B
Backdocket

Backdocket is practice management software for law firms from solo practices to about 300 people, built around claims from intake through settlement and disbursement. Depeltier Technologies, LLC sells it. Claim records, documents, calendars, the ledger with check approvals, trust accounting, dashboards and reporting sit in one system, with templates for personal injury, auto claims, medical malpractice, mass torts, workers' compensation and other practice areas.

AI Case Chat answers questions about a claim with citations to the source document and page, a note or a ledger entry. Agents such as Medical Chronologist, Demand Analyst, Billing Auditor and Compliance Checker build treatment timelines, audit bills, detect liens and draft demands and settlement brochures. Firms run the built in AI on their own Anthropic, OpenAI or Azure OpenAI key, or connect Claude, ChatGPT, Gemini, Microsoft 365 Copilot or Zoom AI Companion through the Model Context Protocol.

Dudley DeBosier Injury Lawyers and Caldwell Wenzel & Asthana use it for case data, intake and reporting. The subscription runs month to month at $79.99 per user with every feature, including BackVault, a synchronized SQL Server copy on the firm's own infrastructure. The model provider bills the firm directly.

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.

BB on AI CentralityThe models are the engine of a core capability, layered on a product that would still function without them as a document or workflow system.

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.

Claim chat uses a model the firm licenses to answer questions from a live matter. The platform extracts text and entities at upload, segments documents and uses Amazon Bedrock for embeddings in a vector index dedicated to each firm. Agents named Case Analyst, Document Reviewer, Medical Chronologist, Demand Analyst, Billing Auditor, Compliance Checker and Data Validator take the work, chosen automatically, and firms can add their own.

Background agents classify documents, review medical records, audit bills and detect liens as files arrive. Intake, accounting, case management and reporting run without a connected model.

Source: Vendor Published
BB on Citation Accuracy and Hallucination DisclosureGrounding is real and documented, with linked primary sources and a described retrieval method, short of published accuracy figures an outsider can test.

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.

Case answers can link to a source document and page, a claim note, a ledger entry, or a field in the case record. Users can limit context to selected documents or include more than one claim. The system retrieves and reranks document segments when they are available. The terms caution that generative output may be inaccurate or incomplete. The company does not perform judicial citation validation or report a reference accuracy rate for medical and case material.

Source: Vendor Published
BB on Autonomy and Oversight ModelA written commitment that the models work alongside a supervising lawyer, with real review surfaces, short of the full control structure: commonly the threshold at which the system stops or what happens after it is wrong.

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.

Staff can start from a specified claim, choose its documents as context and save a draft to the case after reviewing it, and they can cancel an AI operation midway while a bar shows how much context remains. An external assistant can read and update records within the connected user's permissions, and Claude or ChatGPT can run scheduled tasks such as a morning review of new documents. The Microsoft 365 Copilot connector is read only.

Administration includes revoking API access and restricting integrations, and the subscription contract makes the customer responsible for checking AI output. No universal approval step covers every connector action or generated change.

Source: Vendor Published
BB on Operational and Outcome EvidenceReal deployment evidence with substance, short of full attribution or measurement: a named customer without figures, or figures without the named customer.

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.

Dudley DeBosier Injury Lawyers reports using the software to hold case information and build its own reporting. Caldwell Wenzel & Asthana calls it the firm's first intake management software and credits it with better processes and reporting, and Brian Hodgkiss praises the accounting for calculating offers quickly. The company's walkthrough shows an assistant questioning a claim, preparing a demand and assembling a report from case data, along with selecting claims that need client contact and building an intake dashboard. No measure of the chronology agent's error rate or of AI's effect on claim outcomes accompanies these accounts.

Source: Vendor Published
AA on Privilege and Confidentiality PostureWritten commitments a buyer can read before signing: no training on client data, segregation documented at the level the buyer segment requires (matter level walls for a firm, tenant level separation for an in house team), privilege and work product handling addressed directly, retention and deletion stated, and the position on third party model providers made explicit.

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.

Section 13.3 of the subscription agreement bars Backdocket from using Customer Data to train or fine tune models. The platform isolates firms, gives each its own vector index, supports field and role permissions and restricts private claims. A connected assistant gets only the access its user already has in the product. Model processing under the firm's own license follows the firm's agreement with that provider. For qualifying HIPAA relationships, the subscription includes business associate terms covering Backdocket's processing, with a separate provider relationship for the firm's model.

Source: Vendor Published
BB on UPL and Professional Responsibility PostureA real position is published on advice versus tooling, short of full treatment: commonly a disclaimer without the supervision and competence dimension, or silence on jurisdiction limits.

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 system prepares working material for attorneys, including a treatment timeline or a draft demand populated from a firm's templates. A lawyer remains responsible for professional decisions and for checking output under the subscription agreement. Firms control which users and data the assistants can access. Medical records may be handled under the applicable business associate terms. The company does not provide a named bar rules mapping or a product certification for using a generated demand in practice.

