Built for the moment you've been deleting & retyping for ten minutes.

100 ways to say I’m sorry — in 30 seconds.

Tell us four things about what happened. We’ll write you three real apologies — the kind a wise friend would — calibrated to your tone, your relationship, and the one question a chatbot would never know to ask.

Begin the apology  → See how it works
★★★★★
First 3 apologies free · no card · $9.99 unlocks everything, forever.
One price. No subscription. Ever.
Person looking at their phone, drafting a hard message
YOU
“I don’t know how to word this.”
US ↓
“You were right to be upset. I’m sorry — the real kind.”
001 / 100 moments
30s
to a real apology
3
options every time
$9.99
once. yours forever.
0
subscriptions, ever
Person staring at a phone screen, trying to write a hard message
Real you, 11:42pm. Six drafts in. Nothing’s right.
The Problem

You meant it to land. But you’ve been deleting and retyping for an hour.

Hard conversations are unevenly distributed in skill — and the cost of getting them wrong is enormous. Here’s why nothing you’ve tried so far is working.

  • ✕ Greeting cards say one thing, one way. And they cost more than this product.
  • ✕ ChatGPT happily writes “I’m sorry you feel that way.” If you don’t know it’s a trap, you’ll send it.
  • ✕ Asking a friend takes two days and exposes the situation to someone else.
  • ✕ Winging it is how every bad apology in the history of apologies got sent.
  • ✕ Your own draft doesn’t know what a good apology is supposed to do — and so it doesn’t do it.
How it works

Five taps. Three real ways to say it.

We don’t hand you a chat box. We ask the five questions a wise friend would ask — in the order they’d ask them — and write back something you’d actually send.

Two people sitting together at a kitchen table
Step 01

Who is this for?

Partner, parent, boss, friend, ex. Eleven options because the relationship changes every word.

Person looking thoughtful, holding their phone
Step 02

How badly did it land?

A scratch. A real hurt. Something broke. We calibrate the weight of the apology to the size of the harm.

The moat ◆
Two people having a serious conversation
Step 03

Were you actually in the wrong?

The one question a chatbot would never ask you. The answer changes whether you should be apologizing at all.

Hands typing a message on a phone
Step 04

One line. What happened.

Plain language. No need to perform. We do the craft — you get three real options to choose from.

★ Try it free · no card · right here

Write your apology. Right now.

First three apologies are on us. By the time you finish your third, you’ll know whether $9.99 is worth it.

1 Who
2 How bad
3 Hard question
4 Context
5 Tone
6 Length
Step 01 of 06 Who is the apology for?

The relationship changes every word. Pick the closest match.

Step 02 of 06 How badly did it land?

This calibrates the weight. Be honest, not modest.

Step 03 of 06 · the moat ◆ Were you actually in the wrong?

This is the question a chatbot will never ask you. The answer changes whether you should be apologizing at all — and what the words should do.

 

Step 04 of 06 In one sentence — what happened?

Plain language. No need to perform. We do the craft.

0 / 500
Step 05 of 06 What tone do you want?

Three real registers. Not the same line with adjectives swapped.

Step 06 of 06 How long should it be?

Format choice. Text-message, email, or letter. Most apologies should be short.

Real people. Real sends.

Words that actually landed.

Submitted by users with permission, names changed. Receipts in the dashboard.

★★★★★
“I’d been drafting the text to my mom for three weeks. Three weeks. Wrote four, deleted four. This thing gave me one I sent in five minutes — and she called me crying. In a good way.”
Casey M.
Casey M. Used /sorry for: an adult-child / parent message
★★★★★
“Picked ‘not really’ on the hard question and braced for the AI to ignore me. It didn’t. It wrote me a repair message that wasn’t a confession. That’s the moment I paid.”
Daniel R.
Daniel R. Used /sorry for: a misread at a party
★★★★★
“I snapped at a coworker in standup. The brief version was three sentences and honestly cleaner than anything I’d have written. Sent it before lunch, we’re fine.”
Priya N.
Priya N. Used /sorry for: a workplace apology
Why this beats the alternatives

You already tried the other options.

A greeting card
$6.99 + drive to CVS
  • ✕ Says one thing, one way
  • ✕ Generic, prewritten, by a stranger
  • ✕ Takes a day to actually arrive
  • ✕ Says nothing about your situation
  • ✕ Costs more than this
ChatGPT
Free, blank box
  • ✕ Won’t ask if you were in the wrong
  • ✕ Defaults to “I’m sorry you feel that way”
  • ✕ Three rounds of prompting to get something usable
  • ✕ Tone shifts are cosmetic, not structural
  • ✕ No memory of what makes apologies work
★ This product
100 Ways to Say I’m sorry
$9.99 once · everything included
  • ✓ Asks the question a chatbot won’t
  • ✓ Three real options, not three rephrasings
  • ✓ Tones produce structurally different writing
  • ✓ Built-in traps: blocks “I’m sorry if…” & the other 8 wrong moves
  • ✓ Refund inside 7 days if it didn’t land
Pricing

One price. No subscription.

Three apologies free to try it. After that, one price unlocks everything — current moments and every future moment we ship. Refunds within 7 days, no questions.

★ The whole library
One price · everything · forever
$9.99
All access
  • ✓ Unlimited apologies, any tone, any length
  • ✓ Sorry · No · Thank you · Goodbye · Condolences and every future moment
  • ✓ One-time, no subscription, yours forever
  • ✓ 7-day no-questions refund
Start free first →
FAQ

The honest answers, including the awkward ones.

Is this just a wrapper around ChatGPT?

No. It uses Claude under the hood — but the value isn’t the generation. It’s the four questions we ask before we generate, in the order we ask them, with the third one (were you actually in the wrong?) that no chatbot would think to ask. Strip that out and you’d have a worse chatbot. Add it back and you have a product.

What if I weren’t actually in the wrong?

Pick “not really” on step 3. We’ll write you a repair message instead of an apology — words that acknowledge the impact without confessing to something you didn’t do. Most apology tools can’t do this. It’s the case we’re proudest of.

Will the words actually be good?

Yes. We bake banned phrases (“I’m sorry you feel that way,” “sorry if,” “sorry but,” and six more) directly into the system prompt, so they never appear in your output. Every option must do three jobs at once: name the harm, take responsibility, close the loop. If a draft fails any of those, the model rewrites it.

Why isn’t this a subscription?

Because most people only need this a handful of times a year. A subscription would be a worse fit for the moment — you’d feel obligated to use it. One-time payment matches one-time use. If we’re wrong and you do use it constantly, $9.99 once is already a deal.

What about privacy — do you keep what I write?

We store the metadata of generations (which moment, which tone, which relationship category) to enforce the free-tier cap and improve outputs. We do not store your context sentence or the AI’s generated apologies after the session ends. Your draft isn’t training data and never will be.

What if I hate the output?

Regenerate. Free, unlimited, no penalty. Most users get the one they send within 1–2 generations.

Can I get a refund?

Yes — within 7 days, no questions. Reply to your Stripe receipt and we’ll refund. We’d rather lose $9.99 than have you carry a grudge about it.

What’s coming next?

/no (declines & boundaries), /thank-you, /condolences, /goodbye, /space, and /money. If you bought all-access, every one of those is already unlocked for you the day it ships.

You already know what you want to say.
We’ll help you find the words.

Begin the apology  →

First three on us. No card. 30 seconds.