AI coding assistants are easy to overhype. In practice, the interesting question is much narrower: where do agentic coding tools actually help when building and maintaining a real QGIS plugin?

This talk presents lessons from developing qfit, a QGIS plugin for importing, analysing, and publishing personal fitness activity data, using OpenClaw as an agentic coding environment. Rather than treating AI as a magic code generator, I will focus on practical workflows: breaking work into small reviewable changes, using agents to explore code, draft implementations, refactor modules, and strengthen tests, while keeping a human firmly responsible for architecture, validation, and release quality.

I will share what worked well, where the approach failed or created extra review burden, and which guardrails mattered most, especially around testing, CI, code review, and incremental design in a PyQGIS codebase. Attendees will leave with concrete patterns for using agentic coding in QGIS plugin development without lowering engineering standards.

This session is aimed at developers and technical QGIS users who are curious about AI-assisted plugin development but want concrete practices rather than hype.

Fitness activity data usually lives inside proprietary platforms, which makes it hard to analyse, combine with other spatial data, or publish in reusable map products. qfit is a QGIS plugin that brings that data back into an open GIS workflow.

In this talk, I will present qfit, a plugin that imports fitness activities from Strava into a local GeoPackage, turns them into analysis-ready QGIS layers, and supports a complete workflow from import to publication. The plugin covers three main use cases: importing and synchronising activities, visualising and filtering them in QGIS, and generating PDF atlas outputs with activity pages, summaries, and profile-ready metadata.

I will show how personal activity data can become a real geospatial dataset: styled, filtered, queried, combined with basemaps, and prepared for high quality print layouts. I will also share a few practical lessons from building the plugin, including handling detailed track geometry, temporal data, and atlas-oriented layer design.

This session is aimed at QGIS users and plugin developers interested in personal mobility, sports data, and new geospatial workflows built on open tools.