Gary Ross
About
I'm the creator of Edzil.laSessions
Presentation Building AI workflows: A practical approach for language teachers more
Many language teaching tasks work better through structured AI workflows that coordinate multiple tools rather than relying on a single AI tool. For example, generating realistic multi-character conversations, providing scaffolded feedback that adapts to student responses, or managing feedback across many students often requires a sequence of coordinated AI actions. A typical workflow might allow students to record a spoken dialogue, have the audio automatically transcribed, receive targeted feedback on vocabulary, grammar, and fluency, and then obtain an overall evaluation or grade. This practice-oriented session presents how teachers can build such workflows using AI tools to complete multi-step pedagogical tasks. Co-presented by a language teacher with no programming background and an app developer, the session presents classroom-tested examples including generating multi-character dialogues, building personalised feedback cycles for student writing, and managing scalable homework correction. Participants will see how chaining instructions allows teachers to guide AI behaviour more reliably than relying on a single tool. The session also demonstrates how local tools can be combined with online services to improve privacy and reduce platform lock-in. Participants will leave with practical examples and a simple framework they can adapt to their own teaching contexts.
Workshop Extensive Reading texts generated by AI: What Learner Behaviour Reveals more
An AI-driven system has generated over 600 stories, adaptively levelled to reader proficiency for extensive reading, initially targeting first-year university students. Linguistic complexity is adjusted at the point of generation rather than selected from a fixed corpus, allowing us to compare predicted difficulty with actual student reading behaviour. The system collects fine-grained, page-level interaction data alongside learner comments and ratings, including time on each page, stop points, and total completion. Data from over 20,000 reading sessions are analysed using behavioural features such as completion rate, speed consistency, and re-reading frequency. Using these indicators, this study examines which linguistic or narrative features of stories sustain reading, as well as specific sections that delay, disrupt, or deter progress. Elevated reading speeds suggest superficial interaction, while reduced reading speeds may indicate increased cognitive load, but there are various intrinsic or extrinsic reasons why reading speed may change, from getting a coffee to not actually reading. Completion at a stable pace indicates their reading is comprehensible and compelling. Sentiment analysis of learner comments identifies patterns associated with successful and problematic texts. These findings are examined against intended text levels, with particular attention to performance at the lower and upper ends of the proficiency range.
