Resources
Straight answers.
What NyayaDesk does and doesn’t do, the words we use for the litigation chain, and where to read further.
Frequently asked
Is NyayaDesk a legal chatbot?
No. It is a matter-centred litigation workspace. Legal AI is one way to work with the record; evidence, strategy, drafts, hearings, compliance and audit are structured parts of the product.
Does AI approve or file documents?
No. AI prepares and checks. Officers confirm facts, the Government Pleader approves, the deponent executes the affidavit and counsel files through the court registry. The software records those acts.
Does an independent check guarantee a correct answer?
No. A separate model family checks the work, but model agreement is not legal truth. Source review, unresolved findings and human accountability still matter.
Can a new user create a workspace immediately?
No. Workspaces are provisioned through authorised onboarding. A person must already be a member to sign in; single sign-on does not create membership.
Does AI processing stay in India?
No. Model calls currently run outside India. Most use a zero-data-retention route; Gemini and GPT calls go directly to Google and OpenAI under their API terms. Embeddings use a separate self-hosted model. Confirm hosting and processing for your deployment before onboarding.
Which languages are supported?
The interface, AI answers, fact-confirmation questions and drafts are in English. Documents in English and Telugu can be read. A Telugu interface is deferred.
Are court integrations automatically available?
No. Availability depends on the source, adapter configuration and access. Manual entry remains important, and CAPTCHA-protected court systems are not scraped.
Does it cover contracts and other legal work?
Yes. Contracts, instruments and paralegal work (notice replies, trade mark clearance and patent review) sit beside litigation. Signing through NyayaDesk is not available; signed-copy verification is not an e-signing service.
Glossary
The words used across this site and the product.
Product guides
Reading departmental records and building the chronology.
How officers answer questions about their own record.
From confirmed facts to a checked counter affidavit.
Access, audit, retention and where models run.
Shared, dedicated database or dedicated stack.
Evaluation
No evaluation report is published yet. When one is, this page will carry the method, the question set and the results, including where the system fell short.
Ask about evaluation