Case Study

A conversational learning experience

tl;dr

I defined and designed a learning experience aimed at introducing its users to AI and teach them about its capabilities and how they could apply them in their day-to-day work. I defined requirements in collaboration with a product manager based on user experience principles related specifically to conversational interactions and designed various concepts including flows and interaction mechanisms to support learning goals. My product partner and I worked with a group of talented software engineers to develop an internal facing live proof of concept for testing.

Below are the key screens and deliverables from this case study, organized to show the UI decisions, interaction patterns, and how the experience works end to end..

Video demo of the conversational learning experience prototype where user navigates instructions and interact with the AI-powered chatBot.

I’ll start by showing you the concepts I came up with

My first design concept for this learning experience involved learning from and with the AI-powered chatbot directly.

The idea was for learners to interact conversationally with the AI as it guides them through various use cases through narrative-led scenarios while delivering explanations and clarifications via meta-commentary.

The AI introduced itself, established expectations, and guided learners into their first exercise using a familiar chat interface designed to feel approachable and intuitive.

The following screen shows the bot responding to an off-topic question; We ensure that it does not respond to or act on requests that are not aligned with the main objective of the learning experience.

This is meant to reinforce the experience’s educational purpose and ensure learners follow and progress through our predetermined conversation flow.

The AI was intentionally scoped as a learning coach rather than a general-purpose assistant, keeping learners focused on the lesson while clearly explaining why off-topic requests couldn’t be fulfilled.

Annotated screen describes the rational behind where and how UI elements are placed; **The main content is vertically aligned centered on screen and has plenty of open space to anchor user’s attention** on the chat elements.

Teaching prompt engineering through examples, helping learners understand how adding context and specificity leads to more useful AI-generated responses.

The bot characterizes its own responses, provides explanations and describes ways to phrase (or rephrase) instructions to modify and adjust its output.

In this concept, the AI is both the tool and the instructor. It responds to the messages and provides useful tips to help learners understand how their messages influence its output.

The experience explains why the AI responded differently, helping learners understand how context, constraints, and follow-up prompts influence AI-generated outputs.

The second concept explored a group chat-style learning experience involving the learner, an AI-powered coach and the course author.

The session begins with the AI coach and the author introducing themselves, explaining their respective roles, and setting clear expectations for how they will support the learner throughout the experience.

UI state showing the bot processing input; input processing is denoted with 3 dots alternating their opacity over time.

Suggested prompts have a star symbol to denote when the AI will respond or when a message will be interpreted by the AI itself.

More stakeholders responded positively and favorably to this concept and any other concept where an author or a guide was explicitly represented. Stakeholders seemed to resonate better with the method of instruction delivery implied by this concept.

Clear visual and conversational cues signaled the transition from guided instruction to direct interaction with the AI, helping learners understand when they were practicing independently.

The third concept explored a more traditional learning experience, where the course author guided learners from outside the chat interface while the AI functioned as a supporting tool.

Unlike the previous concept, where both the author and AI participated within the conversation, this approach positioned the AI as an on-demand assistant that responded only when prompted by the learner. The author’s guidance was delivered through the surrounding interface, providing instructional context before learners engaged with the AI.

I developed this concept in response to stakeholder feedback regarding the perceived ambiguity of the relationship between the author and the AI coach in the previous design. Stakeholders also wanted learners to have clear moments of pause and reflection between activities—”inflection points” that encouraged them to absorb the material before applying it in practice. Separating the instructional guidance from the conversational experience created a more structured learning flow while preserving the AI’s role as an interactive practice tool.

Author led guided conversation; There’s a persistent author persona which delivers instructions for learners to follow from outside the chat interface.

Stakeholders ultimately preferred this concept over the others, largely due to its split-view layout. Its familiar structure helped distinguish instructional guidance from AI interaction, making the experience feel more intuitive and easier to navigate.

Why do I keep mentioning Stakeholders?

My preferred approach when developing design concepts is to test them directly with its target users. However, in the organizational and cultural environment context of this project, early concept evaluation was primarily driven by stakeholder feedback and alignment.

As a result, concepts needed to resonate with stakeholder expectations as well as satisfy product requirements. For example, stakeholders consistently favoured split-view layouts and information-dense interfaces, believing that users felt more confident and could work more efficiently when presented with a greater amount of information on screen. These preferences influenced the direction of the concept that was ultimately selected for further development.

It was challenging to overcome especially as this organization had more of a top-down decision making framework. While I’ve always advocated for user-centric design methods, stakeholders support and buy-in for those approaches weren’t always forthcoming.

Skeleton placeholder works as the feedback mechanisms to communicate to learners when the AI is actively processing information.

Users follow guided instructions in a linear sequence; Dialog options are represented as clickable tiles with a dashed outline.

A disabled text input field shows a message when learners hover over it, the message states that they must complete the walkthrough before they can begin writing their own prompts.

