W×W
AUSTIN, TX --:--:-- CST
← ALL WORK

[ LIVE ] NOV 2026 2-week build DESIGNBUILDAI

Sound Like Me AI × End AI Slop

AI Writing AppClaude · falLaunch Campaign
1 afternoonVoice memo to working app
81%Less editing after training
<$15PSA generation spend
A frame from the End AI Slop PSA. A man sits in silhouette on a couch under a lamp, with the lower third MARCUS, 38, Name changed to protect identity, and the caption It's not just lasagna... it's a statement
END AI SLOP · MARCUS, 38 · ONE OF TEN TESTIMONIALS

Problem

Everyone writes with AI now, and most of it reads the same. The tools that promise to make it sound like you want writing samples first, or they ask to scrape your email. I've never used one. I don't have a clean set of writing I'd want everything based on, and most of my best recent writing started in AI anyway, so it carries some of the habits I'd be trying to remove. What I do have is a lot of edits. I fix AI drafts every day, and the edits are mostly the same ones.

The launch problem was attention. Launch videos all look alike right now, and there are plenty of posts explaining how to make another one. I wanted a launch that would get noticed for being different, show off some of my work, and give me practice with AI video. While researching product names I found that endaislop.com was available, and that turned into a small campaign.

Approach

The product rule was to learn from edits, not samples. That fits how people already work: they generate a draft anywhere, then edit out everything that sounds like AI. It also fits where writing is going, where most things start as an AI draft and the job is getting them into your voice. The edits are the training data, and the user never has to think about training.

I also wanted learning I could inspect. Each user gets their own hypotheses, which become laws as the evidence holds up, and their own banned terms. I'd added banned-word lists to other projects and then found I used some of those words myself, so here a word is only banned if the writer never uses it in a finished draft.

The campaign rule was to keep the product out of it. An ad gets scrolled past. A PSA about AI slop, played completely straight, makes people wonder who's behind it. When they find out it's an app, I'd rather they think that's clever than feel sold to. The campaign is also pro-AI on purpose. The enemy is sounding generic, not using AI, so it can run as a reply to AI-sounding posts without coming off as mean.

What I shipped

The editor and the learning engine

Claude Code turned my voice memo into a brief and a phased build checklist, then built it. The first version took nine phases, from scaffold to a working learning engine and admin dashboard, committed between 2:10 and 5:00 that afternoon. Five more iterations followed over the next two weeks, 137 commits in all. It's Vue 3 with a TipTap editor on Supabase, with Claude doing the AI work from edge functions: Haiku classifies the document, Sonnet writes and learns, and Opus judges each rewrite before you see it. The editor's typography extension is off, because it inserts em dashes and curly quotes on its own and would teach the app habits the writer doesn't have.

The Sound Like Me editor comparing an AI email with the working copy. Struck-through red text shows removed AI phrasing like I hope this email finds you well, Moreover, and an In summary paragraph, and green text shows the replacements, including crew in place of team and contractions like I'd and we'll
THE COMPARE VIEW. EVERY CHANGE BETWEEN THE AI DRAFT AND THE FINISHED VERSION (DEMO WRITER)

When you hit Done, the app compares three versions: the original paste, its own rewrite, and your final. If you undo one of its changes, that counts against the rule that caused it. If you keep a change, the rule behind it gets stronger. Only style edits can create rules, so fixing a wrong date teaches it nothing about your voice. Plain code, not the model, does the counting and promotes or retires rules. The number the whole system is built around is the edit rate, the share of each rewrite you still change.

The Your voice page with two columns. Always lists rules at 96% confidence, such as using crew instead of team, contractions, simple connectors like And instead of Moreover, and cutting summary sentences. Noticing lists two patterns at 75% confidence
YOUR VOICE. LAWS ON THE LEFT, HYPOTHESES IT'S STILL TESTING ON THE RIGHT (DEMO WRITER)

Users see their habits in plain language, under "Always" and "Noticing." Admins see the evidence behind every rule, the cost of every run, and a replay tool that runs past drafts through the current pipeline, so a change to the engine gets measured instead of guessed at.

Training in two short drafts, and testing the samples idea

New users can teach it before their first real paste by fixing short pre-written drafts, which are free and get no rewrite. Each one ends with a card listing what it picked up.

A Nice work modal over a training email reading Draft 1 of 2 done, with a What I learned list: use contractions instead of spelled-out forms, and prefer simple connectors like And or But over Moreover or Furthermore
AFTER THE FIRST TRAINING DRAFT. WHAT IT LEARNED, IN PLAIN LANGUAGE

Learning from edits was the decision I felt surest about, and I still tested it. I ran the real pipeline on a test persona with five specific habits: "crew" instead of "team," contractions, "And" instead of formal connectors, no closing summary, and no "delve." Then I compared fresh accounts on the same new drafts.

