C
CounselPro
CounselPro is forensic financial analysis software from CounselPro, Inc. of New York for family law, bankruptcy, probate, estate and business litigation lawyers, mediators, trustees and accountants. It reads a production of bank, credit card and check statements, extracts and categorises every transaction, reconciles each statement cycle to the balances the bank printed and re-reads pages that do not balance, and flags missing months, duplicate statements and figures the records cannot support.
Its Daystrom AI answers plain-English questions with the arithmetic shown and every figure linked to its page, and it drafts an editable forensic report shaped to the matter type. Brokerage and tax documents are planned for late 2026. Pricing is published: $499 per matter, or firm-wide plans from $100 a month, with no per-seat charges.
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.
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.
The models are the product. CounselPro's AI reads each statement page, extracts and categorises transactions, re-reads pages that do not reconcile, answers questions about the records in Daystrom chat and drafts a forensic report. Without the models there is little left to sell. Verified 22 September 2026.
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.
Grounding and a checking method are described; accuracy is not measured. Every figure links to the statement page it came from, each statement cycle is added up against the beginning and ending balances the bank printed, a cycle that misses is re-read against the page image, and one that still cannot be proved is flagged rather than closed. Daystrom shows the arithmetic behind each answer and leaves unsupported figures open. No error rate, test set or independent evaluation is published. Verified 22 September 2026.
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.
Flagged gaps and a written review duty, short of stated limits. The product flags statement cycles it cannot reconcile, missing months and unsupported figures for the lawyer to weigh, and reports are editable after they are written. The Terms of Service say output is not legal advice and must be reviewed by a qualified lawyer. Nothing states what the forensic report may not be used for without review. Verified 22 September 2026.
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.
Checked the home, About, How it works, Platform and Pricing pages on 22 September 2026. No named customer, testimonial, case study or measured result was located; the site's examples are illustrations. Verified 22 September 2026.
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.
Strong commitments, partly in the agreement, with a gap on the vendor's own use of data. The Terms of Service treat customer data as confidential information, bar sharing it with other customers or third parties beyond named subprocessors, and state that, to CounselPro's knowledge, data sent to third-party language models is not used to train them. The security page says each matter is processed in isolation, even from other matters in the same firm, that records never train any model, that data stays in the United States and can be deleted at any time, and names every AI provider.
The terms also reserve by default the processing of customer data to calibrate CounselPro's internal AI systems for general product improvement, and privilege is addressed only in marketing. Verified 22 September 2026.
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.
A clear advice line in the agreement, short of jurisdiction limits. The Terms of Service say output is not legal advice, that CounselPro does not provide legal advice, and that customers who are not lawyers must have output reviewed by a qualified lawyer; the warranty section repeats the review requirement. The security page says the product is built around ABA Model Rule 1.6. The jurisdictions and uses the product covers or excludes are not stated. Verified 22 September 2026.
AI Governance and Bias Disclosure
Published governance over model behaviour: who owns it inside the vendor, what is tested before release, and what is disclosed about disparate output across matter types, parties, or populations.
Checked the home, About, Security, Platform and Changelog pages, the Terms of Service and the Privacy Policy on 22 September 2026. No AI governance framework, accountable owner or testing before release was located beyond the stated principle of flagging what cannot be verified. Verified 22 September 2026.
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.
Most of the ground is published and specific; incident handling is not. The security page describes AES-256 encryption at rest, TLS 1.3 in transit, per-matter isolation, one-time-code sign-in with no passwords, US-only hosting and deletion of any document or matter at any time, and the subprocessor page names every vendor with its role and location and is updated when the list changes. No incident notification commitment was located, and the Privacy Policy, from July 2024, does not state retention periods. Verified 22 September 2026.
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.
Addressed through a standard limitation clause. The Terms of Service cap CounselPro's liability at the fees paid in the prior twelve months, exclude indirect damages with carve-outs, disclaim warranties of output accuracy with a requirement for qualified lawyer review, and require the customer to indemnify CounselPro for claims arising from customer data and misconduct. Nothing stands behind a figure that proves wrong. Verified 22 September 2026.
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.
Checked the home, Platform, How it works and Help Center pages on 22 September 2026. Statements are uploaded as PDFs and results export as CSV, XLSX, PNG or PDF; no connection to a case management, document management or accounting system was located. Verified 22 September 2026.
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.
