D
Draft Bot Pro

Draft Bot Pro is an AI workspace for Indian lawyers, law students, legal teams and law firms, made by Rarelabs Private Limited, the maker of the Law Bot Pro legal app. It drafts Indian legal documents from typed facts or uploaded reference PDFs, with tone and clause changes in its own editor and Word or PDF downloads. It also reviews drafts with tracked changes and writes legal memos with headings, references and judgments.

Its research tools answer legal questions with an AI overview, cited provisions and landmark and similar judgments. A research panel lists cases for and against the user, arguments in the user's favor and a neutral judicial evaluation. More than 2.4 crore judgments and orders can be read in the product, and each cited judgment links to its source. Chat with PDF summarizes documents of up to 600 pages, answers questions and prepares lists of dates.

A free plan allows 500 AI words a day, and the Infinity plan costs ₹999 a month with near unlimited words under a fair usage policy. Draft Bot Pro says it never trains on user data and deletes uploaded files after seven days, while chat history is kept.

Capability grades

All 15 axes, graded from public sources on the date shown. Hover a grade to see what the letter means on that axis.

AA on AI CentralityThe artificial intelligence is the product. Remove the models and there is nothing left to sell.

AI Centrality

How much of the product is actually AI. Whether the machine learning is the mechanism the buyer is paying for or a feature layered onto conventional software, and whether the vendor is specific about which is which.

Drafting, memos, legal research, draft review, argument and counter argument generation and PDF question answering are all model driven, and the product is sold as an AI workspace rather than a database with AI added. The research panel's tools, cases for and against the user, arguments in the user's favor and a neutral judicial evaluation the site calls an AI judge, run on the same models. Only reading access to the judgment collection and the editor would remain without them.

Source: Vendor Published
CC on Citation Accuracy and Hallucination DisclosureAccuracy is asserted without measurement, or grounding is claimed while output cites sources the reader cannot open and verify.

Citation Accuracy and Hallucination Disclosure

Whether the vendor publishes measured accuracy on citations and assertions, grounds output to primary sources, and says plainly what its system does when it does not know. Legal has a documented public record of fabricated citations reaching filed briefs, so an untested claim of accuracy is not evidence.

Research answers cite provisions and judgments, and each cited judgment links to the product's own collection or to an outside source so a lawyer can read it. Draft Bot Pro promises that it does not make up cases, citations or references and also concedes that no AI is fully accurate. Its claims to be the most accurate legal AI for India and more accurate than SCC Online, Manupatra and general chatbots come with no test, method or error rate.

Source: Vendor Published
CC on Autonomy and Oversight ModelAutonomy is claimed and oversight is asserted without a mechanism. Human in the loop appears as a phrase rather than a described control.

Autonomy and Oversight Model

What the system decides on its own, what a lawyer must approve, and whether the vendor documents where the review point sits. A tool that drafts under review and a tool that files without one are different products and different risks.

Users draft, edit and download documents themselves in the product's editor, add facts, change tone and add clauses, and a review tool tracks its changes to a draft. The site urges users to read each cited source and concedes that no AI is fully accurate. No review step, approval control or limit on how drafts, arguments or the AI judge's evaluation may be used before filing is described.

Source: Vendor Published
DD on Operational and Outcome EvidenceNo production evidence located. Announcements, funding and launch coverage are not deployment evidence.

Operational and Outcome Evidence

Named, dated evidence that the product works in production at real firms or legal departments. Case studies with figures and identified customers count. Unattributed testimonials and launch announcements do not.

No customer, law firm or court user is named, and the one quote, calling it ChatGPT for law but more accurate, is unattributed. User counts differ from page to page, from 76,379 legal professionals on the teams page and 1,54,479 on the homepage to 4,64,500 users in the footer, and the sister app Law Bot Pro claims more than 4,27,000 users. The claimed 70% cut in review time and cost savings of around 90% come with no method, and press mentions in Bar & Bench, Shiksha and Beebom are coverage rather than deployments.

Source: Operator Verified
CC on Privilege and Confidentiality PostureConfidentiality is asserted in general terms, or the commitment lives only in a sales conversation and cannot be read in advance.

Privilege and Confidentiality Posture

How client confidences are handled: attorney client privilege and work product treatment, segregation of one client matter from another, whether client data trains any model, and what the vendor commits to in writing rather than in marketing.

