Research
Research from Good Guy Apps on context provision, memory and coordination for teams of humans and AI coding agents, and the evidence behind Kanban Pro's agent-native design.
-
Toward an Agent-Native, Local-First Work Tracker
Don Kruger · Working paper v2 ·Abstract. Coding agents now claim, execute and hand over work, so the work tracker has become part of the agent's runtime. This working paper asks what data model and agent interface would make a local-first, file-based tracker the strongest option for teams of humans and coding agents, and how we would know. It scores six options on ten scenario-anchored quality attributes with swing weights and Monte Carlo sensitivity analysis, proposes an eight-pillar architecture built on six design principles, and states five falsifiable hypotheses with a local replay benchmark. Kanban Pro 1.2.0 implements the architecture.
Cite as: Kruger, D. (2026). Toward an agent-native, local-first work tracker: A design science evaluation of Kanban Pro against the LLM Wiki pattern and agent-native rivals (Working paper v2). Good Guy Apps. https://goodguyapps.com/research/agent-native-context-provision/
Read the summary →