AI-assisted robotic process automation helps businesses achieve unprecedented efficiency
Discover IBM Watson Discover IBM Cloud
AI android in front of interactive abstract of formulas

Companies around the world are embracing digital transformation, and employees are the key enablers of a successful transition to a better way of working. To help its clients’ staff focus on strategic activities, not low-value tasks, Contextor teamed up with IBM to augment its robotic process automation solutions with artificial intelligence capabilities.

Business Challenge

Contextor uses robotic process automation (RPA) to help its clients augment the human capabilities of their employees. The company realized that artificial intelligence could help it take RPA to the next level.


Contextor is training IBM Watson® Machine Learning to recognize patterns in user activity and map out business processes automatically, helping it deliver RPA solutions to clients faster than ever before.

Results 20%
acceleration in RPA solution development with cognitive business process mining
15% to 95%
reduction in average handling times can be realized by adopting RPA
Full ROI
can be achieved within weeks or months with Contextor’s RPA solutions
Business challenge story
Automating tasks, boosting productivity

No matter what industry you operate in, the chances are that many of your staff spend too much of their time on low-value, often monotonous tasks. From manual data entry and validation to information retrieval and answering simple customer inquiries, your workforce is probably allocating time and talent to activities that could be automated.

What if you could give your staff some of their precious time back, and allow them to focus on tasks that really help your business thrive? French software developer Contextor is working to help companies like BNP Paribas, EDF Energy, Bouygues and Engie achieve exactly that.

For the past 15 years, Contextor has been developing Robotic Process Automation (RPA) solutions that enable companies to automate the less exciting parts of their employees’ jobs—anything that involves switching between apps or screens, copying and pasting data, retrieving files, and so on.

However, many tasks require more than just mechanical data processing—they need some intelligent agent to interpret data and use it to make decisions. For example, although a traditional RPA solution might be able to input incoming customer emails into a CRM system automatically, it would still need a human to read the emails and make sure the most urgent ones are handled first.

With the rise of artificial intelligence and machine learning technologies, Contextor saw an opportunity to take RPA to the next level by enhancing its solutions with cognitive capabilities. For example, a cognitive RPA solution could be trained to understand the content and sentiment of thousands of emails, and instantly highlight the most relevant messages to help customer service teams prioritize more effectively.

The company also realized that cognitive technologies could help it deliver value faster, by speeding up the deployment of its RPA solutions. Since each of Contextor’s clients has its own unique systems and workflows, the first phase of any RPA project involves a process known as “business process mining”. A logging tool is installed on a user’s PC, which captures every action the user takes as they work on everyday tasks. Contextor’s expert consultants then review the logs and identify the sequences of actions that are necessary to complete important business processes, such as new client onboarding, or “know your customer” validation. These action sequences can then be automated using the RPA software.

Pierre Col, CMO at Contextor, explains: “Business process mining is essentially a matter of intelligent pattern recognition—the kind of problem that machine learning excels at solving. We knew that if we could harness machine learning during the business process mining phase, we could reduce the amount of time our consultants need to spend analyzing logs, and accelerate the design phase of our RPA projects significantly.”

With cognitive technologies from IBM Watson, our RPA solutions will help our clients combine automation with intelligence, empowering employees and helping companies drive their digital transformation. Pierre Col CMO Contextor
Transformation story
Enhancing RPA with cognitive technologies

Contextor evaluated several different vendors in the machine learning space, and was impressed by IBM®’s ability to provide cognitive and cloud technologies, and its position as a trusted IT provider for many large enterprises in France and around the world.

Pierre Col confirms: “IBM and its Watson cognitive solutions are highly regarded by major players in the banking and energy sectors. We felt that building a stronger relationship with IBM could open doors for us both technically and commercially. For example, there is a lot of potential for IBM to act as a systems integrator, using our RPA software to build custom automation solutions for its clients.”

Contextor has started its cognitive journey by using IBM Watson Machine Learning to build a machine learning model that automates and accelerates the business process mining phase of new projects. The model is trained using sequences of actions that have already been identified as known parts of common business processes. It can then be used to analyze new sequences, detect similar patterns, and assess whether they are part of the same process. This gives Contextor’s consultants instant insight into a company’s working practices, without spending hours poring over thousands of lines of logs.