First-rewrite edit rate for the test persona (lower is better)
TestNo trainingWriting samplesTraining drafts
Three writing samples vs. three training drafts6.6%4.6%0.0%
Two short training drafts8.5%1.6%

Samples picked up a general voice but missed the personal choices. After three samples, the rewrites still said "team." One run also confirmed my worry about samples: when they still carried AI wording, the learner took that wording as the writer's taste and started preferring words like "thrilled" and "incredible." Training drafts are built around the exact choice points, so they teach the specific habits. These are small runs on a made-up persona, and that's how I read them.

An API, built the morning a beta user asked for one

Feedback from a beta user set the agenda for the November 10 iteration. Most of it was about onboarding, and it led to the shorter training drafts and a first-person welcome screen. It ended with this:

Bonus: make an API. I don't want to go into other tools and definitely don't want to copy and paste. Give me an API so I can pipe directly into my workflow.

I planned that iteration at 9:25 that morning and shipped the API at 10:37. You create a personal key, post a draft, and get it back in your voice through a signed webhook, or you poll for it. Seventeen minutes later I shipped a fix so a webhook address can't be pointed back into the server's own network. It uses the same credits as the app.

The API keys page with a key named Zapier: blog drafts and a quick start showing a curl request that posts a draft to the rewrites endpoint with a webhook URL
API KEYS. SEND A DRAFT FROM N8N, ZAPIER, OR AN AGENT AND GET IT BACK IN YOUR VOICE

The voice also works outside the app. An MCP connector lets Claude and other AI tools sign in, read your voice, and write with it. You can also export your voice as a Claude skill. In a test, the exported skill used as a plain Claude prompt replaced all eight of the persona's "team"s with "crew." A neutral prompt left five.

The brand and the launch video

I designed the brand myself: the SoundLikeMe.AI wordmark, the cursor mark, and an ear icon I ended up using less. The interface is plain on purpose. It looks like ChatGPT or Claude, because that's where people do this kind of writing. The Spectrum color system is the one thing I wanted to stand out. It's a set of six color stops the accent moves through, a small nod to the fact that nobody writes in just one style. The same stops color the app's confetti and the launch video's title cards.

Six title cards from the launch video in six colors, purple, red, orange, olive, green, and blue, reading Make it sound like you, Your voice wherever you write, and the SoundLikeMe.AI wordmark
SPECTRUM. THE APP'S SIX ACCENT COLORS, USED FOR THE VIDEO'S TITLE CARDS

The 30-second launch video is written as code in Remotion. Scripts drive the local app through each scene and record it, with a drawn cursor and typing at a human pace. The writer on screen, Marlowe Finch, is made up, but the account has three weeks of real learning behind it. When the UI changes, I rerun a script instead of re-recording by hand. The music is generated with ElevenLabs Music, and the same footage renders a 16:9 and a 9:16 cut.

THE SOUND LIKE ME LAUNCH VIDEO · 0:30 · BUILT FROM SCRIPTED RECORDINGS OF THE APP

End AI Slop: the PSA

I picked the format from four concepts. The winner, "It Can Happen to Anyone," borrows the anonymous testimony of an after-school special: people in backlit silhouette, a first name and an age in the lower third, confessing to slop. "I said 'delve.' Out loud. At Thanksgiving." Five characters deliver ten testimonials. One character started out as "Karen," and I renamed her Linda, because the meme reads as a jab and the spot has to stay kind.

END AI SLOP · 0:40 · SIX TESTIMONIALS, THE VERSION ON THE SITE'S HOME PAGE

The silhouettes solved the hard parts of AI video. Nobody's mouth is visible, so there's no lip sync to get wrong, and one clip per character can carry any of that character's lines. Five clips cover all ten testimonials, which kept the video budget small and made new versions nearly free. The "identity protected" voice filter suits the era and also hides AI voice artifacts.

A contact sheet of six versions of the same prompt, an older man in a recliner with a dog at his feet in a wood-paneled room, two each from Flux 3, Nano Banana Pro, and Seedream 5 Pro
THE BAKE-OFF. ONE PROMPT FOR GERALD, 67, THROUGH THREE IMAGE MODELS

I tested models before spending on any of them. I ran the same prompt through three image models and picked Nano Banana Pro for the stills, then tried four video models and chose MiniMax for the clips. The VHS look is added in post rather than prompted, which keeps it consistent: a scripted ffmpeg edit grades each scene, adds the tape noise and color bleed, scanlines and closed captions, and mixes the voices, music, and effects. All of the generation happened in one evening and cost about $15 in fal credits across 64 calls, against a $100 budget.

A grid of nine candidate closing shots: a wooden chair under a spotlight, two office chairs at glowing 1980s computer desks, two floral couches, two kitchen tables, and two foggy suburban streets at night
THE CLOSING SHOT. THE SPOTLIT CHAIR, TOP LEFT, WAS REPLACED BY THE DESK, TOP CENTER

The closing shot was the one I changed after the first cut. An empty wooden chair under a spotlight read as an interrogation room. I generated four other settings and went with an empty office chair at a glowing 1980s computer desk. The edit renders 32 files: a hero cut, a cold open, two alternates, a 35-second and a 40-second version, and ten single-testimonial cutdowns, each in 16:9 for X and 9:16 for phones. The cutdowns are made to reply to specific posts. Gerald's "delve" tape goes under a post that says "delve."

endaislop.com

The site is a circa-1998 government campaign page, played straight: beveled gray buttons, Verdana and Times, a scrolling ticker, "Best viewed in Netscape Navigator 4.0 at 800×600," and a hit counter that really counts, stored in Netlify Blobs. It's plain HTML with no build step. A script generates the header mark, tape labels, badges, and the animated GIF banner ads, frame by frame.

