HomeAI Detector › For Paralegals

AI Detector built for paralegals, legal assistants, and document review teams, calibrated for supervised legal drafting.

Pre-scan every memo, demand letter, NDA, discovery summary, deposition prep doc, and citation check before it reaches the supervising attorney. Sentence-level highlights show exactly which lines read AI on recitals, fact narratives, application paragraphs, and newly drafted clauses. Calibrated for the formal register and IRAC structure of paralegal work product. Aware of unauthorized practice of law limits: TextSight is a workflow hygiene tool, never a substitute for attorney review or legal advice. No training on submitted drafts. Free to try. No card.

Start free, no card See pricing
Pro at $19.99/mo, $14.99 yearly Attorney-supervised workflow 90-day matter history
Who it is for

Built for paralegals, legal assistants, and document review teams.

Litigation paralegals, transactional paralegals, in-house legal-ops staff, contract administrators, and document review attorneys all face the same question by 2026: did this draft pass through an AI tool before it reached the supervising attorney, and can the firm defend the work product if a client or a court later asks. The pre-handoff scan is the cheapest answer that fits inside the supervision chain.

Paralegal work product runs from the demand letter to the privilege log narrative to the deposition prep memo. Pre-scanning fits every drafting stage because supervising attorneys, opposing counsel, partners, and sophisticated clients now read with the AI question in mind, and the supervising attorney owns the Rule 5.3 duty to direct non-lawyer staff using AI tools on a matter.

Litigation paralegals

Litigation paralegals draft the first cut of motions, briefs, demand letters, and discovery responses under associate or partner supervision. AI assistance has crept into routine drafting tasks during 2024 and 2025: case summaries, fact recitations, deposition prep memos, and citation explanations. The pre-handoff scan catches AI-shaped phrasing in narrative sections before the supervising attorney reads the draft and before the partner signs anything under their name.

Transactional and in-house legal assistants

Transactional paralegals prepare NDA first drafts, contract addenda, closing checklists, and corporate filings. In-house legal assistants run policy summaries, contract redlines, and internal client memos that feed the GC and the business stakeholders. Both roles routinely lean on AI for stock clauses and recital sections; both roles need the residue-check before handing the draft up the supervision chain.

Document review and discovery teams

Document review attorneys and discovery paralegals work on Relativity, Disco, Everlaw, and Reveal platforms. The detector is not a review-platform integration; it sits next to the work product around the review itself: the deposition prep memo, the discovery summary, the privilege log narrative, and the production cover letter. Business tier API access supports lightweight integration where firms want to push drafted memos through detection before they reach the supervising attorney.

UPL and attorney supervision

Unauthorized practice of law limits, and the duty to supervise.

Every US jurisdiction prohibits non-attorneys from giving legal advice, accepting cases, setting fees, or signing pleadings. Paralegals work under the supervising attorney's direction, and the attorney owns Rule 5.3 supervision duties for any non-lawyer using AI tools on a matter. TextSight is a workflow hygiene tool that sits inside that supervision chain, never above it.

What unauthorized practice of law actually prohibits

Unauthorized practice of law restrictions in every state prohibit non-attorneys from giving legal advice to clients, accepting cases on behalf of a firm, setting legal fees, signing pleadings, or appearing in court except where specific authorisation exists. The line is not blurred by AI tools. A paralegal who runs a scan and rewrites a sentence is doing drafting work, not advising. A paralegal who tells a client what the contract means crosses the line whether AI was involved or not. TextSight does not change the UPL framework; it operates inside it.

Rule 5.3: the supervising attorney's duty over non-lawyer staff

ABA Model Rule 5.3 makes the supervising attorney responsible for the conduct of non-lawyer assistants, including paralegals, contract reviewers, and document subscribers using AI on a matter. The attorney's duty is to ensure the assistant's work is compatible with the lawyer's own professional obligations under Rules 1.1 competence, 1.6 confidentiality, and 3.3 candor. Pre-handoff detector scanning supports the supervision chain by surfacing AI residue before the attorney's own review, which makes the attorney's Rule 5.3 oversight efficient rather than reactive.

NALA and NFPA certification context

The NALA Code of Ethics and Professional Responsibility and the NFPA Model Code of Ethics and Professional Responsibility both reinforce the same principles: paralegals work under attorney supervision, do not give legal advice, maintain client confidentiality, and disclose their non-attorney status to clients and third parties. Both codes are silent on AI tools by name, but the supervision principle covers them by extension. Certified paralegals through NALA's CP or NFPA's RP and PACE-Registered designations operate inside the same framework, and detector scanning fits without modification.

