fibtec-docugen Privacy Policy

Last updated: 12 November 2026

fibtec-docugen (“Document Generator”) is a product of Fibtec Limited, a company registered in England and Wales under company number 07098379, with registered office at 71-75 Shelton Street, Covent Garden, London, WC2H 9JQ (“Fibtec”, “we”, “us”).

This policy explains what personal data fibtec-docugen collects, why, and what your rights are. It covers the web application, the API, the docugen command-line client and Python SDK, and the Claude Code plugin that drives that client. It deals with two kinds of data. Account data (who you are, your organisation, your keys, your payments): Fibtec is the data controller for it. Repository content (the code and files you give the service to document, and the documentation made from them): it is yours, and we handle it on your instructions to provide the service.

1. What the service does with your repository — and what it keeps

You give fibtec-docugen a repository as an archive (a zip file). The service unpacks it with strict safety limits, redacts secrets it recognises (§3), and starts a documentation session: an AI model reads the files and writes documentation (Markdown and diagrams), and if you ask for it, PDFs. Programs of ours then check everything that was written, and you download the result.

This is not a “nothing is kept” service, and we do not say it is. A documentation session takes minutes, so your repository and the documentation made from it are stored for a time. Exactly:

• The archive you upload, and the working copy made from it, are deleted when the session ends, and are in any case removed automatically within 2 days.
• The documentation we deliver is kept so that you can download it, and is removed automatically within 8 days. You can delete it sooner at any time (§7).
• Records without content remain for longer (§7): that a session happened and how it ended, counts, and what was charged.

Document Generator does not build, install or run your code. The model may read your files and write documentation. The only programs it is allowed to start are the diagram renderers (Mermaid and PlantUML, which draw the diagrams the model wrote), our own tools that read and check the files, and, after the model has finished, the program that prints PDFs from the documentation. The session runs in a container that is created for that session and discarded afterwards. If we add a feature that runs your code, we will describe it here before it is switched on.

During the pilot, sessions can be run only by organisations we have invited. You can create an account, look at the prices and, once we sell credit, buy it; you cannot start a session until your organisation is enabled.

2. Personal data we collect about your account

If you create a fibtec-docugen account, we collect:

• Your email address — used as your login identity and to determine which organisation you belong to (organisations are matched by company email domain; signing up with an email and password does not accept free or consumer email providers, while signing in with Google accepts any Google account and gives a personal address an organisation of its own).
• Authentication data held by our identity provider (a securely hashed password, and an optional two-factor authentication secret if you enable it) — this is held by our authentication infrastructure, not duplicated in our own application database.
• API keys, if you create any. A key is shown to you once; we store only a one-way hash of its secret, never the secret itself, together with its identifier, the label you gave it, its scopes and expiry date, the account that created it (and the one that revoked it, if it was revoked), and when it was created and last used. Revoking a key does not delete this record: it stays as an audit trail for your organisation.
• A record of each session you start — see §7. By default a session is visible to the person who started it and to your organisation’s Owners, not to every member of the organisation. Credit is shared by the organisation.
• Billing and usage information, if your organisation makes a payment or uses the product — see §5 and §7.

We do not collect your name, phone number, or physical address at any point in sign-up or account management.

3. The repository you process through fibtec-docugen

A repository can contain things you did not mean to share: personal data in comments, test data and fixtures; customers’ or colleagues’ names; credentials; code that belongs to someone else. Whatever is in the archive you upload is read by the AI model (§4). You are responsible for making sure you have the right to give us what you upload, including the right to have it processed by a third-party AI provider, and for not uploading repositories that contain live credentials.

Secret redaction is a safeguard, not a guarantee. Before the model sees your files we search them for things that look like secrets (keys, tokens, private-key blocks, and the like) and replace them. That search recognises patterns; it will miss some secrets and will occasionally replace something that is not one. If a repository has ever held a live credential, treat it as exposed and rotate it, whatever this service did.

When you use the plugin, it builds the archive from the files Git knows about (tracked files, and untracked files that are not ignored), leaves out Git’s own data, dependency folders and files whose names look like secrets, and asks you before it uploads and again before it spends credit. You can run the same step yourself with the client’s preview command to see exactly what would be sent.

3.1 Using the command-line client, the SDK or the Claude Code plugin

The docugen command-line client, the Python SDK and the Claude Code plugin call the same API as the web application, with an API key (§2). They send the same things: the archive you give them and the options you choose. The client sends no telemetry or usage data of its own. When you use the plugin from Claude Code, what you type to Claude and what Claude shows you is a conversation between you and Anthropic, under Anthropic’s own terms and privacy policy; fibtec-docugen sees only the resulting API calls, exactly as if you had made them yourself with the command-line client.