Region and isolation are stated for a single hosted service. The security and subprocessor pages say all client data is hosted in US data centres and never leaves the country, with every subprocessor located in the United States, and that each matter runs in its own isolated space. No other deployment option is offered, and where each model provider processes data beyond the country is not broken down further. Verified 22 September 2026.
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.
No attestation of its own. The security page says CounselPro runs on providers audited to SOC 2 Type II and states that this is the providers' certification, not CounselPro's. The security page and subprocessor list are public and security questionnaires are welcomed, but no audit report or certification of CounselPro itself is published. Verified 22 September 2026.
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.
Providers are named; models are not. The subprocessor page names Anthropic, Google, Cohere and DeepInfra as AI model providers, says what each does and that each is in the United States, and says every provider is bound by an agreement that forbids training on customer data; the page is updated when the list changes. Which models are used, and advance notice of a change, are not published. Verified 22 September 2026.
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.
A buyer can price it without a sales call. The pricing page publishes a Single Project at $499 per matter and firm-wide plans at $100, $250 and $500 a month, lists what each includes, prices usage in credits per page with top-up packets from 10 to 40 cents a credit, charges no per-seat fees, offers a free trial and links a refund policy. Verified 22 September 2026.
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.
Coverage and limits are both stated. The site names family law, bankruptcy, probate, estate planning, business litigation and accounting, with use cases for paralegals, high-net-worth divorce, mediation and bankruptcy trustees; it reads bank, credit card and check statements from PDFs, says paper must be scanned first, gives typical matter sizes, and states that brokerage and tax documents are not yet supported and are planned for the fourth quarter of 2026. Verified 22 September 2026.
7 public documents
The public pages on file for CounselPro, 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.
-
counselpro.ai/security4 signals
Client Data in Training, Prompt and Output Retention, Ethical Walls and Matter Segregation and 1 more
Read Sep 22, 2026
-
counselpro.ai/daystrom1 signal
Refusal and Uncertainty Behaviour
Read Sep 22, 2026
-
counselpro.ai/platform1 signal
Court Disclosure Support
Read Sep 22, 2026
-
counselpro.ai/pricing1 signal
Billing and Fee Posture
Read Sep 22, 2026
-
counselpro.ai/privacy1 signal
Third Party Request and Subpoena Notice
Read Sep 22, 2026
-
counselpro.ai/subprocessors1 signal
Outside Counsel Guideline Readiness
Read Sep 22, 2026
-
Fabricated Citation Record
Read Sep 22, 2026
$100 per month (Core plan, whole firm)USD, as published, never converted
- CounselPro's Core plan is $100 a month for the whole firm, with no per-seat charges.
- Plus is $250 a month and adds AI chat and forensic reports; Premier is $500 a month and adds reconciliation.
- Or pay $499 for a single matter with everything included, billable to the client as a case expense.
- Each plan includes 1,000 credits a month, and one statement page uses one credit.
- Extra credits cost 10 to 40 cents each depending on the plan.
Published plans, no seats. **Single Project**: $499 per matter, every capability including reconciliation, 1,000 credits (top up to 10,000). **Core**: $100 per month, extraction, categorisation, insights dashboard, Excel export. **Plus**: $250 per month, adds Daystrom AI chat and AI forensic reports. **Premier**: $500 per month, adds self-healing reconciliation and duplicate detection. Monthly plans include 1,000 credits a month; yearly plans 12,000 up front. **Credits**: 1 per standard page (bank, card, check images), 2 per dense page (investment, brokerage, tax). **Top-ups**: 1,000, 5,000 or 10,000 credit packets at 10 to 40 cents a credit depending on plan.
Implementation: None published; nothing to set up beyond uploading statements.
Confidentiality and data terms: No Business Associate Agreement is offered or referred to on the pages read; the product handles financial statements rather than health records.
Note: Plans cover the whole firm with unlimited users; the only difference between them is how deeply the records are read. Extra credits are non-refundable, and a refund policy is published separately. Annual subscription increases are capped at 10% under the Terms of Service unless the service materially changes. A free trial and a demo on one real matter under mutual NDA are offered.
Legal Signals
What each signal meansA 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.
Client Data in Training
Can material a lawyer puts into this product be used to train a model?
A public policy or trust page states no training on customer content, with no matching term located in the published agreement.
The security page says client records never train any model and that the enterprise agreements CounselPro signs with its providers forbid it. The customer Terms of Service state only that, to CounselPro's knowledge, data sent to third-party language models is not used to train them, with opt-outs taken, and reserve by default the processing of customer data to calibrate CounselPro's internal AI systems for general product improvement or personalisation, without using the word training.
