Privacy Policy

Edward is an AI software development platform. Pragnya Works is the legal operator responsible for the data described in this policy. Wherever this policy says “we”, it means Pragnya Works. “Edward” and “the service” mean the product at https://edwardd.app.

You provide this information when you sign in and use the service:

• Account details from GitHub sign-in, including your name, email address, avatar, and GitHub account identifier
• OAuth tokens for the GitHub repositories you connect, and the repository and file metadata we read to sync your projects
• Your prompts, the responses we generate, and the resulting code and project files
• Images and documents you attach to a message, including any file names, file types, and the file contents we can read
• Your model provider selection and preferred model, for example Anthropic Claude, OpenAI, or Gemini
• Your provider API key, stored encrypted as described under API keys
• Build, run, and sandbox activity for your projects, including commands executed, command output, container logs, build status, and preview addresses
• Technical and security logs such as IP address, user agent, request timestamps, and error reports

Edward uses your own key rather than keys we hold on your behalf. When you save a provider API key we encrypt it with AES-256-GCM before it is written to our database. The decryption key lives in our server environment and never reaches the browser.

We decrypt your key in memory only to call the provider you selected. Because our servers hold that key, the connection is encrypted at rest and in transit, but it is not end-to-end encrypted and we can read it.

We store and process information using the following services:

• PostgreSQL for accounts, sessions, chats, and run records
• Redis for background job queues and short-lived rate limiting state
• Amazon S3 and CloudFront for sandbox workspaces, builds, and preview assets
• Docker containers on our own infrastructure to run your projects while you work on them
• GitHub, for sign-in and for repositories you connect
• Cloudflare, for email delivery on the edwardd.app domain and traffic handling
• Sentry, for error reporting, which may include request context and stack traces

When you run a generation, the prompt content for that request is sent to the model provider you selected, which is Anthropic, OpenAI, or Google. Your API key authorizes that request. Each provider handles what it receives under its own privacy policy and terms.

Edward sends prompts to providers only when you ask it to do work. We do not use your prompts to train models, and we do not sell your content.

• To run the service: sign-in, chats, sandboxes, builds, and previews
• To keep your projects working and to resume them when you return
• To sync projects with the GitHub repositories you authorize
• To enforce daily usage limits, protect against abuse, and keep the service available
• To diagnose errors and investigate security incidents
• To respond to your support requests

We do not sell your personal information. We do not run advertising or cross-site tracking. Edward does not use Google Analytics or any other advertising analytics product.

We share information with the service providers listed above, and in two other cases: when we are legally required to disclose it, and when we are part of a business transfer such as a merger or sale of assets.

Your prompts and generated code are not shared with anyone beyond the model provider handling the request.

Account data, chats, prompts, generated files, and run records are kept for as long as your account exists. Deleting your account removes them. Sandbox containers and their contents are deleted when a project is closed or abandoned, and logs are rotated out on a short retention cycle.

Traffic is served over HTTPS. Provider API keys are encrypted at rest with AES-256-GCM. Sandboxes run as isolated containers with CPU and memory limits rather than sharing a filesystem with the host.

No system is perfectly secure. If a breach affects your information we will tell you and describe what we changed.

You can delete your account and its data from within the app. You can also ask us to export or delete your information by writing to the address at the end of this policy.

Depending on where you live you may have rights to access, correct, export, or delete your personal information, or to object to certain processing. We will honour those requests. We do not sell personal information, so we do not treat “sale” opt-out requests as applicable.

Edward is a developer tool and is not intended for anyone under 16. We do not knowingly collect information from children. If you believe a child has given us personal information, write to us and we will delete it.

Our infrastructure and our service providers process data outside your country of residence, including in India and the United States. Some providers offer their own transfer safeguards.

When this policy changes we update the date at the top of the page. If a change materially affects your data we will tell you before it takes effect.

Edward questions, privacy requests, and support all go to:

• Legal operator: Pragnya Works
• Email: shubho@edwardd.app
• Website: https://edwardd.app