The product pages say user data is never used for training, that session content is visible only to the user and that no data is accessible to the company. The terms, shared with Rarelabs' other apps, contain no confidentiality clause or training term and allow personal information to be shared with third parties for email delivery and marketing assistance. Nothing addresses privileged material in uploaded case files.

Source: Vendor Published
CC on UPL and Professional Responsibility PostureA boilerplate disclaimer sits in the terms while the marketing describes the product in advice terms, or the intended audience is left ambiguous.

UPL and Professional Responsibility Posture

Whether the vendor is clear that it supplies a tool rather than legal advice, who its audience is, and how it addresses unauthorized practice of law, competence and supervision duties, and jurisdiction limits. ABA Formal Opinion 512 is the reference point. Where the advice line is not the duty a product raises, the axis is read through the nearest professional duty it does raise: judicial conduct rules and the reviewing duty for products sold only to courts, and the duty to bill for time actually spent for products that draft time entries.

The terms describe the applications as informational and not a recommendation or legal advice, and disclaim responsibility for the accuracy of their content. The product is sold to advocates and law students but also, in its FAQ, to companies and individuals with drafting needs. Nothing addresses a lawyer's duty to verify AI drafts, how people without legal training should use them, or how the AI judge's evaluation should be read.

Source: Vendor Published
DD on AI Governance and Bias DisclosureNo governance position published for a system whose output affects legal outcomes.

AI Governance and Bias Disclosure

Published governance over model behavior: who owns it inside the vendor, what is tested before release, and what is disclosed about disparate output across matter types, parties, or populations.

No AI policy, named owner for the models, testing of drafting or research accuracy, or review across languages and courts is offered. Rarelabs is led by lawyers by its own account, with no one tied to model oversight, and the neutral judicial evaluation tool rates arguments with no account of how its judgments are tested.

Source: Operator Verified
CC on AI Safety and Data StewardshipA generic privacy policy covers the product without addressing what happens to documents and prompts after processing.

AI Safety and Data Stewardship

Retention, deletion, access control, and what happens to prompts and documents after they are processed. Whether the vendor states its subprocessors and its incident practice, or leaves the buyer to assume.

Uploaded files are deleted automatically after seven days, while chat history is kept with no stated period. Session content is said to be visible only to the user and inaccessible to the company. Security is promised at an enterprise level and in line with leading guidelines, without any named control, subprocessor, hosting provider or breach notice practice.

Source: Vendor Published
DD on AI Liability and RecourseNothing published on who bears the loss when the system is wrong.

AI Liability and Recourse

What the vendor stands behind contractually when its output is wrong. Indemnities, caps, carve outs, insurance, and whether any of it is published or only reachable through a negotiated agreement.

The terms, shared across Rarelabs' apps, state that Rarelabs and its people are not liable for damages of any kind, with no cap, warranty or vendor indemnity. Users must indemnify Rarelabs, attorneys' fees included, and no governing law or venue is stated. The terms also disclaim responsibility for the accuracy of content in the applications.

Source: Vendor Published
DD on Practice Systems Integration DepthNo integration into practice systems located, or the product stands alone and requires work to move to it.

Practice Systems Integration Depth

How deeply the product reaches into the systems legal work already lives in: document management such as iManage and NetDocuments, Word and Outlook, contract lifecycle management, matter management, e-billing, and court filing systems.

Documents come in as PDF uploads of up to 600 pages or typed facts and leave as Word or PDF downloads. No connection to case management, court filing, document management or email systems is offered.

Source: Operator Verified
CC on Deployment Model and Data ResidencyCloud delivery is implied and neither the tenancy model nor the region is stated.

Deployment Model and Data Residency

Where the software runs and where the data sits. Multi tenant cloud, single tenant, private deployment, on premises, and whether region of residence is a published option or an enterprise conversation.

Draft Bot Pro runs as a web application reached by signing in to its app. No hosting provider, region, tenancy model or location for model processing is stated.

Source: Vendor Published
DD on Security Certifications and Trust CenterNo independent security attestation located.

Security Certifications and Trust Center

Independent attestation a buyer can pull without a sales call: SOC 2, ISO 27001, penetration test summaries, a trust center with current reports and named scope rather than a badge image.

Security is described only as enterprise level and compliant with leading guidelines, with no certification, audit report, trust page or named control behind it.

Source: Operator Verified
DD on Model Supply Chain DisclosureNothing published about the model supply chain a customer inherits.

