Data, product & AI systems
Shawn Ganz.
Civic data products
& AI working systems.
Shawn designs civic data products and AI working systems. At NYC Parks, he presented a model for identifying tree-planting opportunities. In Corpus, he works with AI agents to design how work is reviewed and continued across sessions.
The common thread is system design: understand the real decision, bring the right information together, and build a process people can inspect and improve.
Selected work
Two settings.
One design practice.
Corpus
Give agent work
a life beyond the session.
- Contribution
- Shawn originated the project and shaped its product choices. Agents co-designed, built, investigated, and reviewed.
- Observed result
- Continuing obligations survived handoffs; review caught an omission before work was judged complete.
Civic data
Connect analysis
to a city’s decisions.
- Contribution
- At NYC Parks, Shawn takes data requests from idea through implementation and checks their use and effects on related processes.
- Public result
- A model presented at NYC Open Data Week and a contribution acknowledged in The Nature Conservancy’s practical canopy release.
What carries across
From domain knowledge
to system design.
A portfolio reading of the two bodies of work.
| Practice | Civic data | AI collaboration |
|---|---|---|
| Problem framing | Turn a city planning question into a decision model. | Turn an agent failure into bounded, judgeable work. |
| Data & source integration | Combine spatial datasets while preserving the meaning of each input. | Connect work records, source state, and reviews through a recoverable trail. |
| System boundaries | Keep data inputs, assumptions, and use distinct. | Separate current state, obligations, making, and review. |
| Operational design | Connect spatial analysis to the people using it. | Design handoffs and continuation around actual working conditions. |
| Evidence & iteration | Make the model’s basis and limits legible. | Measure friction, inspect candidates, and preserve corrections. |
Looking toward AI development
Bring the work
into the conversation.
Shawn wants to bring this practice into AI development: framing useful problems, designing the working environment, and testing whether the structure earns its cost.
Start with a concrete question: what should an agent leave behind so someone else can judge and continue its work?