State bar paralegal regulation variation

State bar paralegal regulation varies widely. California, Florida, North Carolina, and several other states have specific paralegal definitions and supervised-status requirements. Texas, Ohio, and Illinois treat paralegals as part of the supervising attorney's professional responsibility chain without a separate registration. Some states allow limited licensed paralegals (LLLT in Washington, LLP in Utah) to perform circumscribed advisory work; even there, AI tools sit inside the limited license framework. Confirm the rules in every jurisdiction where you work, and align tool use with the firm's written policy.

Why this matters for AI tools specifically

Detector scanning supports UPL compliance by reinforcing the supervised-drafting model: paralegal drafts, supervising attorney reviews and signs, firm bills the work. The scan surfaces AI-shaped passages before the attorney review so the attorney sees what residue, if any, made it into the draft. The professional judgment on whether the final document is fit to send remains with the supervising attorney; the scan provides the visibility, not the decision.

Plans & pricing

Pricing for solo paralegals, firms, and legal-ops teams.

Pro at $19.99 a month standard, $14.99 a month on yearly billing, fits solo paralegals and legal assistants. Business at $39.99 a month, or $29.99 a month on yearly, fits in-house paralegal pods, legal-ops groups, and document review teams with 5 seats. Full details on the pricing page.

Free
$0/forever

 

Sample a short memo, demand letter, or NDA recital section.
  • 3 scans / day
  • 5,000 chars per scan
  • Sentence-level highlights
  • 2 lifetime AI rewriter uses
Start free
Starter
$7.49/month

Billed $89.88/year — Save $30

For a paralegal or legal assistant running a few documents per week.
  • 20 scans / day
  • 20,000 AI rewriter words/mo
  • Chrome extension
  • Email support
Get Starter
Business
$29.99/month

Billed $359.88/year — Save $120

For legal-ops pods, document review teams, and in-house paralegal groups.
  • 100,000 AI rewriter words/mo
  • 5 team seats, shared history
  • Audit log, REST API
  • White-label PDFs
Get Business

Most paralegals see Pro pay for itself the first time a flagged memo or demand letter gets caught and rewritten upstream rather than coming back from the supervising attorney for revision. View full pricing →

Document genres

Memos, demand letters, NDAs, discovery summaries, deposition prep, and citation explanations.

Every paralegal document genre carries a distinct AI risk profile and a distinct calibration target. The headline score on an NDA recital is not the headline score on a deposition prep memo, and the editing posture differs accordingly. Read the sentence map by section type, not the single percentage across the document.

Internal memos and case briefs

Internal memos summarising case law, deposition transcripts, or discovery production are common AI tasks because input volume is large and output format is consistent. The risk is the memo inheriting the model's hedging cadence and tidy parallel structure, then becoming the input for the supervising associate or partner. Pre-scan the memo before it leaves the paralegal's hands, focus the rewrite on the analysis paragraphs, and leave the case citations in their reporter-standard form.

Demand letters and routine client correspondence

Routine demand letters for breach of contract, unpaid invoices, or consumer disputes are commonly AI-assisted at the first-draft stage. The recitation of facts and the description of the breach often retain LLM phrasing patterns; the remedy paragraph and deadline are usually fine because the language is fixed. The narrative paragraphs are where AI residue concentrates and where the rewrite focus belongs.

NDAs, contract addenda, and clause libraries

NDAs are the canonical template document. Paralegals routinely use ChatGPT or in-firm AI tools to draft first versions, then revise against the firm's preferred clauses. The risk concentrates in mutual-NDA recitals, custom confidentiality definitions, and newly drafted addenda for data processing, AI use disclosure, or ESG provisions. Settled boilerplate (severability, choice of law, notice) scores low regardless and is rarely the editing target.

Discovery summaries and deposition prep

Discovery summaries, document production cover letters, deposition outlines, and witness prep memos are paralegal work product that sits next to the document review platform rather than inside it. AI assistance often enters at the summarisation step where input volume is large. The pre-handoff scan catches residue in the narrative summaries before the supervising attorney runs the deposition or files the cover letter.

