Writing for AI

Writing for AI

While data models and algorithms hog the limelight, we often overlook the importance of well-structure content in AL systems

We have long been talking about the wonderful possibilities of Artificial Intelligence – automated systems, chatbots, and all. They are emerging technologies and marvels of data science indeed. But not all of it is algorithm or data. The greatest challenge in actually using any of these emerging technologies is understanding and clearly defining the business need as well as having the right data and content to fuel the technology engine.

“Articulation” is a key part in any problem. A problem is not really a problem, unless you assess the situation, process the information and articulate it in a well-formulated problem statement. Only then can you set out to find a solution to it. All this involves logic, and some good old-fashioned writing in plain human language – the stuff that the industry calls “content”. Be it conditional programming, automotive solutions or chatbots, and user submits the problem to it via language and gets a solution in a structured format as a result of pre-planned, well thought out content structuring. Chatbots are but channels to content and information to solve specific problems. The end solution, then, is a combination of writing and programming – none of which can be lacking in importance. Sadly enough, the contribution of content professionals is often overlooked while praising the successes of an AI system.

Seth Earley, the CEO of Earley Information Science and the editor and data analytics for IT Professional Magazine from the IEEE, who currently works on cognitive computing, knowledge engineering, data management systems, taxonomy, ontology, and metadata governance strategies – has been pointing out this unfortunate scenario. In a recent article, he writes:

“For some time, the AI vendors claimed that all you had to do was “train the AI,” but never defined exactly what that meant. “We need more training,” and “We need the right learning content,” were the often-repeated statements from developers that accompanied change order requests and additional funding requirements. Now, many companies are aware that chatbots are channels to content and data and realize that AI is actually a content delivery platform—that the magic is in how the content is structured and rationalized.”

All companies produce various kinds of content – technical product documentation, instructional content, and support information. Regulatory requirements often deem it compulsory to create and organise content. Anything that a company markets is now well documented, and various content functions, such as content marketing and technical publications, fulfil that requirement.

Yet, Earley writes, the fact remains that they still have no idea how to decide what to publish or how to structure it. “Most companies have never done a content inventory, and there is likely no Director of Content Experience who has any insight into which silos contain what content. Where does a company even begin?”

Of course, Earley helpfully offers eleven pointers for technical writers to get started:

  1. Understand and map out the customer lifecycle.
  2. Identify the points in the lifecycle where the customer needs to accomplish an objective.
  3. Deconstruct this objective into a finer-grained journey that illustrates the customer’s wants, needs, thoughts, emotional state, and tasks along with the content and information the customer requires to get to the next step to achieve their objective.
  4. Identify the sources of content and data and how they will be accessed.
  5. Determine the best channel to that content.
  6. Evaluate the state of the content and restructure it to answer specific, common, high-value questions.
  7. Map out possible customer questions at each step and structure dialogue to prompt the correct question.
  8. Test on actual customers.
  9. Use human-bot hybrid learning to train the bot.
  10. Provide points of human escalation.
  11. Measure, manage, govern, and improve.

As technology gets more and more immersive, the modern-day content writer has a preeminent role to play in making the user find sense in the virtual world. It is going to be a coveted job for talents with diverse educational backgrounds and a healthy interest in logic and technology.

Earley sums it up succinctly in his article: “Amidst the appeal of new technology, technical writers serve a vital role in development of AI applications, including chatbots, by being the subject experts most equipped to address the content requirements of chatbots. … … These skill sets are going to be in greater demand today than they ever have been and will continue to be as these technologies evolve. … These individuals, whose significance is often obscured by the latest technology, are important now and will be even more so in the future.”


Acknowledgement : Intercom, the magazine of the Society for Technical Communication

© 2024 Praxis. All rights reserved. | Privacy Policy
   Contact Us