Cognatu matches ads to what an AI conversation is about, inside your own app. Our servers never see a word anyone writes. Publishers set the floor they're willing to serve at.
Calm · Sleep stories and a 7-day wind-down course. Try it free →
Display units were built for pages. Dropped into chat, they read as an intrusion, and users treat them like one.
Third-party cookies are gone and cross-site identity is collapsing. The networks built on following people around the web are running out of signal.
Some AI ad networks monitor prompts server-side to pick ads. In apps where people discuss health, money, and relationships, that isn't a growth strategy. It's a liability.
One rule makes everything else possible: the conversation never crosses the device boundary. Watch what does.
Your model, prompts, and response format stay exactly as they are. The SDK does the rest.
Swap your OpenAI or Anthropic call for the Cognatu SDK. Browser JavaScript today, with Go and Python as the public repo opens.
A compact classifier runs on the device, in parallel with the LLM call, off the critical path.
The winning ad is appended to the response, clearly marked. No confident match, no ad, ever.
Most networks promise not to misuse conversations they collect. We designed a system that never collects them, so there is nothing to misuse, leak, or subpoena.
A compact classifier reads the conversation locally and outputs a broad category: "career", "travel", "wellness". The transcript is never transmitted to us or anyone.
Advertisers bid on moments ("someone is discussing relocation"), not on identities. No conversation text enters the auction, and no advertiser ever receives a user identifier.
Our servers never hold a transcript, so there is no conversation database to hack, leak, or hand over. You can't lose what you never had.
Health, relationships, money, faith. The categories where AI apps thrive are exactly the ones where server-side prompt reading is untenable. That's who we built this for.
Contextual demand in premium verticals, a revenue share agreed with you directly, and an SDK that respects both your users and your latency budget.
Someone asking an AI about moving abroad is telling you exactly what they need next. Cognatu lets you be the relevant answer in that moment, without touching their data.
Minutes with the browser script tag, which is the SDK available today. Under four hours for a server-side integration, where you replace your LLM call with a Cognatu SDK call. The SDK proxies the request, runs topic matching on-device, and injects the ad into the response stream. Your prompt, model, system message, and response format don't change.
The Browser JavaScript SDK is a single script tag and works today. The Go, Python, WordPress, iOS, Android and React Native SDKs are built and become installable as the public repo and package registries open; until then any language can integrate against the REST API.
No effect on quality. The ad is appended after the LLM's response, never inserted into your prompt or system message. Topic matching runs locally, in parallel with the LLM call, so it stays off your critical path.
Nothing is shown. Cognatu only injects an ad when topic match confidence exceeds a threshold you configure. There's no fallback to generic or irrelevant ads. An empty result is always better than a mismatch that breaks the conversation.
A compact model classifies the conversation into a broad topic category, and it runs wherever your app already runs: in the user's browser or phone with the client SDKs, inside your own server process with the server-side ones. Only that category, never the conversation, and never anything that identifies the user, reaches us or the advertiser. We walk publishers through the full architecture during integration.
Most AI ad networks send conversation text to their servers to pick an ad. Cognatu's matching runs inside your own app, so our servers never receive the conversation. There is nothing to read, store, leak, or subpoena.
Publishers also set their own floor: no ad serves below the rate you name, with no minimums and no exclusivity.
Dating & relationships, wellness & mental health, beauty & lifestyle, career & professional development, personal finance & fintech, travel & experiences, meditation & mindfulness, fitness & nutrition, education, and subscription products. Reach out if your category isn't listed. We add new mappings quickly.
A clearly labelled "Sponsored" message appended after the AI response, native to chat, not a banner. It reads as a short, relevant suggestion. Publishers customise the styling to match their app's design system.
Every early publisher gets a direct line to the team, integration help, and a say in what we build next. Request access and we'll review it personally.