As a next step, Contextor is also evaluating how IBM Watson Natural Language Classifier can be embedded into its RPA solutions for clients—for example, to help analyze incoming emails from customers, understand their contents and context, and route them to the most appropriate customer service agent for further processing.

Contextor also sees opportunities for IBM Watson Assistant to augment the capabilities of human employees, by acting as an AI-powered chat bot that can answer questions and retrieve information almost instantly. Such chat bots could be used as a first point of contact for customer service, helping to triage customer inquiries and automatically triggering RPA workflows if appropriate. They could also be used internally as a virtual personal assistant for employees, providing intelligent alerts, answering questions, and performing RPA tasks when requested.

The ability to integrate Contextor’s RPA technology with IBM Watson services via easy-to-use cloud-based APIs is also a key advantage: it means Contextor’s developers can quickly add cognitive capabilities to an RPA project whenever necessary, without having to redesign the entire solution.

Pierre Col notes: “We are now building cognitive-enhanced RPA solutions that can run either on-premise or in the IBM Cloud®, and we’re educating our clients about the advantages of the cloud-based approach. For example, cloud technologies can accelerate speed-to-market by avoiding the up-front investment, installation and configuration concerns that you get with an on-premise solution. The savings on hardware and software maintenance over the long term can also be significant.”

Results story
Focusing on what matters most

By integrating IBM Watson and Cloud technologies into its RPA solutions, Contextor is in a better position than ever before to help its clients to automate low-value, tedious tasks, and improve productivity and efficiency. 

Pierre Col remarks: “With our cognitively enhanced RPA solution, our clients will be able to improve key business metrics such as average handling time and first-call resolution even further. We’ve already seen clients accelerate processes such as new client onboarding by 80 percent or more, and as we add artificial intelligence to the mix, we’ll open up even more complex processes to these kinds of time savings.”

The IBM Watson solution should also help reduce time-to-value, which is a critical metric for RPA projects. For example, one of Contextor’s key clients in the banking industry will only proceed with automation projects if it is confident of obtaining return on investment in less than a year.

Pierre Col comments: “Our initial results show that by using machine learning to automate our business process mining workflow, we can accelerate RPA deployments by at least 20 percent. As a result, clients can start seeing the benefits of RPA within weeks, and achieve a full return on investment in just a few months.”

He concludes: “When people hear about automation, they worry that robots will take away their jobs; but RPA is about augmenting people, not replacing them. The real potential of robots lies in their ability to eliminate the tedious tasks we encounter every working day, so we have more time to develop our skills and deliver value. With cognitive technologies from IBM Watson, our RPA solutions will help our clients combine automation with intelligence, empowering employees and helping companies drive their digital transformation.”

The word "Contextor" is written next to an orange logo of a finger pushing a button. Beneath this is written "we augment humans with bots."

Founded in 2000, Contextor designs software solutions, including robotic process automation (RPA). Located in Orsay, France, the company produces application assistants and wizards to help improve its customers’ operational efficiency.

Take the next step

To learn more about IBM Cloud, please contact your IBM representative or IBM Business Partner, or visit the following website:

View more case stories Contact IBM


© Copyright IBM Corporation 2018. 1 New Orchard Road, Armonk, New York 10504-1722 United States.

Produced in the United States of America, March 2018.

IBM, the IBM logo,, IBM Cloud, and Watson are trademarks of International Business Machines Corp., registered in many jurisdictions worldwide. Other product and service names might be trademarks of IBM or other companies. A current list of IBM trademarks is available on the web at “Copyright and trademark information” at

Not all offerings are available in every country in which IBM operates.

The performance data and client examples cited are presented for illustrative purposes only. Actual performance results may vary depending on specific configurations and operating conditions.

All client examples cited or described are presented as illustrations of the manner in which some clients have used IBM products and the results they may have achieved. Actual environmental costs and performance characteristics will vary depending on individual client configurations and conditions. Contact IBM to see what we can do for you.

The client is responsible for ensuring compliance with laws and regulations applicable to it. IBM does not provide legal advice or represent or warrant that its services or products will ensure that the client is in compliance with any law or regulation.