Source: Vendor Published
BB on AI Governance and Bias DisclosureA published governance framework with real substance, short of testing results or a named owner.

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.

Firm administrators manage roles, field access and connected services. Conversations about a case can be limited to selected documents. Separate agents handle treatment history, billing issues, compliance checks and case analysis, and the firm can configure agents for its own workflows. Audit logs tie platform actions to an endpoint and a timestamp, and usage records keep the provider, model and purpose of each AI call. No bias or outcome testing by client group, matter type or model version is reported.

Source: Vendor Published
BB on AI Safety and Data StewardshipSubstantive published policy covering most of the ground, short of the full set: commonly no named subprocessor list or no stated incident practice.

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.

Customer data lives in the firm workspace during the subscription, subject to deletions, and is normally kept for one year after cancellation. A firm can ask for earlier deletion, completed within 30 days. Activity audit logs are kept for 90 days and usage metadata for each AI call for 24 months. Generated downloads that are not filed stay available for 30 days, and copies saved to a claim become case documents. The firm's chosen AI provider handles inference under the firm's own contract, and case data stays in Backdocket rather than being copied into another product.

Source: Vendor Published
BB on AI Liability and RecourseA real published position on liability, short of the full picture: commonly a stated indemnity without scope or caps.

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 subscription agreement disclaims a warranty for AI output and leaves professional decisions with the firm. Its general liability limit is the fees paid over the preceding 12 months, with exceptions including indemnity, gross negligence, and willful misconduct. Backdocket gives a defense and indemnity for specified third-party intellectual property claims about the supplied service. A customer connects its own model and must rely on the terms it negotiated with that provider for that service.

Source: Vendor Published
AA on Practice Systems Integration DepthDocumented, verifiable integrations into the systems legal work already lives in, with the depth described: what syncs, in which direction, and what a firm must configure.

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.

Named connections include Microsoft 365 and Google Workspace for documents and communications, QuickBooks for accounting, DocuSign for signatures and Twilio for messages. BackVault synchronizes a SQL Server replica for tools such as Microsoft Power BI, Tableau or SQL Server Reporting Services. Every endpoint is open to assistants through the Model Context Protocol, and the Microsoft 365 Copilot connector is on the Microsoft Marketplace, approved once by an administrator and signed into by each user. The firm keeps its document templates and fills them from case and ledger fields when generating Word output.

Source: Vendor Published
BB on Deployment Model and Data ResidencyDeployment model is stated clearly with partial residency detail, or residency is offered without the processing location being addressed, or the tenancy model is stated on its own with no residency detail published.

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.

The product and its backups are hosted on AWS in the United States under the privacy policy. BackVault can keep a separate SQL Server replica, which the firm can read but not change, on the firm's own infrastructure, refreshed as often as once a minute. That replica is a data custody option beside the hosted production service. Generative inference runs on models under the firm's license and processing terms, while Backdocket runs document embeddings on Amazon Bedrock.

Source: Vendor Published
CC on Security Certifications and Trust CenterBadges appear on the site with no scope, no date, and no report available.

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.

Technical safeguards include encryption at rest and in transit, multifactor authentication, tenant isolation, and private claim controls. The company identifies AWS as its hosting subprocessor and states it has a business associate agreement for the environment. Personnel can access data for operation or support, and that direct database access is not separately logged in the application audit trail. The terms make security commitments but do not identify a product SOC report or an ISO certificate.

Source: Vendor Published
BB on Model Supply Chain DisclosureThe supply chain is partly disclosed: providers named without change notification, or architecture described without the providers.

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.

Firms choose Anthropic, OpenAI or Azure OpenAI for the built in generative functions on their own API key and can switch providers without migrating data or rebuilding the index. External assistants, Claude, ChatGPT, Gemini, Microsoft Copilot and Zoom AI Companion among them, connect through the Model Context Protocol. The embedding pipeline Backdocket runs uses Amazon Bedrock and is covered by the subscription. The system records the model and token counts for each AI call. The model versions behind the hosted embedding and segmentation steps go unnamed.

Source: Vendor Published
AA on Commercial TransparencyA buyer can learn what this costs without entering a sales process: published rates, the unit being charged, and what implementation adds.

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.

Backdocket charges $79.99 a month for each active user on a month to month subscription, with one feature set, no tiers or add ons and no minimum seat count, for firms from solo practices to 300 users. Standard onboarding is currently free, support is free, and BackVault comes with every subscription with no storage fees. Firms pay their own model provider for inference with no markup, and Backdocket covers document embedding on Amazon Bedrock.

Nonstandard migration and extra configuration can be scoped and billed separately. Existing customers get six months' written notice of a price change, and cancellation carries no fee.

