learning and how that plays into automation of contracting.

Creating the contract

Managing your templates

A contract template contains pre-defined legal content and serves as the basis for future contracts of a certain agreement type. Most organisations will have a number of contract templates, and more complex organisations will have different templates of the same type (e.g. an NDA for Investors may slightly differ from an NDA for Suppliers).

For automation purposes, you'd like the templates to be linked. That means, if you make changes to one template you should have the ability to have them trickle down to other templates. A good way of achieving this is through the concept of a "clause library", where your template consists of a collection of clauses and each clause may or may not be shared with other templates. Changes to clauses should trickle down automatically to the relevant templates.

Creating your agreements

Creating an instance of a contract is often done by copying the appropriate template and renaming and adjusting it to the specific situation. The most manual way, will be to literally copy a template file, paste it, rename it and then adjust the specific fields inside the contract.

Automation opportunities exist whereby this whole process is instantly executed upon a certain trigger. The trigger may be the click of a button or even a trigger coming from an upstream system (e.g. CRM platform triggers creation of the contract when moving a deal to a different stage).

For full automation you want the contract to be parametrized, which means that fields that typically require manual updating (e.g. counterparty name, address) are automatically populated based on your counterparty data source. In addition, parametrizing contracts allows you to configure parameters of the contract upon creation - for example the duration of the contract.

Negotiating the contract

For automating the contract negotiation process we will look at the different aspects that are relevant during a negotiation.

Version Management

During the negotiation, the contract will change and you want to ensure you automate version management to a maximum extent. Doing this manually results in increased risks, slowdown of the process and often a frustration to the individuals involved. Read our post for more information on automating contract version management.

Managing the back-and-forth

Negotiation will by definition include some back-and-forth between two or more counterparties. This is typically a very manual process done by a combination of email, instant messages, phone conversations and face-to-face meetings. While the last two may be beneficial from a relationship point of view, you'd want to find a technology solution that helps you eliminate any written communication outside of your contracting platform to avoid it getting lost and to avoid it not being available in the context of the contract.

Making changes to the contract

As you are negotiating, you may want to make changes to the contract or respond to changes that your counterparty is suggesting. When changes are made, you want to be able to automatically keep track of each change (who made it and when) as well as have visiblity into the history of the contractual changes.

Also the process of proposing changes and then either accepting or rejecting these suggestions by the counterparty is a fundamental part of contract negotiation. Most modern text editors support track changes but they may not strictly enforce it which can cause risks in the legal contract negotiation context.

With the latest developments in Machine Learning and Artificial Intelligence it becomes more and more realistic to even have some of these edits be auto-proposed or executed for you. This will require a sophisticated Natural Language Processing (NLP) understanding of the contract negotiation platform that you are using. More is expected on this front over the next couple of years.

Signing the contract

Initiating signing

Once the contract negotiation comes to an end, you want to be able to initiate signing of the contract without friction. During typical negotiations it may not always be clear when a counterparty is ready to sign the document when this is not explicitly indicated during the back-and-forth. Ideally you want this to be an explicit indication, which should then allow either counterparty to initiate signing and automatically trigger the signing flow once both counterparties are ready to sign the same version of the agreement.


The act of signing a contract itself will always involve at least some action by the signer, but the aim should be to minimize manual effort involved without compromising on the risks. Today's e-signature providers do a decent job in this regard but unfortunately they are only one piece of the overal contracting lifecycle and therefore require system integration with other technology solutions used for your contracts.

Managing the contract

Storing the contract

Once the contract is signed, you want to be able to automatically store it in a safe and secure location. File storage providers such as SharePoint and Google Drive allow you to integrate and achieve this objective.

Ideally however, you would store both the file (ie. signed PDF) as well as the digitized version of the contract with all it's historical creation and negotiation context, comments and approval flows. While the PDF may be used for enforcement purposes, the digitized version allows you to understand context and drive further business decisions.

Finding information

Finding information in contracts has historically been an unpleasant task, due to the length of these types of documents and (depending on the organisation) the fragmentation around how they are managed.

What you want to strive for when automating your end-to-end contracting process, is to have a single search bar, that would accept "real" queries (like "What is my SLA with company X?") and then filters through the your contracts and surfaces the precise information you were looking for. An absolute pre-condition for this, is to have your contracts be digitized and stored digitally and not just as files.

Feeding information

Many contracts are signed and then kept as a file on record. To derive real value from your contracts, you want to feed the key parameters to your down- and/or upstream business systems. For example, if you sign a clause that agrees on payment terms that are 30 days from the invoice date then you want to feed this automatically to your finance system to initiate the appropriate invoice, reminders and collection processes on time (and automatically).

Post-Signature actions

Several contract related activities can occur after the original one is executed, for example Amendments, Novations or Terminations. To some extend, automating these activities are similar to what is described in the rest of the blog post but you would want to ensure it can be done in the context and with reference to the original contract.

Using AI and Machine Learning

Artificial Intelligence (AI) and Machine Learning (ML) are broad topics, even when narrowed down to the context of contract automation. Before you start exploring how you can apply AI/ML to your contracts you want to (1) have the basics right in terms of process automation as described throughout this blog, (2) know which (type of) data you are going to need / use for this purpose and (3) have sufficient data to train your models.

Opportunities are endless but a few ideas to get you started are to apply Machine Learning to predict your contracting cycle, apply Natural Language Processing (NLP) for contract negotiation automation purposes or automatically creating organisational approval workflows based on the suggested contract (changes or template) by your counterparty.

About Canveo

Canveo is a contract negotiation and management platform and end-to-end contract automation is our bread-and-butter. Contact us if you are interested to learn more or if you would like to see a demo of our contracting suite.