The endaislop.com home page: an END AI SLOP header, a row of beveled gray nav buttons with a yellow GET HELP button, a SoundLikeMe.ai banner ad, and a wood-grain CRT TV playing the PSA with DAVE, 34 on screen
HOME. THE PSA PLAYS IN THE TV, MUTED, WITH A TAP-FOR-SOUND BUTTON

Most visitors will come from an X reply on a phone, so sharing is the main feature. The Video Library shelves the ten testimonials as labeled VHS tapes. On a phone, Share opens the native share sheet with the video file attached, so a clip can go straight into a post. On desktop there are 16:9 and 9:16 downloads and a Post to X button.

The Video Library: ten black VHS tapes with handwritten-style labels such as GERALD, 67, delve and MARCUS, 38, lasagna, next to a 120 by 600 skyscraper ad for Sound Like Me reading Teach any AI to write like YOU
THE VIDEO LIBRARY. ONE TAPE PER TESTIMONIAL, EACH ONE SHAREABLE

Warning Signs is a tri-fold pamphlet for the refrigerator ("Their grocery list has a wrap-up paragraph"), and Our Mission makes the pro-AI case with an FAQ for parents and educators.

The Warning Signs page: a cream tri-fold pamphlet headed KNOW THE WARNING SIGNS in red, with a still of Gerald and lists under WATCH FOR and ALSO WATCH FOR, such as They delve in and Every reply begins with Great question
WARNING SIGNS. A PAMPHLET FOR THE FAMILY COMPUTER

The product only shows up in four places, all of them in period: the banner ads, a sponsor line ("This public service announcement was made possible by SoundLikeMe.ai"), a card that fills the TV when a tape ends, and the Get Help page. Get Help is the way out to the product, written as a four-step recovery program.

The Get Help page: a box reading Recovery is possible, then The Program, four numbered steps: keep using your AI, paste it into Sound Like Me, edit until it sounds like you, and take your voice with you
GET HELP. THE ONE PAGE THAT NAMES THE PRODUCT

The disclosure line: marketing inside the product

A campaign gets attention once. I also wanted something that keeps spreading for as long as people use the app. It started in a launch brainstorm as a badge, like "Sent from my iPhone." But a badge only works on a web page, and most writing isn't one. Meanwhile more platforms, publishers and journals are landing on the same rule: it's fine to write with AI, just say so. So the badge became a line of plain text that works at the bottom of an email, a Slack message, or a LinkedIn post.

Writers can turn on a disclosure line, and the app adds it to the end of what they copy: "Drafted with AI and edited with Sound Like Me AI to sound like me," in a full, short, footer, or inline style. It's off by default, so it's something the writer chooses to say and never a watermark. The wording follows how the text was made, so it's always true. Text edited in the app gets one version, text another AI tool wrote from your exported voice gets another, and a doc you typed from scratch gets no line at all. The API returns the line as its own field, so it never breaks a pipeline that processes the text, and the MCP connector and voice export carry it too. If a finished text comes back with the line still on it, the app strips it before learning, so it never counts as an edit.

The soundlikeme.ai AI disclosure guide showing two tables of lines with Copy buttons. Lines for text edited with Sound Like Me AI in full, short, footer, and inline styles, such as Drafted with AI and edited with Sound Like Me AI to sound like me, and lines for text another AI tool wrote using an exported voice
SOUNDLIKEME.AI/AI-DISCLOSURE. THE SAME LINES THE APP ADDS, READY TO COPY

The hard call was the link. The line names the product but doesn't link to it. A link reads as an ad, and people would switch it off. A named tool reads as honest disclosure. Most of these lines will end up in email and DMs, where a link does nothing for search anyway, and writers who publish on the web can choose to link the name. The trade-off is that the name has to be findable on its own, so searching "Sound Like Me AI" needs to lead to the site.

The line comes with a public guide at soundlikeme.ai/ai-disclosure: why to disclose, who's asking for it, when to do it, and lines anyone can copy for any AI tool, not only mine. It also answers the obvious question, "if it sounds like me, why disclose?" Disclosure covers honesty, and your voice covers quality. A disclosed email can still read like every other AI email, and an email that sounds like you shouldn't have to hide where it started.

Outcome

Sound Like Me AI runs at soundlikeme.ai with training, the API, the MCP connector, voice export, and the disclosure line, and every edit a user makes adds evidence to their own rules. The campaign was finished in every format it needs before launch: the 40-second PSA, ten single-testimonial cutdowns in 16:9 and 9:16, the launch video, and endaislop.com to share them from. Each cutdown answers a specific kind of slop, so the campaign can keep running as replies for as long as people keep writing "delve."