Model Supply Chain Disclosure

Which models sit underneath, whose they are, where they run, and whether the vendor commits to telling customers when that changes. A legal buyer inherits every dependency it cannot see.

Drafting rests on what the site calls a proprietary multi step agentic approach, with no model, model provider or hosting location named and no notice of change promised.

Source: Operator Verified
BB on Commercial TransparencyReal pricing is published for part of the range, with enterprise tiers withheld, or the unit and structure are stated without the figure.

Commercial Transparency

Whether a buyer can learn what this costs without entering a sales process: published rates, the unit being charged, what sits behind an enterprise tier, and what implementation adds.

Prices are listed in rupees, with a free plan of 500 AI words a day and limited PDF uploads and the Infinity plan at ₹999 a month with Deep Thinking Mode and near unlimited words under a fair usage policy. Students get 30% off Infinity in their first term, and teams and institutions get seat based pricing on request after a demo. Refunds are available within seven days of purchase, plans do not renew by automatic deduction, and GST treatment is not stated.

Source: Vendor Published
CC on Firm and Practice CoverageCoverage is claimed broadly, for all firms or all practice areas, without evidence that the breadth is real.

Firm and Practice Coverage

Who the product is actually built for. AmLaw, midlaw, small firm and solo, in house departments, government and courts, and which practice areas are supported rather than merely claimed.

Advocates, young lawyers, law students, legal teams and law firms across India are the named audience, with companies and individuals also mentioned, and drafting covers any Indian legal document. A banner claims daily use in courts across India, with no court named. Coverage is limited to Indian law, and no list of courts or practice areas is given.

Source: Vendor Published
Sources on file

4 public documents

The public pages on file for Draft Bot Pro, with the recorded signals each one supports and the date it was last read. Open any of them and check the reading against the record.

Pricing

₹999/month

INR, as published, never converted
  • The Infinity plan costs ₹999 a month.
  • A free plan allows 500 AI words a day with limited PDF uploads.
  • Students get 30% off Infinity for their first term, and team pricing is quoted per seat.

Infinity includes all features, Deep Thinking Mode and near unlimited words under a fair usage policy, with call, email and chat support. The free plan gives partial access to drafting, research and memos. Team and institutional plans use seat based pricing set on request.

Implementation: None stated.

Note: Refunds are available within seven days of the initial purchase, and add on words are not refundable. Plans can be canceled at any time before renewal, with email cancellations due three days ahead. GST treatment is not stated.

Legal Signals

What each signal means

A signal records what public sources say on the date shown. It is not a grade and it is not a recommendation. Where a signal reads Not addressed, it means the index did not locate the material in public sources on that date, which is a statement about disclosure rather than about the product.

Confidentiality and Privilege

Client Data in Training

Can material a lawyer puts into this product be used to train a model?

Never, in policy only

A public policy or trust page states no training on customer content, with no matching term located in the published agreement.

The product pages say user data is never used to train models and that session content is not used for training. The terms, shared with Rarelabs' other apps, carry no training term, so the commitment rests on the product pages alone.

Source: Vendor PublishedWe never train on your data.As of Nov 20, 2026Evidence

Prompt and Output Retention

How long does the product keep what a lawyer typed, and can that be set to zero?

Disclosed without a period

Retention is acknowledged in public materials with no stated period.

Uploaded files are deleted after seven days, while chat history, prompts and outputs included, is kept with no stated period. Drafts and memos stay in the user's workspace until removed.

Source: Vendor PublishedFiles get auto-deleted in 7 days for maximum privacyAs of Nov 20, 2026Evidence

Ethical Walls and Matter Segregation

Does retrieval respect the firm’s ethical walls, or can the model read across them?

Claimed, not documented

Segregation is asserted in public materials with no published detail on how it is enforced.

Session content is said to be visible only to the user who wrote it, with no description of how team plans separate matters or clients across seats.

Source: Vendor Publishedonly accessible to you and is not used to train our modelsAs of Nov 20, 2026Evidence

Third Party Request and Subpoena Notice

If someone subpoenas the vendor for a firm’s data, does the firm hear about it first?

Not addressed

No located term or policy addresses third party requests for customer data.

The terms reserve a right to share personal information with third parties for business purposes and say nothing about court orders, government requests or notice to the user.