Prompt and Output Retention
How long does the product keep what a lawyer typed, and can that be set to zero?
The customer controls the retention window, by product configuration or by contractual instruction, but zero retention is not stated as available.
The security page says the source document is kept only so every figure keeps its page, and that a customer can delete a document or a whole matter at any time. How long data persists after deletion, and default retention otherwise, is not stated.
Ethical Walls and Matter Segregation
Does retrieval respect the firm’s ethical walls, or can the model read across them?
The product maintains its own permission model, documented, requiring the firm to keep it aligned.
The security page says every matter is processed in its own isolated space reachable only by the systems that need it, and lists another matter, even in the same firm, among the places a document never reaches. Team membership is managed in CounselPro's own account settings; nothing describes inheriting permissions from another system.
Third Party Request and Subpoena Notice
If someone subpoenas the vendor for a firm’s data, does the firm hear about it first?
Published terms or policy address disclosure to authorities or in response to legal process, and no commitment or reservation regarding customer notice is located anywhere. The vendor has told the customer that data can leave and has said nothing about whether the customer hears of it.
The Privacy Policy says CounselPro may preserve or disclose information where reasonably necessary to meet applicable legal process or an enforceable governmental request. Nothing in it or the Terms of Service commits to notifying the customer.
Primary Law Corpus Provenance
Where does the law in this product come from, and does the vendor have the right to use it?
No located public material identifies the corpus behind the product’s answers.
Checked the Platform, How it works and Daystrom pages on 22 September 2026. CounselPro works only on the statements a customer uploads and does not answer from a body of law, so no legal corpus is identified.
Good Law Verification
Does the product tell you when the authority it just cited has been overruled?
No located public material addresses whether authority is checked for subsequent history.
Checked the Platform, Daystrom and forensic report pages on 22 September 2026. The product cites statement pages, not legal authority, and nothing addresses checking authority for later treatment.
Refusal and Uncertainty Behaviour
What does the product do when the answer is not in the corpus?
The vendor describes refusal or abstention behaviour in public materials.
The Daystrom and Platform pages say a figure the records cannot support is left open and flagged for the lawyer, that a statement cycle which cannot be reconciled to the printed balances is flagged for review and never quietly closed, and that missing months are shown as gaps. No published evaluation shows how reliably this happens.
Fabricated Citation Record
Does a public court record exist addressing fabricated or hallucinated legal citations in output from this product?
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.
Searched the AI Hallucination Cases database maintained by Damien Charlotin on 22 September 2026 for CounselPro, and no recorded case was returned. No court order, opinion or disciplinary record naming the product was located. This is a statement about the public record rather than a finding about the product.
Bar Guidance Alignment
Has the vendor engaged in public with the ethics opinions its buyers are bound by?
Public materials engage with at least one named ethics opinion.
The security page names ABA Model Rule 1.6 on confidentiality and says the lawyer's obligation to protect client information shaped how the product works, with the framework kept current as state bars refine their expectations on AI and client data. No state-by-state mapping or ethics opinion is named.
Billing and Fee Posture
Does the vendor address what happens to the bill when the work takes an hour instead of six?
The vendor’s charge reaches the client as a disbursement or case expense, typically advanced by a contingency firm and recovered from a settlement, so the fee question is disclosure of a pass through cost rather than compressed hours. The summary records whether the vendor addresses that disclosure.
The pricing FAQ tells firms to run a Single Project for a one-off matter and bill the $499 to that client as a case expense, like a filing fee or records request, or on a plan to fold the cost into standard case costs.
Outside Counsel Guideline Readiness
Can a firm get this vendor through a client’s AI clause without a bespoke negotiation?
A subprocessor and model provider list plus client facing disclosure material is published or available without an agreement in place.
A published subprocessor list names every vendor, including the AI model providers Anthropic, Google, Cohere and DeepInfra, with what each does and where it sits, and the security page is written to be handed to a client or the firm's IT staff and links the privacy policy, terms and subprocessor list, none of which need a call first.
Court Disclosure Support
If a judge’s standing order requires an AI disclosure, can the product produce one?
Some elements of the record are available, short of a document level export.
Every figure links back to the statement page it came from, sums print their inputs, and exhibits carry the source page on every figure so a lawyer can stand behind them on cross-examination. No record of AI use for disclosure to a court is described.