Pre-send ritual

Before you send the letter

Not legal advice. This page is not a substitute for a licensed attorney, firm process, research, or your judgment. It describes a product ritual for hole-finding on a draft you already wrote. Nothing here creates an attorney-client relationship.

Evening desk light. A lawyer or founder has the PDF open beside a thread of AI suggestions that made the letter feel finished: cleaner facts, a firmer deadline, a closing that sounds inevitable. The recipient has not seen it. The cursor sits on Send. That is the moment this page is for.

People searching demand-letter checklists usually get delivery method, exhibits, and tone advice. Those matter. This page is narrower. It treats the letter (demand, notice, hard founder email, settlement outline) as a social object that will be read by the other side, and sometimes by a judge later, and it is about pressure-testing the AI-shaped draft before the message leaves.

pingpong is a sequential review product for that ritual. Default chain: Grok, then Perplexity, then ChatGPT, then Gemini, then Claude. The first model drafts. Each later model sees your question, the prior answers, and a review frame that can agree, correct, restructure, or reject a weak premise. Brand: pingpong at pingpongit.com. Not getpingpong.ai.

Definition: What is pingpong. Mechanism: How it works. Counsel role page: For lawyers. Founder role page: For founders. First run: How to run a pingpong.

Your first eligible web review is free. When you need more, web Plus is $19.99/month and web Pro is $124.99/month. On iOS the listing shows three free pingpongs, then Plus at $24.99/month or Pro at $59.99/month. Start the free web review on pingpongit.com, then open Plans when you are ready for Plus or Pro. Full table: pricing.

Why a letter is a different kind of commit

A memo to yourself is cheap to rewrite. A letter that names amounts, deadlines, and alleged facts is not. Once the other side reads it, the language becomes an exhibit in the story they tell their counsel, their insurer, and sometimes a court. Softening a claim later looks like retreat. Overclaiming in the first send trains the recipient to discount everything that follows.

People often ask one model to "tighten the demand" or "make this more professional." The model returns calmer prose and a short risk list that preserves the original bet. Socially pleasant. Thin when the next action is Send. Related habit for irreversible moves in general: Catch AI mistakes before you commit.

What usually hides in the draft

The dangerous parts are rarely typos. They are soft premises dressed as conclusions. A damages number that does not reconcile to the attached invoices. A deadline that ignores a contractual notice-and-cure window. A recipient name that matches a brand, not the legal entity. A threat of consequence you will not actually pursue. A "facts" paragraph that quietly invents a meeting nobody can prove. An admission that feels like candor and later becomes a problem.

One chatbot grading its own draft rarely catches that pattern. It softens edges and keeps the structure. Later labs, reading a concrete draft without being told to flatter you, are a different social object. Framing: AI second opinion. Sycophancy angle: Debias AI and sycophancy research.

How the five-model handoff works on a letter

Paste one clear question, not a vibe. Example shape: "We plan to send this demand letter to RECIPIENT by METHOD on DATE, demanding AMOUNT by DEADLINE, based on the attached chronology and exhibits. Where is this weak, overclaimed, or incomplete before Send?" Attach the draft and the source record when you can.

Grok goes first. Perplexity reviews with that draft in view. ChatGPT, Gemini, and Claude follow in order. Each pass can keep, fix, or refuse. You get a final answer and can open earlier passes. The product bet is not that five models invent the right legal strategy. It is that skipped edge cases and soft premises are harder to ship unnoticed when later labs have to look at them.

Architecture: Sequential vs parallel AI. Category map: Multi-model AI review. Fair single-model contrast: pingpong vs ChatGPT.

What to listen for in the middle passes

Treat independent convergence as a stronger signal than polite agreement. If three later models keep challenging the same clause (wrong entity, unsupported damages math, deadline that conflicts with the contract, tone that reads as threat rather than demand), that clause is your checklist, not a reason to force a synthetic consensus.

Treat unresolved split the same way. One model may want a softer ask; another may want another exhibit before any send. You still decide. pingpong does not replace counsel, research, or firm review. It pressure-tests the AI-shaped draft you were about to trust.

Decision reliability framing (not uptime SLAs): Extreme reliability. Clarification of the "insurance" metaphor: Decision insurance.

When to skip the chain

Skip it for exploratory outlines, internal brainstorms, and early drafts nobody will see. One strong model is enough when being wrong costs almost nothing. Save the free eligible review for the letter that is hours from the other side's inbox. Role pages if the decision is not yours alone: lawyers, founders, executives, teams.

Related commits

Cluster hub: before you commit. Same handoff, other irreversible moves: before you change pricing, before you hire, before you reply to the board, before you sign the contract (not legal advice), before you launch, before you post, before you let someone go (not HR or legal advice), before you partner (not legal advice). Pattern page: catch AI mistakes before you commit. Chooser: when to use pingpong. Continue on Plus or Pro.

Plans

Your first eligible web review is free. Further web reviews need a subscription. Web Plus is $19.99/month. Web Pro is $124.99/month. iOS lists three free pingpongs, Plus at $24.99/month, and Pro at $59.99/month (yearly options appear on the App Store). Confirm the live plan at checkout. Details: plans and pricing. Related: Is pingpong worth it.

Run it before Send

Take the draft, the exhibits, and the send plan you almost executed. Restate them as one decision question. Run the default pingpong order once. Keep what survives. Fix what later models break. Escalate what they cannot settle to a human who owns the matter. Start with the free eligible web review on pingpongit.com. If the chain earns a place before your next irreversible send, choose Plus or Pro under Plans (web Plus $19.99, web Pro $124.99; iOS Plus $24.99, Pro $59.99). Or start on the App Store.

Again: not legal advice. Not medical or financial advice either. Hole-finding on your draft is not a substitute for counsel.