4. AI processing — what we share with our AI provider

To write the documentation, fibtec-docugen sends the content of your repository (after redaction), and what the model writes while it works, to Anthropic, the company that provides the Claude AI models we use. We do not control Anthropic’s own data practices for these calls — see Anthropic’s privacy policy for detail.

Before anything is delivered, everything the session produced is checked by programs of ours, not by an AI: they refuse files that should not be there, active content, unsafe links and results outside the size limits, and they check the PDFs again. If the model reaches its time, cost or size limit, you receive what was completed and are told it is incomplete.

5. Payment data

If your organisation purchases credit, payment is handled entirely by Stripe, our payment processor. We never see or store your card number, expiry date, or security code — Stripe’s own hosted checkout collects this directly. We only ever store the amount charged, the resulting credit balance, the charges and refunds made for sessions, and a reference to the transaction, so we can show your organisation its own billing history.

6. Cookies and tracking

fibtec-docugen does not use cookies, and we do not run any analytics or tracking software — no Google Analytics, no advertising pixels, nothing of that kind. Where we use browser storage at all, it’s limited to what’s strictly necessary to sign you in and keep you signed in: your sign-in tokens, a note of how you signed in so that signing out ends the right session, and, for the few minutes a sign-in with Google takes, a one-time code that your browser keeps in that tab only and deletes when the sign-in finishes. We never use browser storage for tracking, profiling, or advertising.

7. How long we keep data, and your rights

Your repository and its documentation. As set out in §1: the uploaded archive and the working copy within 2 days at the latest (and at the end of the session); the delivered documentation within 8 days, or at once when you delete it from the session’s page, with the client or through the API. Deleting a session before it has started cancels it. We keep no copy of either once those periods have passed, and we do not keep earlier versions of deleted files.

Session records. For every session we keep one record with no repository content in it: a session identifier and timestamps; your organisation and the account that started it; whether it was uploaded, started, delivered, delivered incomplete or failed (and, for a failure, one fixed reason word); the PDF option chosen; the number of documents and PDFs delivered and their size in bytes; the price quoted and the amount charged or refunded; and when the delivered result expires. It holds no repository name, no file name and no archive name. We keep it for 30 days after the result expires, and keep the records of payments and charges for as long as the law requires us to keep financial records.

Deletion receipts. When a session’s data is deleted we write a receipt that holds the identifiers, how the session ended, when its data was deleted and how many objects were deleted. It holds no content, and it expires after about 8 days.

Account data. We retain account and organisation metadata (your email, role, API-key records and billing/usage history) for as long as your organisation’s account exists — we do not currently offer a self-service account-deletion option through the product itself. If you want your organisation’s account data deleted, contact us at info@fibtec.co.uk and we will action the request. You can revoke your organisation’s API keys yourself at any time from the API keys page (§2).

Logs. Our service logs are limited, in code, to a fixed set of operational fields (session identifier, organisation, status, counts, sizes, timings, and, for an API key, its identifier and whether the call was allowed). They never contain your repository, file names, documentation or email address. Our service logs (the session pipeline, the API and the sign-in functions) are kept for 7 days and then deleted automatically.

Backups. The bucket that holds your repository and documentation is not versioned and keeps no backup: a deleted file is deleted. Our database keeps point-in-time backups, so when we delete a record at your request, a copy can remain in those backups for up to 35 days.

Under UK GDPR you have the right to access, correct, or request erasure of your personal data, to object to or restrict our processing of it, and to data portability; the same email address is the way to exercise any of these rights, and if you’re not satisfied with our response you have the right to complain to the UK Information Commissioner’s Office (ico.org.uk). For personal data inside a repository you gave us, ask your own organisation first: it decides what it uploads, and we can delete a session on request.

8. Where your data is hosted, and who else sees it

fibtec-docugen’s own infrastructure runs entirely in Amazon Web Services’ Ireland (eu-west-1) region — your data does not leave the EU/UK by virtue of our own hosting. (The portal’s static pages are served through Amazon CloudFront’s global network, which holds no account data and no repository content.) Where we use other companies to help run the service (our “sub-processors”), here’s the full list and what each one sees:

This version does not connect to GitHub or to any other code host: you give us an archive.

9. Changes to this policy

We may update this policy from time to time, and for material changes, we’ll make reasonable efforts to notify account holders directly.

10. Contact us

Privacy rights and data requests: info@fibtec.co.uk

Fibtec Limited
71-75 Shelton Street, Covent Garden, London, WC2H 9JQ