How can we help?

You can search and read public patent records without an account. An account lets Patent Bear remember your work: saved patents, annotations, highlights, notes, claim charts, chats, analysis runs, usage, and plan state.

The Library is the research hub for your account. It brings together recent activity, saved patents, annotations, search history, claim charts, chats, analysis runs, plan state, and usage so you can resume work without reconstructing it from browser history.

Yes. You can highlight text, save claim terms, add notes, annotate figures, track occurrences, hide or restore markings, and keep research state attached to a patent. Signed-in users keep their annotations across sessions.

Yes. Patent Bear can split claims into elements, let you add notes beside each element, and export charts to Word for briefs, memos, or client reports. Claim chart limits may depend on your plan.

The Guides at patentbear.com/guides walk through search, the reader, claim charts, file history, Research, and connecting an AI agent, step by step.

On the sign-in page, choose the forgot password option and enter your email. We will send you a reset link. If you are already signed in, open Library, then Preferences, and choose Reset password.

Check your spam or quarantine folder first, and look for mail from patentbear.com. Law firm mail filters often hold automated messages, so your IT team may need to release it or allow the domain.

If it still does not arrive, send us a request using the address on your account.

You can sign in with Google, with your email and password, or through your organization's single sign-on if your firm has it set up.

Open Library, then Preferences, and choose Export your data. We will verify the account and email your export within one month.

Open Library, then Preferences, and choose Delete account. This opens a request so we can verify ownership and remove your account data safely. Deletion removes active application records, subject to the limited backup retention and operational requirements described in the Privacy Policy.

Patent Bear has Free, Plus, Pro, and Firm plans. The Pricing page has current prices and what each plan includes. Firm plans are arranged with our team through the Contact page.

Open Library, then Plan, and choose Manage billing. You can change your payment method there and open or download past invoices.

Open Library, then Plan, and use the Cancellation option. You can cancel at any time. Your plan stays active until the end of the period you have paid for and does not renew after that.

Credits: yes. If you buy a credit and are not happy with it, contact us within 14 days of purchase and we will refund it.

Subscriptions are not refunded for partial billing periods. If you were charged by mistake, send us a request and we will put it right.

Team seats are a way to pay for several Plus or Pro accounts on one bill. They are billing only: each person keeps a private account, and teammates do not see each other's work. You manage seats in Library, under Seats.

Research is where Patent Bear runs structured patent analyses: Prior Art, Forward Art, Charting, Disclosure, Clearance, Invention, and Citations. Each one combines search, ranking, claims, specifications, and citations into an output you can review and save, rather than a one-off chatbot answer.

One credit runs one analysis, on any plan, including Free. Purchased credits never expire. An analysis can run many searches, ranking passes, OCR or column-line jobs, and AI calls in a single workflow, and credits cover that compute and AI usage while giving you a predictable budget.

Analyses can take from a few minutes to about 20 minutes, and you can leave the page while one runs. You will find it under Research in your Library.

If it has clearly stalled or failed, send us a request with the link to the run so we can look at it.

No. A generic chatbot only has whatever you paste into it. Ursa works from patent text, claims, figures, prosecution history, family data, citations, search results, and analysis context already inside Patent Bear.

No. Ursa, Patent Chat, and the analyses in Research are research tools. They can miss references, misunderstand claim language, cite the wrong location, or produce incomplete analysis. Verify every citation, date, claim mapping, legal standard, and conclusion against the underlying documents and qualified counsel before relying on it.

Patent Bear is listed in Claude's connector directory and the ChatGPT plugin directory, and works in Gemini. The Connect page and the Connect your AI agent guide have step-by-step instructions for each one.

Use https://www.patentbear.com/mcp as the endpoint, with the Streamable HTTP type where your client asks for one. You will sign in with your Patent Bear account the first time you connect.

Connector requests are metered by plan each month. You can see your usage in Library, under Plan, and add more requests or change plans from there. The Pricing page lists the current options.

Patent Bear gets its raw data from public patent-office records, including USPTO sources, and hosts the data itself. We build our own searchable corpus of patents, publications, applications, file histories, assignments, family data, PTAB records, figures, OCR, citations, and generated research artifacts.

Because the corpus is inside the product, it connects directly to the reader, search, citations, annotations, claim charts, Ursa, and Research.

Patent Bear supports searching patents, pre-grant publications, patent applications, and related technical sources. When you find a record, you can read it, cite it, chart it, ask questions about it, inspect its file history, and run analysis over it.

Basic patent, publication, and application lookup is designed to be free. Some saved workspace features, AI chat, claim charts, and Research analyses may require an account or paid plan because they use storage, compute, and AI budget.

Official patent PDFs remain patent-office records, and PDF downloads may link to or come from the original source where available. Patent Bear hosts the layer professionals work with: structured text, claims, figures, OCR, column-line artifacts, search indexes, citations, and generated research files.

Patent Bear is designed to stay current with public patent-source data. Source systems can still lag or change, so check official records for legal deadlines, ownership, and status.

No. Official portals remain the legal source of truth for filings, deadlines, and status. Patent Bear is built for doing the work after you find the record.

Send us a request with the patent or application number and the page where you saw the problem, so we can reproduce it quickly. Design patents are not currently covered, so a missing design patent number is expected.

No. Patent Bear does not use your prompts, chats, annotations, saved patents, analysis inputs, analysis outputs, invention descriptions, product descriptions, or work product to train AI models.

When AI providers process API requests for Patent Bear, their current API terms state that API inputs and outputs are not used to train models unless the customer opts in. Patent Bear does not opt in.

Beyond that, every AI call Patent Bear makes runs under Zero Data Retention: OpenAI and DeepInfra do not log or keep your prompts or results after answering the request.

For AI chat and analyses, we may send the patent text, selected claims, pasted invention or product descriptions, generated elements, search queries, evidence snippets, and your instructions as needed to provide the requested analysis, both to the model that writes the response and to the reranker that ranks which patent passages are most relevant to your question. Billing details, passwords, and account credentials are not sent to our AI providers.

The Patent Bear web application is hosted on Vercel. Account data and application data live in Supabase. Patent figure images and related generated files are stored in Cloudflare R2 and served through Cloudflare.

Some worker services for analyses, OCR, column-line generation, search, and ranking run on Patent Bear's own private, single-tenant Hetzner-hosted infrastructure, not a shared multi-tenant pool.

Account data, saved patents, annotations, highlights, notes, search history, chats, analysis runs, and durable outputs are stored in Patent Bear's database and object storage systems. Worker services are designed as transient compute, not durable storage for user work product.

Yes. Patent Bear uses HTTPS for data in transit. User data is stored with encrypted infrastructure. The Security page describes provider controls, encryption, authentication, worker processing, and access-control practices in more detail.

No. Patent Bear does not sell your data to advertisers or data brokers. We do not use advertising pixels or cross-site tracking scripts.

They are private to your account. Administrative access is limited to operational need, debugging, reliability, billing, abuse prevention, and security response.