Gridspace
Insights

How we decide where a battery goes.

Every score Gridspace produces comes from an ontology — a structured theory of what makes a place work for storage. It is versioned, auditable, and open to argument. This is where we show it.

8 site types
23 scoring weights
v2.8 current model
4 hypotheses tested
—% validation rate (publishes at n ≥ 10)

Ontology Explorer

Browse the site types we screen for — what defines each one, why it works, what kills it, and how confident we are.

Explore the ontology →

Decision Log

Every change to the scoring model, dated, explained, and attributed. What we changed, what evidence moved us, who validated it.

Read the log →

Discovery Feed

The AI proposes site types and candidates. Humans confirm or reject. Both outcomes are published — including the misses.

See what we're testing →

Ontology Lab

Disagree with our weights? Fork the ontology, change them, and run it against the real map. Publish your version.

Open the Lab →

The current model

Model v2.8 · published 2026-06-14 · 312 parcels scored · calibrated against 19 operating installations
Grid Value Amplification
35%
Spatial Creativity & Fit
20%
Economic & Lifecycle Upside
20%
Social & Permitting Friction
15%
Pattern Similarity
10%

Why these weights? → The decision record that set them, including the recorded dissent.

Latest findings

Things we learned from running the ontology. Every finding has a number in it.

All findings →
Post-mortems

What actually kills a battery site — nine post-mortems

Six of nine failed on ownership fragmentation, not on grid or permitting.

Methodology

Inside the feasibility score, 0 to 100

Five categories, 23 weights, and the confidence rating that changes what a number means.

Ontology

Why we retired cemetery maintenance yards

Adequate on geometry and access; fails on social license in every district tested.

Get the decision log by email when the model changes.