Citation explanations and research narratives

AI-generated case citations are a known accuracy risk; even verified citations carry AI signal in the surrounding explanatory prose. Verify every citation independently against an authoritative reporter or research platform, and rewrite the explanation in your own voice. The Mata v. Avianca sanctions made the consequence of skipping citation verification stark, and the supervising attorney owns the final accuracy duty under Rule 3.3 candor.

Pre-handoff workflow

Scan before the supervising attorney sees the draft, and before the partner signs.

Most paralegal work product clears three checks before it reaches the client or the tribunal: the paralegal's own pass, the supervising attorney review, and the partner sign-off on the consolidated document. The pre-handoff scan fits before the first attorney review so the version the attorney reads is already AI-clean.

Step 1: draft using firm-approved tools

Build the first version using your firm's approved drafting tools and templates. If AI is part of the workflow under firm policy, use it as an aide for structure and first-pass prose. Always retype and edit anything from an AI suggestion so the voice lands in your own hands rather than the model's hands. Working outside the firm's stock template on new clauses or addenda is where AI residue most often leaks in.

Step 2: verify every citation independently

Before the AI scan, verify every citation against an authoritative reporter or research platform: Westlaw, Lexis, Bloomberg Law, the underlying federal reporter, or the state equivalent. Detection does not verify citations; that check sits on its own track and is the non-negotiable step before the document leaves the supervising attorney. The paralegal owns the citation verification step; the supervising attorney owns the final accuracy duty under Rule 3.3.

Step 3: paste and scan section by section

Open app.textsight.ai, paste each section, and scan. Free tier handles 5,000 characters in one paste. Pro handles 10,000, which fits a typical demand letter, a memo section, or a long contract clause. For a 20-page brief or deposition prep packet, split by section: facts, analysis, application, conclusion. The scan returns in well under a minute with an Authenticity Score and a sentence-by-sentence colour map.

Step 4: rewrite reds in your own voice

Rewrite flagged sentences in your own voice while preserving legal precision, defined terms, and citation accuracy. A memo or demand letter typically needs three to eight sentence rewrites to move from a 65 score into the 85 range. The sentence map tells you which lines need attention; the headline score confirms the rewrite landed. Required legal phrasing such as defined terms and boilerplate is the false-positive class to leave alone.

Step 5: hand the draft to the supervising attorney

Send the revised draft to the supervising attorney for substantive review. Pro history keeps every section scan for 90 days for the matter file. PDF export gives the firm a contemporaneous record of the pre-handoff check. A typical demand letter round-trips in about fifteen minutes; a deposition prep packet in about forty-five. The attorney's own scan now reads cleanly the first time, which is where most paralegals see the tier pay for itself.

Document review at scale

e-Discovery, Relativity, Disco, Everlaw, and the prose work product around the review.

Document review on Relativity, Disco, Everlaw, and Reveal centres on responsiveness coding and privilege review, not AI detection on the produced documents. Where TextSight fits is the prose work product around the review: deposition prep, discovery summaries, privilege log narratives, and production cover letters. Business tier API supports lightweight integration for legal-ops teams pushing drafted memos through detection before they reach the supervising attorney.

Discovery summaries and production cover letters

Discovery summaries and production cover letters are paralegal work product that travels to opposing counsel and the court. AI assistance enters at the summarisation step because input volume is large and the output format is consistent. Pre-handoff scanning catches AI-shaped phrasing in the narrative paragraphs before the document goes out under the firm's name. The cover letter signature line is the supervising attorney's; the responsibility for the prose under it is shared.

Privilege log narratives and Bates-stamp explanations

Privilege log entries and Bates-stamp explanations need a level of precision that AI tools handle inconsistently. The privilege description column is the highest-risk field: a hedging or hallucinated description can become a privilege waiver problem under Rule 502 in federal litigation. Pre-handoff scanning catches obvious AI residue, but the privilege judgement itself is the supervising attorney's call. Detector scanning never substitutes for the privilege review.

Deposition prep memos and witness outlines

Deposition prep memos and witness outlines are heavy AI-assistance candidates because the input includes thousands of pages of transcripts, exhibits, and prior depositions. The risk is the memo inheriting the model's hedging cadence and parallel structure. The supervising attorney walks into the deposition with the memo in hand; the memo needs to read in the attorney's voice, not the model's. Pre-scanning the memo before the attorney reads it makes the deposition prep efficient.

