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.