The intention behind this is to ensure that all learners review the instructional guidance that we’ll prepare to equip them with a foundational understanding of Generative AI and its concepts.

Users must complete an introductory exercise to enable open ended interaction with the AI. Hovering the disabled input field triggers an inline message conveying this prerequisite.

When a learner has completed the introductory exercises they are able to experiment with writing their own prompts.

…and now, to give you some context

The following tells the story of project itself, the historical context behind it and how I collaborated with my product counter-parts to define, design and deliver a product experience aligned with business objectives.

It also highlights the specific design decisions I made to support the desired learning outcomes and high-level product goals.

The project epic details as captured in Jira — the project management tool where I tracked all design activities relevant to this work.

I’ve organized the following artifacts and described my overall design process to showcase my analytical thinking, critical thinking and problem solving skills. If you’d like to understand how I make decisions, this is for you 😄

This was a stakeholder-initiated project; Our goal was to develop a product to meet the needs of enterprises looking to up-skill their workforce on GenAI.

Exec stakeholders across marketing and sales’ were looking to offer a solution to enterprise customers who wanted to equip their employees with foundational AI knowledge and practical skills.

The target audience comprised non-technical professionals across a wide range of business functions, including HR, Legal, Finance, Operations, Marketing, Manufacturing, Customer Service, Project Management, Design, Administration, and executive leadership.

I relied on stakeholder context, domain knowledge, and informed assumptions to develop an initial understanding of the target audience. The following artifact outlines the user characteristics and motivations that informed the early product and design decisions.

Proto-Persona (Analytical Ana) The following describes the presumed behavioral and attitudinal characteristics of the target audience for this learning experience based on anecdotal evidence and domain exposure.

These were educated assumptions and not validated empirical data and also not what I’d typically reference when making design decisions.

Why a conversational learning experience? Because it reflects the real world use of GenAI tools like ChatGPT, Gemini.

Instructional design research shows that an effective learning experience is one that is engaging, relevant to the learner, interactive, provides opportunities for application and promotes active participation.

I believed that a learning experience which mimics the real world interaction users have with GenAI tools (like ChatGPT) would make for a compelling learning experience and it would enable users to build accurate mental models which I believed they could draw from when putting their knowledge into practice—in short it is:

Accessible and a practical way of learning; a chat-based, conversational format would encourage active engagement, which I believed would help learners better retain the concepts.
Personalized and represents its real-world usage context: one of my concepts involved using a chatbot to teach about GenAI which would provide a practical, hands-on experience that mirrors real-world interactions learners would have with AI tools, plus, a conversational approach allows for adaptive feedback which makes for a personalized learning experience.

Defining requirements for a chat-based AI-powered conversational learning experience

To identify requirements for conversational interaction, I held a design exercise (a live workshop) with my Miranda Mota (my product partner) where we collaboratively mapped out the desired conversational flow between an artificially intelligent chatbot (the system) and learners.

Together we devised the supporting system behaviors that would create the desired user experience and support our users’ goals.

Using asynchronous collaboration to capture requirements, challenge assumptions, and make informed product decisions around the chatbot’s conversational capabilities and release scope.

On conversational design

I learned about the conversational design exercise from Strategic UX writing by Torrey Podmajersky and although this was our first-time defining and designing for a conversational learning experience, we successfully identified relevant requirements which we analyzed to capture dependencies and implications.

As part of the exercise we each took turns assuming the role of learners and the system, then alternated while enacting various scenarios to identify and capture key considerations and experience requirements.

Defining tasks, usage and context scenarios

I defined user and bot conversation flows to support a continuous learning feedback loop. The learning experience was developed iteratively, with concepts continuously refined as new dependencies, user flows, and data requirements emerged throughout the design process.

I prefer to visualize concepts with stakeholders when discussing requirements for complex systems and that typically takes the form of live sketches on a whiteboard like this example.

The conversation flow was mapped visually as a diagram which captured relevant considerations for learner:bot interaction. The following image shows a snapshot of the high-level flow, which my product partner and I closely examined to determine key requirements.

Visualizing the end-to-end conversational workflow, including prompt submission, AI evaluation, feedback, and iterative revision to reinforce learning through practice.

The learning experience was successfully launched and is now actively used by learners as part of O’Reilly’s AI learning offerings.

Following several rounds of stakeholder feedback and iterative refinement, the experience evolved from an MVP concept into a production-ready learning solution.

Throughout development, I partnered closely with Product and Engineering to clarify requirements, refine the interaction model, and provide supporting design deliverables to ensure the experience aligned with both learner needs and technical constraints.

The final product became a key component of O’Reilly’s AI learning strategy, providing non-technical professionals with an interactive, conversational way to build practical generative AI skills through guided practice and iterative feedback 👍

Next Case