Legal-ops API integration on Business tier

Business tier with REST API access supports lightweight integration where legal-ops teams want to push drafted memos through detection before they reach the supervising attorney. The audit log captures who scanned what and when, which fits the contemporaneous-record expectation under federal preservation rules. Shared scan history on 5 seats lets the supervising attorney, the lead paralegal, and the document review team see the same Authenticity Score and flagged sentences.

Client trust and firm AI policy

Clients ask the AI question directly, and firm policies are real.

Sophisticated corporate and litigation clients increasingly ask, in writing, whether AI was used to draft the documents they paid for. The answer needs to be accurate and consistent across the paralegal, the supervising attorney, and the firm's billing description. Firm AI policies are real and enforced; pre-handoff scanning fits inside both the disclosure layer and the policy layer.

Why clients lose confidence in AI-shaped letters

Clients pay for an attorney's professional judgment delivered through paralegal-supported drafting, not for prose generation. A demand letter or memo that reads as AI-shaped sends the implicit signal that the firm did not engage with the matter, regardless of how much substantive work happened upstream of the writing. The signal is wrong in most cases but the perception sticks. Pre-handoff scanning is the lowest-cost client-retention investment available to a drafting paralegal.

Firm AI policy patterns in 2026

Most mid-market and large firms now have written AI use policies. Common patterns include: disclosure to clients when generative AI assisted a draft, outright prohibition on specific document categories such as court filings or regulatory submissions, an extra partner review step for AI-assisted drafts, and rules against including client matter details when running drafts through external AI tools. Read your firm's policy in full before relying on either AI drafting or detector scanning, and confirm with the supervising attorney on the practice group.

Sophisticated client AI disclosure requirements

Several large corporate legal departments now require outside-counsel firms to disclose AI use on any work product billed at the partner rate or above. The exact form varies: some clients ask for a line item on the engagement letter, others ask for a per-matter disclosure, and a smaller group requires per-document disclosure with the detector scan attached. The pre-handoff scan history on TextSight gives the firm a contemporaneous evidence trail supporting whatever disclosure the client requires.

Shared scan threshold on Business tier

Business tier with 5 seats and shared history lets the supervising attorney, the lead associate, the contract reviewer, and the paralegal all see the same scan and flagged sentences. The Authenticity Score becomes the team threshold rather than a per-author judgment. The audit log records who scanned what and when, which is useful when a junior paralegal delivers a section that flags higher than the rest of the brief and the supervising attorney needs to see the chain.

Your client matter stays yours

Privilege-aware: no training on submitted text, redaction is the safe default.

Legal work is privileged and Rule 1.6 confidentiality duties apply to every third-party tool in the workflow. The supervising attorney owns the Rule 1.6 decision for the matter; TextSight is designed to fit inside whatever rule the attorney sets. For privileged matters, the firm IT and the bar guidance for every jurisdiction where the supervising attorney practices are the binding context, not this page.

No training on submitted drafts

Memos, demand letters, NDAs, discovery summaries, deposition prep, and citation explanations submitted for scanning are never used to train the classifier or any other model. This is a contract clause, not a configuration toggle. It applies on the free tier the same way it applies on Pro and Business. The scan runs against the existing model and returns a score and sentence highlights without feeding the training pipeline.

Redaction is the safe default for privileged content

Many firms allow paralegal detector use on redacted drafts where party names, matter numbers, addresses, dollar figures, and confidential facts are replaced with placeholders. The detector reads prose cadence, not party identity, so redaction does not affect the score. For privileged matters and any matter under a protective order, confirm with the supervising attorney or firm IT before pasting any content into a third-party tool.

Retention you control

Free tier scans are not stored beyond the result session. Pro tier history is retained for 90 days; individual scans are deletable on request. Business tier offers configurable retention with team controls and a standard DPA on request for in-house procurement. Match the tier to the firm's external-tool retention policy, and align retention settings with the bar guidance for every jurisdiction where the supervising attorney practices.

Consult the supervising attorney and firm IT

None of this page is legal advice and none of it substitutes for the bar guidance issued by the jurisdictions where the supervising attorney is admitted. Before using any third-party detector on client matter, confirm with the supervising attorney, firm risk teams, and firm IT. The professional judgments on competence, confidentiality, candor, and supervision remain with the attorney of record. TextSight is a workflow hygiene tool that operates inside the supervised drafting chain, never above it.

FAQ

Paralegals frequently ask.