Source: Vendor Published
BB on Firm and Practice CoverageSegment and practice coverage is described with substance, short of the boundaries: what is supported is clear, what is not is left open.

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.

The case system supports firms from solo practices to teams of several hundred. Its claim workflows span treatment records, settlement demands, expenses, and disbursement. Templates cover personal injury, auto, malpractice, mass torts, and workers' compensation, alongside family, estate, immigration, and other matters. Firms can configure the case type, required fields, and workflow. The product emphasizes plaintiff case examples while also providing general practice management and intake.

Source: Vendor Published
Sources on file

3 public documents

The public pages on file for Backdocket, 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

$79.99 per user per month

USD, as published, never converted
  • Backdocket costs $79.99 per active user each month.
  • Every user has the same feature package, including BackVault.
  • The firm pays its selected model provider separately.
  • Standard onboarding is currently included.

Monthly fees are based on active authorized users at billing. The subscription includes the platform's own AI tools, the API, BackVault and the vendor's document embedding service. A firm's own model, connected services and replica infrastructure can carry separate charges.

Implementation: Standard onboarding is included under current practice. Custom configuration, nonstandard migration, or additional training can be separately priced. The firm supplies and pays for its BackVault replica infrastructure.

Confidentiality and data terms: Section 14 automatically applies to qualifying covered entities and business associates handling protected health information. Standalone signed copy available on request.

Note: The subscription can be canceled after the active month without a cancellation fee. Price changes for existing subscribers require at least six months' written notice.

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 the contract

The published terms prohibit training on customer content. Not a policy page, the agreement.

Section 13.3 of the subscription agreement bars Backdocket from training or fine tuning AI or machine learning models on Customer Data. Inference under the firm's own AI license is governed by the firm's separate terms with the chosen provider.

Source: Vendor PublishedCompany never uses Customer Data to train or fine-tuneAs 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?

Customer controlled, no zero option

The customer controls the retention window, by product configuration or by contractual instruction, but zero retention is not stated as available.

Firms may delete case material or request earlier deletion under the subscription agreement. Generated files stay downloadable for 30 days, and saved copies follow case retention. Retention at the model provider depends on the firm's own license.

Source: Vendor PublishedAs of Nov 20, 2026Evidence

Ethical Walls and Matter Segregation

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

Own model, documented

The product maintains its own permission model, documented, requiring the firm to keep it aligned.

Firm isolation applies to application and AI access, and each firm gets a dedicated vector index rather than shared infrastructure with filtering. Role and field permissions and private claim restrictions govern what a connected assistant can reach, and they are Backdocket's own permissions.

Source: Vendor PublishedRole-based and field-level access control, including private-claim restrictionsAs 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?

Notice committed

Terms commit to notice where lawfully permitted. No transparency report located.

The incorporated privacy policy commits to prompt notice when a firm's data is compelled, with advance notice where lawful, and limits any disclosure to the minimum required.

Source: Vendor Publishedwe will notify the firm promptlyAs 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?

Not addressed

No located public material identifies the corpus behind the product’s answers.

Case chat links to the firm's own case files, notes and ledger entries. Firm chat takes broader legal and operational questions, and no primary legal collection or rights basis for one is named behind it.

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.

The assistant links generated case content to the records behind it. No check of later history or legal treatment for court opinions is part of the product.

Source: Vendor PublishedAs 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.

Case chat retrieves supporting material and runs in a reduced mode when vector retrieval is unavailable rather than failing. No explicit rule says it declines to answer when case records do not support a conclusion.

Source: Vendor PublishedAs 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 Backdocket. The product drafts demands and settlement materials from a firm's own case records rather than court filings with case citations.

Source: Operator VerifiedAs of Nov 20, 2026
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.

The subscription contract makes the firm responsible for reviewing AI output and exercising professional judgment. The AI features are not tied to guidance from any bar authority.

Source: Vendor PublishedAs 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?

Audit record only

A usable record of AI assisted work exists with no published fee guidance.

The Billing Auditor agent reviews bills on a claim, generated summaries can be saved to the claim, and usage records keep the provider, model and purpose of each AI call for 24 months. Nothing covers how a firm bills a client for AI assisted time or for provider charges.

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?

Subprocessors listed

A current subprocessor or model provider list is published.

The privacy policy lists AWS for hosting and Braintree for subscription payments and separates the providers a firm brings under its own subscriptions. No bundled packet for a law firm's clients is offered.

Source: Vendor PublishedAs of Nov 20, 2026Evidence

Court Disclosure Support

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

Partial record

Some elements of the record are available, short of a document level export.

Case chat links to source documents and pages, and users can save its output to the claim. The system keeps AI call metadata separately. No export for a disclosure combines the model, the sources and the human check behind a document.

Source: Vendor PublishedAs 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