# Don't Get Sued: a pre-launch legal-risk gate for AI-built apps and agents > A read-only agent gate for the fourteen legal risks that hit small builders most: marketing texts and email, trackers before consent, accessibility, kids' data, biometrics, plain-text personal data, AI disclosure, AI claims you cannot prove, takedowns, policies that do not match the product, renewals and refunds, licenses, and agents that act for users. Evidence rule, gate register, seeded test app, 12 prompts, counsel packet. Not legal advice. - URL: https://paperchasewebb.ai/bots/marketplace/items/dont-get-sued-pre-launch-legal-risk-gate-for-ai-built-apps/ - Type: Prompt pack - Category: Vibe coding - By: PaperChaseWebb - Works with: Claude Code, Codex, Claude, Grok Bot, Hermes, ChatGPT (named in the listing); Plain .md - Price: $29 USD - Difficulty: Intermediate - Setup time: 1 hr 30 min - Time to result: About 90 minutes for one product, then a rerun after any change to sign-up, payments, messaging, tracking or AI features - Format: Markdown (.md) file, dont-get-sued-pre-launch-legal-risk-gate-for-ai-built-apps.md - Version: 1.0, updated 2026-10-27 - License: Personal and commercial use inside your own business, including gates you run for your own clients. Do not resell, republish or share this file. ## What you end up with Before launch, every risk area that applies to your app ends as pass with evidence, a fix, a signed and dated exception, or a question for a lawyer, and you have a one-page gate report that says launch or hold. ## What you get - 17 sections in one .md file - Eight scope questions that decide which checks apply - Fourteen risk areas, each with the usual place to read, what the agent checks, the usual fix and the evidence to keep - A rules block that keeps the agent read-only and bans "compliant" - The evidence rule and a gate register with four outcomes - 12 copy-paste prompts with harness notes for Grok Bot, Claude Code, Codex and Hermes - A seeded test app with nine expected findings, and quick searches - A counsel packet prompt for your lawyer - A failure table and an illustrative worked example - A competitor teardown and credited sources ## Who it is for Builders and agencies about to launch something made with an AI coding agent, who want the common legal risks found and decided before launch rather than after a demand letter. ## Tools needed - Grok Bot, Claude Code, Codex or Hermes: reads your code and pages read-only and reports findings with file and line - Claude or ChatGPT: optional: every prompt also works with page text pasted in - A /gate folder in your project: holds the findings, evidence, register and gate report - You need: An app, site or agent you are about to launch, with its code or pages - You need: One person who can decide each register line and sign the gate report Cost to run: The pack is the only purchase. Uses the agent harness you already have. A lawyer's time for counsel lines is separate. ## How it works 1. **Scope.** Answer the eight scope questions with prompt 1. A no removes areas. Expected: The list of areas that apply, and any straight-to-counsel lines. 2. **Test the gate.** Run it on the seeded test app in section 9 first. Expected: All nine expected findings, no edits, no "compliant". 3. **Map and check.** Prompt 2 builds the data map from your code; prompts 3 to 10 check each area. Expected: Findings with file and line, or "cannot see" with what to check by hand. 4. **Decide.** Fill the gate register: pass with evidence, fix, signed exception, or counsel. Expected: One outcome per area, every exception named and dated. 5. **Report and sign.** Prompt 11 writes the counsel packet; prompt 12 writes the gate report. A person signs. Expected: LAUNCH, LAUNCH WITH EXCEPTIONS, or HOLD. ## Sample prompt: Claims audit (Grok Bot, Claude Code, Codex, Hermes) ``` Read [pages, listings, ads, deck]. List every claim about what the product does or what users get. Sort each: describes a feature, describes a result, describes the future. For each, name the evidence on file or write "none". Draft a plainer version of every claim with no evidence. Never add a number we cannot prove. ``` Prompt 9 of 12. Runs after the rules block in section 3. ## Sample prompt: Gate report (Grok Bot, Claude Code, Codex, Hermes) ``` Write one page: the register with every outcome, open fixes with owners, exceptions with who signed and the look-again date, counsel lines with the answer filed or "waiting". Final line: LAUNCH, LAUNCH WITH EXCEPTIONS, or HOLD, by the launch rule. Leave the signature line blank. ``` Prompt 12 of 12. A person signs, never the agent. ## Free preview of dont-get-sued-pre-launch-legal-risk-gate-for-ai-built-apps.md ````markdown # Don't Get Sued: a pre-launch legal-risk gate for AI-built apps and agents A pre-launch gate by PaperChaseWebb for solo builders, small teams and agencies who build apps, sites and AI agents with Claude Code, Codex, Grok Bot or Hermes. Fourteen risk areas that hit small builders most often (marketing texts, marketing email, tracking before consent, accessibility, kids' data, biometrics, plain-text personal data, AI disclosure, AI claims you cannot prove, policies that do not match the product, subscriptions and refunds, user uploads, licenses, and agents that act for users), a read-only agent that finds them in your code and pages, an evidence rule, a gate register where every line is pass, fix, signed exception or counsel, a seeded test app with expected findings, 12 prompts with harness notes, and a counsel packet so an hour with a lawyer goes on the hard questions. Plain .md. Version 1.0, 2026-10-27. Works with Grok Bot, Claude Code, Codex and Hermes, and pastes into Claude or ChatGPT. **This is not legal advice.** It is a checklist and a method for finding risk before launch. It names the laws that usually sit behind each risk so you know where to read and what to ask, but it does not say what any law requires of your product, and it never tells you that you are compliant. Laws differ by country and state and they change. Anything the gate marks "counsel" goes to a qualified lawyer before launch. ## Contents 1. Who this is for, and what it does 2. How to run it: one ```` ## Worth knowing - Not legal advice. The laws named are where a lawyer would usually start reading, not a statement of what they require of your product. Have every counsel line answered by a qualified lawyer. - The gate never tells you that you are compliant. It finds risk and records your decisions. - The worked example is invented. It is not a client and nothing in it is a legal conclusion. - On 2026-10-27 the seeded test app was built and the quick searches returned every expected hit; the prompts were walked through against it as a design check. Run the seeded app in your own harness first. ## Questions **Is this legal advice?** No. It is a method for finding common risks and recording decisions before launch. Anything that depends on reading a law closely is marked counsel and goes to a lawyer, with a short packet so the hour goes on the hard questions. **Will the agent change my code or policies?** No. The rules block keeps it read-only. It may draft fixes as patch files and draft policy text for you to edit; a person applies and publishes everything. **Which countries does it cover?** It is written for US builders first, with notes for EU, UK and California users where the usual checks differ. The scope questions decide which areas apply to you. **How is it different from a security checklist?** Security checklists cover code. This covers what small builders actually get letters about: messaging consent, trackers, accessibility, kids' data, AI disclosure, claims, renewals and refunds. Pair it with Pre-launch security prompts for the code side. **Which tools does it work with?** Grok Bot, Claude Code, Codex and Hermes, with harness notes for each. Every prompt also works with page text pasted into Claude or ChatGPT. ## How to buy $29 one time at https://paperchasewebb.ai/bots/marketplace/items/dont-get-sued-pre-launch-legal-risk-gate-for-ai-built-apps/. Stripe checkout, then an instant download page; the download link is also in your emailed receipt. Seller: PaperChaseWebb Inc., mgmt@paperchasewebb.com