video1.0<iframe src="https://www.loom.com/embed/856bebba84cb445db263f78e0e5065ef" frameborder="0" width="960" height="720" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>720960Loomhttps://www.loom.com720960https://cdn.loom.com/sessions/thumbnails/856bebba84cb445db263f78e0e5065ef-22a179e2a91bf61e.gif281.0808A Flask backend that classifies whether submitted text was AI-generated or human-written. It returns a calibrated confidence score and a plain-language transparency label, with an appeals path for creators who think a classification is wrong. - Multi-signal detection: an LLM-based semantic judgment (Groq/Llama 3.3 70B) combined with independent stylometric heuristics (sentence variance, punctuation density, connector-phrase usage), merged via log-odds combination. - Asymmetric confidence thresholds: deliberately harder to reach a confident "AI" verdict than a confident "human" one, since a false accusation is worse than a missed detection. - Appeals workflow, structured audit logging, rate limiting, and a small analytics dashboard. This walkthrough shows the detection pipeline live: a clearly-AI submission, a clearly-human one, and a genuinely human but formally-written one that the system correctly avoids misflagging, plus the appeals flow, audit log, analytics view, and rate limiting in action. For the full write-up and design rationale: see README.md and planning.md in the repo.