Source: Operator VerifiedAs of Nov 20, 2026Evidence
Accuracy and Authority

Primary Law Corpus Provenance

Where does the law in this product come from, and does the vendor have the right to use it?

Jurisdictions only

Coverage is described by jurisdiction with no identification of the underlying corpus.

The collection is described as more than 2.4 crore Indian judgments, orders and more, without naming the courts, tribunals or suppliers behind it or an update cadence. Memos are said to rest on current information without a date.

Source: Vendor PublishedAs of Nov 20, 2026Evidence

Good Law Verification

Does the product tell you when the authority it just cited has been overruled?

Not addressed

No located public material addresses whether authority is checked for subsequent history.

Nothing describes whether a cited judgment has been overruled, stayed or distinguished, though the panel separates landmark and similar judgments and cases for and against the user.

Source: Operator VerifiedAs of Nov 20, 2026Evidence

Refusal and Uncertainty Behavior

What does the product do when the answer is not in the corpus?

Not addressed

No located public material addresses what the product does when it cannot ground an answer.

The site concedes that no AI is fully accurate, but no behavior is described for questions the collection cannot answer or for when the AI judge cannot reach a view.

Source: Operator VerifiedAs of Nov 20, 2026Evidence

Fabricated Citation Record

Does a public court record exist addressing fabricated or hallucinated legal citations in output from this product?

None located

No court order, opinion or disciplinary record addressing fabricated or hallucinated legal citations produced by this product has been located as of the date shown. This is a statement about the public record on that one subject, not a finding about the product, and this signal is not a litigation history.

The AI Hallucination Cases database kept by Damien Charlotin has no entry naming Draft Bot Pro or Rarelabs.

Source: Operator VerifiedAs of Nov 20, 2026Evidence
Professional Responsibility

Bar Guidance Alignment

Has the vendor engaged in public with the ethics opinions its buyers are bound by?

Not addressed

No located public material engages with bar or ethics guidance.

No Bar Council of India or court guidance on AI use by advocates is referenced. The product is sold to advocates and law students, and its terms describe the apps as informational only.

Source: Operator VerifiedAs of Nov 20, 2026Evidence

Billing and Fee Posture

Does the vendor address what happens to the bill when the work takes an hour instead of six?

Savings claims only

Public materials claim time savings without addressing billing or disclosure, and the product sits inside a fee relationship between a lawyer and a client where those savings would change the bill.

Advocates and law firms are the buyers, and the site claims cost savings of around 90% and a 70% cut in review time without addressing how that changes fees charged to clients. It also compares its ₹999 plan with a general chatbot subscription it prices at ₹17,000 a month.

Source: Vendor PublishedAs of Nov 20, 2026Evidence

Outside Counsel Guideline Readiness

Can a firm get this vendor through a client’s AI clause without a bespoke negotiation?

Not addressed

No located public material supports a client side disclosure obligation.

No subprocessor or model provider list, security summary or client facing AI disclosure is available. The terms and privacy policy share one Rarelabs page across its apps.

Source: Operator VerifiedAs of Nov 20, 2026Evidence

Court Disclosure Support

If a judge’s standing order requires an AI disclosure, can the product produce one?

Not addressed

No located public material addresses court disclosure or verification certification.

No record of AI use in a draft or argument is produced for disclosure to a court. Drafts leave as ordinary Word or PDF files.

Source: Operator VerifiedAs of Nov 20, 2026Evidence
Contact

Correct a record, or ask how something was graded

Every grade and every signal on this index is drawn from public sources and dated. If a record is wrong, out of date, or missing an artifact the index did not locate, send the source and it will be reviewed and the record redated. Vendors are welcome to submit documentation. Nothing on this index is for sale, including a listing, a placement, or a grade.

AI Legal Index

The AI Legal Index is an independent index that tracks changes to AI vendors in legal. It holds 617 vendors across 9 categories, each graded on the same 15 capability axes and recorded against 12 legal signals, from public sources. No vendor pays for inclusion, placement, or rating.

Index Status
Last index update
November 20, 2026
The AI Legal Index is an editorial reference. It is not a regulatory body, not a law firm, and nothing published here is legal advice or a recommendation to retain or avoid a vendor. Records are verified against published sources, bar guidance and public court records. Where a record reads not addressed, the material was not located in public sources on the date shown. See the Methodology page for evaluation standards and limitations.
© 2026 AI Legal Index
3801 N Capital of Texas Hwy, Ste E240 · Austin, TX 78746