Privacy Policy

In plain language:

• We collect the account details you sign up with, the questions you ask, and the geographic areas you draw.
• To answer your questions we send your prompts and drawn areas to AI model providers, and we query satellite-imagery services for the location you are interested in.
• We use cloud compute, storage, database, hosting, and monitoring providers to run the service. These are listed individually below.
• We do not sell your personal data. You can ask us to access or delete your data at [email protected].

We collect the following categories of data:

• Account data. Your name, email address, and authentication identifiers. If you sign in with Google or GitHub, we receive a basic profile and email from that provider; if you register with a password, we store only a securely hashed version of it.
• Content you provide. The questions and prompts you type, the geographic regions of interest you draw (as polygons — these can reveal the location you care about), your chat history, projects, and any files or parameters you submit for analysis.
• Generated results. The analyses, measurements, maps, and other Outputs produced for you, along with references to the imagery and processing tasks used to create them.
• Usage and technical data. Log data, approximate request metadata, device and browser information, IP address, and diagnostic and performance telemetry collected to keep the service reliable and secure.
• Cookies. A session cookie is used to keep you signed in. We do not use the cookie for advertising.

We use the data above to:

• provide the Service — authenticate you, run your requested analyses, and return and store your results;
• operate, secure, debug, and improve the Service;
• communicate with you about your account and support requests;
• comply with legal obligations and enforce our Terms.

To deliver the Service we share data with the processors below. Each entry states what kind of data goes to that processor and why. We share only what is needed for that purpose, and we do not sell your personal data. Formal data-processing agreements and the exact processing locations for each provider are [to be finalised].

• AI model providers (via the Vercel AI Gateway, and OpenRouter) — generate AI answers

  Your prompts, relevant chat context, and a description of the area you drew are sent to large-language-model providers routed through the Vercel AI Gateway (and, where configured, OpenRouter) so the model can generate a response. The underlying model providers may include Anthropic, OpenAI, and Google. Providers process this input to return the answer and under their own terms may retain it transiently for abuse monitoring.

• Satellite imagery and catalogue services (Copernicus Data Space Ecosystem / CDSE, Sentinel Hub, and Microsoft Planetary Computer) — fetch imagery for your area

  The geographic area you draw and the parameters of your request are sent to these imagery catalogues and APIs so we can find and retrieve satellite data covering that location. Because the area you draw indicates where you are looking, this reveals your location of interest to these providers.

• Compute providers (RunPod and Modal) — run analysis models

  Imagery and derived data for your requested area are processed on these GPU and compute platforms to run models such as segmentation and feature extraction. They process this data to return results to us.

• Storage providers (Cloudflare R2 and Amazon Web Services S3) — store imagery and results

  Retrieved imagery, intermediate data, and the Outputs generated for you are stored in object storage so they can be served back to you and reused.

• Database provider (Neon — managed PostgreSQL) — store account and app data

  Your account data, chats, projects, and task metadata are stored in our managed PostgreSQL database. This database is currently hosted in the United States; a move to the European Union is planned.

• Hosting and infrastructure (DigitalOcean) — run the application

  Our application servers and background workers run on DigitalOcean, which processes data in transit as the Service operates.

• Observability and telemetry (Grafana, including Grafana Faro and log storage) — monitor reliability

  Performance, error, and diagnostic telemetry — including real-user-monitoring events from your browser and server logs — is sent to our Grafana-based monitoring stack. This telemetry may include identifiers and request metadata used to keep the Service healthy and to investigate problems.

The processors above operate in several countries, including the United States and the European Union, so your data may be transferred and processed outside your own country. Where required, such transfers rely on appropriate safeguards [transfer mechanism and safeguards — to be finalised]. As noted above, our primary database is currently in the United States with a planned move to the European Union.

We keep personal data for as long as your account is active and for as long as needed to provide the Service, then for [retention period — to be finalised] unless a longer period is required by law. Diagnostic logs and telemetry are kept for [log retention period — to be finalised]. Data sent to third-party processors is retained according to their own policies.

Where data-protection law such as the GDPR applies, we rely on the following legal bases: performance of our contract with you (to provide the Service), our legitimate interests (to secure, maintain, and improve the Service), your consent where required, and compliance with legal obligations. [The specific legal basis for each processing activity — to be confirmed with counsel.]

Depending on your location, you may have the right to access, correct, delete, export (data portability), or restrict processing of your personal data, to object to certain processing, and to withdraw consent. You also have the right to complain to a data protection authority.

A self-service account-deletion feature is being built. In the meantime, to exercise any of these rights — including access, deletion, or a portable export of your data — email us at [email protected] and we will action your request.

We use technical and organisational measures — including encrypted transport, access controls, and hashed credentials — to protect your data. No method of transmission or storage is completely secure, however, and we cannot guarantee absolute security.

The Service is not directed to children and is not intended for anyone under [minimum age — to be finalised]. We do not knowingly collect personal data from children. If you believe a child has provided us data, contact us and we will delete it.

We may update this Policy as the Service evolves — for example, when we add or change a sub-processor. When we make material changes we will update the date above and, where appropriate, provide additional notice.

For any question about this Policy or your personal data, contact us at [email protected].