AI & data usage

Which AI do we use?

ResumeSync uses Claude, an AI language model developed by Anthropic PBC. We access Claude via Anthropic's commercial API. We do not run our own AI models and we do not use OpenAI, Google, or other AI providers for resume generation.

What data is sent to Claude?

When you generate a resume, the following is sent to the Claude API:

• The text content of your LinkedIn profile PDF (extracted from the file you upload).
• The job description you paste into the form.
• Your answers to the verification questions during the interview step.
• A structured system prompt that instructs Claude on how to write the resume.

We do not send your name, email address, IP address, or payment information to Claude. Your identity is not included in the AI prompt.

Is my data used to train AI models?

No. Anthropic's API terms of service state that data submitted via the API is not used to train their models by default. We have not opted into any data sharing arrangement with Anthropic beyond what is required to process API requests.

ResumeSync itself does not use your documents or generated resumes to train, fine-tune, or improve any AI system.

How long does Anthropic retain API data?

According to Anthropic's privacy policy, API inputs and outputs may be retained for a limited period for trust and safety monitoring, after which they are deleted. ResumeSync does not control Anthropic's own retention practices — we recommend reviewing their policy directly for current details.

How long do we retain your documents?

Session data (your LinkedIn PDF, job description, and interview answers) is stored temporarily on our servers to complete the generation process. It is deleted within 24 hours regardless of whether you create an account.

If you choose to save your generated resume to an account, the resume text is stored until you delete it. We never store the original documents beyond the 24-hour window.

Where is data processed geographically?

Claude API requests are processed by Anthropic's infrastructure, which operates primarily in the United States. Data transfers from the EU to Anthropic are covered by Standard Contractual Clauses (SCCs) in accordance with GDPR Article 46.

Our own database (Neon PostgreSQL) runs in eu-central-1 (Frankfurt) — your account and resume data never leaves the EU.

Can I see what prompt is sent to Claude?

We don't publish the exact system prompt (it's our core product), but we are transparent about what it instructs Claude to do:

• Cross-reference your experience against the job requirements.
• Only include skills and experience you have explicitly confirmed during the interview.
• Never invent, fabricate, or infer experience without confirmation.
• Format the output as a structured, ATS-compatible markdown resume.
• Include a QA summary noting any gaps or unverified requirements.

What AI cannot do in ResumeSync

• Access the internet, your LinkedIn account, or any external data source.
• Remember previous sessions — each resume generation is isolated.
• Access other users' data.
• Modify your account, make payments, or take any action beyond generating the resume text.

Human oversight

ResumeSync does not use AI for automated decision-making that produces legal or similarly significant effects on individuals. The resume is a document you review and choose whether to use. No application is submitted on your behalf without your action.

Questions about AI usage

If you have questions about how AI is used in the Service, email privacy@resumesync.io. We aim to be transparent and will update this page as our AI usage evolves.