Does using TextSight cross the unauthorized practice of law line?
No. TextSight is a workflow tool that reads prose cadence and returns an AI-likelihood score with sentence-level highlights. It does not give legal advice, draft legal conclusions, or substitute for attorney review. Unauthorized practice of law restrictions in every US jurisdiction prohibit paralegals from advising clients, setting fees, accepting cases, or signing pleadings. TextSight does none of those things. It is a drafting hygiene check, similar to a grammar tool, that runs before the supervising attorney reviews the work product.
Will a case brief or memo flag as AI just because legal writing is formal?
Sometimes, yes. Legal writing uses a formal register, prescribed IRAC structure, defined terms that recur across documents, and settled boilerplate clauses. These features overlap with patterns detectors associate with AI prose. A fully human case brief can land in the 50 to 70 band simply because of the genre. The sentence-level highlights are the diagnostic that matters. You see which sentences flag, decide whether they reflect required legal phrasing such as defined terms or boilerplate, and rewrite only the lines that read AI-shaped without breaking citation accuracy or legal precision.
How does TextSight handle confidentiality on client matter and privileged drafts?
Drafts submitted for scanning are never used to train the classifier or any other model. This is a contract clause, not a configuration toggle. That said, the supervising attorney owns the Rule 1.6 confidentiality decision for the matter. Many firms allow paralegal detector use on redacted drafts where party names, matter numbers, and privileged content are replaced with placeholders. Others permit full text only on an approved-tools list. Treat the scan step like any cloud workflow and confirm with the supervising attorney before pasting client matter.
Do I need to disclose detector use to the attorney reviewing my work?
Most firms treat detector scanning as part of normal drafting hygiene, similar to grammar checks and citation verification, and it does not require separate disclosure. What does need disclosure is the underlying use of generative AI to produce the draft. Many firms now require paralegals to flag when AI assisted a draft so the supervising attorney can review with full context under Rule 5.3 supervision duties. Consult your firm's AI policy or speak with the partner who owns the practice group before relying on either workflow.
Which tier fits a paralegal at a small firm versus a legal-ops team?
Pro at $19.99 a month, or $14.99 a month on yearly billing, fits solo paralegals and legal assistants running 20 to 50 memos, demand letters, or NDAs a week with 10,000 character pastes, unlimited scans, 90-day history, and PDF export for the matter file. Business at $39.99 a month, or $29.99 a month on yearly, fits legal-ops teams, in-house paralegal pods, and document review groups with 5 seats, shared history, audit log, REST API for integration with Relativity or Disco, and white-label PDFs. One avoided revision cycle on a brief or contract covers either tier.
How does this fit with NALA or NFPA certification standards?
NALA Code of Ethics and the NFPA Model Code of Ethics both reinforce the same principles: paralegals work under attorney supervision, do not give legal advice, maintain client confidentiality, and disclose their non-attorney status. TextSight is a drafting hygiene tool that sits inside the supervised workflow. Pre-handoff scanning supports certification standards by surfacing AI residue before the supervising attorney reviews, which strengthens the supervision chain rather than weakening it. The certification standards themselves are the binding rules; this page does not substitute for them.
Can a flagged section actually delay attorney sign-off on a routine document?
It can. When a supervising attorney runs a draft through their own scan and sees a high AI score on a memo or demand letter, the typical response is to send the document back for revision before signing. That round trip costs you a billing cycle and the attorney's review time. Pre-handoff scanning lets you fix flagged sentences upfront so the attorney's own scan reads cleanly the first time. The result is fewer revision cycles and faster turnaround on routine drafting work, which is where most paralegals see the tier pay for itself.
Does this work for document review on Relativity, Disco, or Everlaw?
TextSight is a prose-cadence detector, not a review platform integration. Document review on Relativity, Disco, Everlaw, and Reveal centers on responsiveness coding and privilege review, not AI detection on the produced documents. Where TextSight fits in the discovery workflow is the deposition prep memo, the discovery summary, the privilege log narrative, and the production cover letter; the drafted work product around the review itself. Business tier API access supports lightweight integration where firms want to push drafted memos through detection before they reach the supervising attorney.
Related

More for paralegals and legal teams.

Pre-scan every memo, demand letter, and discovery summary. Hand off clean.

Free to try. No card. Pro at $19.99/mo, or $14.99/mo on yearly. Business with 5 seats for legal-ops teams and document review groups.

Start free, no card See pricing
Attorney-supervised workflow · No training on submitted drafts · UPL aware, NALA and NFPA compatible · Workflow tool, never a substitute for attorney review