--- title: "Correct it once, and every one of our tools learns" description: "When someone on our team fixes something an AI wrote, that fix becomes a lesson six Sneeze It tools read before they write again. Here is how the Brain decides what counts, and what never goes agency-wide without a human yes." section: Inside Sneeze It author: David Steel published: 2026-10-10T20:15:36.037Z url: https://one.sneeze.it/blog/correct-it-once-every-tool-learns tags: ["inside-sneeze-it", "brain", "ai-learning", "feedback-loops"] --- # Correct it once, and every one of our tools learns _When someone on our team fixes something an AI wrote, that fix becomes a lesson six Sneeze It tools read before they write again. Here is how the Brain decides what counts, and what never goes agency-wide without a human yes._ Every agency that uses AI has the same quiet problem. A strategist rewrites a headline because the client hates the word "transform." Next week a different tool writes a report for the same client and uses "transform" again. The correction was real, it was right, and it lived in one person's head and one tool's history. We wanted the opposite. Correct something once, in any Sneeze It tool, and every tool that writes for that client should know. So on October 5 we built the Brain: the agency's shared memory of what our AI got wrong and what the fix was. It went from first commit to live in one day, nine commits and about 2,000 lines of code, and it is now in its first week of use, inside the agency only. :::stats 6 | Sneeze It tools that feed the Brain and read from it 7 | kinds of correction it understands 3 | different clients before a lesson can go agency-wide 15 min | how often it checks for new corrections source: Sneeze Brain code, checked October 10, 2026 ::: ## A contract with two clauses The Brain asks very little of the tools around it. Each tool does exactly two things. It tells the Brain when a person corrects its AI. And it asks the Brain for lessons right before its AI writes. That is the whole contract. Six tools follow it today: Studio (ads, emails, landing pages, video), Coach (weekly performance reports), the Hub (our record of every client location), Audience (market strategy), our call center tools, and Ideate (brainstorming). Each one carries the same small file. If the Brain is switched off or down, the tool behaves exactly as it did before. It never throws an error and never holds work up. We wanted learning to be something the tools gain, not something they depend on. :::flow "How one correction reaches every tool" A person corrects | Rewrites a headline, cuts a line from a report, scores an AI idea low The tool reports it | One signal, tagged with the client and the kind of work The Brain weighs it | A person's word counts 1, a watched change counts half A lesson forms | Short, tied to one client, one tool or the whole agency Every tool reads it | Before its AI writes the next thing for that client ::: Lessons attach to a location or a brand from the Hub, which is our one record of every client. That is what lets a lesson learned in Studio about a location reach Coach for the same location. A correction made in Studio guides Coach, and the other way round. ## What counts as a correction The Brain understands seven kinds of signal: someone said, the client said, a note on the client, asked to change, edited by hand, a check flagged it, and what happened. They are not equal. A person stating something plainly ("never mention price in this client's ads") is the clearest signal there is, and it counts as a full point. A change we only watched, like a person redoing an ad or editing a line by hand, counts as half. A client lesson goes into use at one point. In plain words: one clear statement, or the same quiet change twice. :::chart column "How much a signal counts toward a lesson" A person said it | 1 We watched a change | 0.5 Needed for a client lesson | 1 source: Sneeze Brain learning rule ::: We made that trade-off on purpose. Watching edits catches the things nobody bothers to say. But a single hand edit could be a typo fix or a mood, so it takes two before the Brain acts on it alone. Corrections also do not only happen inside our tools. Strategists say "never do this for this client" in Slack. So the Hub listens in a chosen staff channel. When a message is about exactly one client, it writes a plain restatement and sends that to the Brain. It never replies and never reads direct messages or channels shared with clients, and money is filtered out. :::pullquote Lessons are guidance, never permission. Every tool still enforces its own rules after the AI writes. ::: ## The ladder to agency-wide A lesson about one client stays with that client. But some lessons are really about us. If three different clients have taught the same thing, the Brain has Claude propose it as a lesson for a whole tool or for the whole agency. Proposing is all it does. The wider lesson waits for a person to say yes. It may not carry any client's name. And a lesson that someone has turned off is never proposed again. :::figure wide ![A wooden stepladder in an agency workspace with sticky notes on three rungs; at the top a single magenta card waits beside an empty chair for someone to approve it.](/blog/media/542e8c82c4827da4f96cf488.jpg) One client teaches a lesson. Three clients teach the same one. Only then is it proposed for everyone, and it still waits for a person. ::: There are hard limits on what any lesson can be. A lesson can never be an offer, a price, a promised result, a customer quote or a private fact. Lessons steer how the AI writes. They cannot loosen the rules each tool already enforces. So a lesson can stop Studio from using a word your brand dislikes, but it can never put a discount into your ad. ## What the team sees The Brain opens on "What needs attention": six kinds of counted card over the last 30 days. Lessons waiting for a yes. The kind of work the AI is corrected on most. Clients who keep pushing back. Lessons that are not holding. Lessons that held. Tools that have gone quiet. Every number on those cards is a count of real rows. None of them are written by AI. Once a day it checks whether there is enough material for a weekly read, where Claude summarizes the week's corrections into items, each with a "Do" action. There is also an ask box. Ask it "what do we keep getting wrong in reports?" and it answers only from what it holds, with the evidence. Give it a direction ("from now on, never...") and it drafts the lesson, which is saved only when a person clicks to confirm. Staff can reach the same thing from Claude or ChatGPT through [our AI connector](/blog/why-our-mcp-never-shows-another-franchisees-numbers). :::compare "Before the Brain" "With the Brain" A correction lives in one tool's history and one person's memory. The next tool repeats the mistake. Nobody can see which kinds of work the AI gets wrong most. --- A correction becomes a lesson for that client in every tool. Patterns across three clients are proposed for everyone, with a human yes. The team sees counted cards of where the AI is weakest. ::: What comes next is joining lessons to outcomes, so we can tell which advice actually worked. The Brain already records what happened; using that to rank lessons is the next piece we are building. The same habit runs through our brainstorming tool, where [the AI suggests and your people score](/blog/ai-suggests-your-people-score). :::takeaways "What this means if you run 20 locations" - Tell us once. A preference you give about one location reaches every tool that writes for it, not just the one you were looking at. - Your corrections stay yours. A lesson about your brand only goes wider after three different clients taught the same thing, without your name, and with a person's approval. - No lesson can add an offer, a price, a result or a quote to your marketing. Lessons shape how we write, never what we promise. - The Brain is internal and in its first week. You will feel it as fewer repeated mistakes, not as a screen you log in to. ::: :::cta Want to see how a correction travels through our tools? Book a walkthrough and we will show you with sample data. :::