Ai pipeline produces up-to-date tech tutorials with audience feedback
An AI Factory for Technology Education: An Agentic Pipeline with Closed Loop Audience Feedback
Computers and Society
Summary
Technology tools change quickly, so instructions about them become outdated fast. The authors created a special system that treats making tutorials like a factory process with clear steps and checkpoints. It uses AI to draft content but also collects viewer feedback to improve future tutorials continuously. Over five months, this system produced many guides efficiently and found ways to keep people more engaged.
What this means in practice
- •For corporate training teams: Create and update professional skill tutorials rapidly, guided by real user engagement data to improve content relevance.
- •For online course developers: Develop technology courses that adapt quickly to tool changes, using automated feedback loops to refine instructional style.
Authors
Josue Hernandez, Hector R. Amado-Salvatierra, Rocael Hernandez Rizzardini
Abstract
Technology tools used for professional upskilling change on a timescale of weeks, and written guidance about them ages at the same pace. Large language models have made it inexpensive to draft a tutorial or a course outline, but most deployed generation systems still produce a piece of content once and never check it against what an audience actually does with it. This paper describes an agentic pipeline, organized as a typed workflow graph, that treats instructional content production as a manufacturing process with explicit checkpoints rather than a single generation call. Four node classes structure the graph: deterministic scripts, model steps bound to a fixed rubric, open-ended agent phases, and human approval gates, arranged along a forward production path and closed by a feedback cycle that rewrites generation rules from post level engagement telemetry. Production of content is split into two layers: a demand layer, built from video and community sources, that shapes topic selection and register, and an authority layer, built from official documentation, that every published claim must trace back to. Over five months of continuous operation, the deployed system published 26 documented guides at roughly 1.5 hours of operator time per week, and the feedback loop identified four measurable engagement effects that became binding rules for later runs, including a hook style that outperformed baseline by a factor of 1.83 in its first analysis window.