Questions about money anxiety rose 38% in September
Back-to-school costs pushed budgeting and “how do I save” questions to their highest level this year.
Full article coming soonEngine
The Camino Engine: how conversations become actionable signals
The intent model behind everything we build: how it works, where its data comes from, and what it's teaching us.
Part 1
How it works
Camino isn't a single model or a single score. It's a four-stage pipeline that turns raw, fragmented signal into a structured understanding of intent, and keeps that understanding current as people keep interacting.
- 01Capture
Track each user’s conversational, behavioral, and contextual signals in real time.
- 02Model
Embed each user’s signals into a continuously evolving intent graph.
- 03Activate
Low-latency inference serves the graph where it's needed.
- 04Learn
Every activation is a new signal that feeds back in.
Learn feeds back into Capture: the engine recalibrates continuously.
The four stages
Capture. Every surface we touch, whether it’s a conversational turn inside a Camino Apps experience, a scroll or dwell event, a piece of content itself, or a signal an advertiser already holds, is recorded with its source, timing, and context intact. This forms the engine’s evidence layer: what users explicitly share, how they behave, and the content and context surrounding their interactions.
Model. Transformer embeddings map signals from user conversations, content, and behavior into a shared intent space. Rather than collapsing a person into a single propensity score, we build a persistent, per-user intent graph: a structured, evolving map of what someone cares about, how strongly, and why.
The graph evolves continuously, keeping pace with each user’s changing interests, needs, and intent.
Activate. A low-latency inference layer serves that graph wherever it's needed - shaping a response inside a Camino Apps conversation in milliseconds, riding along as a bid-time signal when publishers enrich their bidstream, or landing as structured audience data inside a publisher's CRM and Google's Publisher Provided Signals (PPS) when they understand their audience.
Learn. Every activation is itself a new signal. Outcomes feed back into the graph, so the engine recalibrates continuously - it gets more accurate the more it's used, not just the more it's retrained.
Design principles
01
Consent at the core
Signal capture is consent-based. The graph is built from what people tell us and do across Camino's own apps and partner publisher pages.
02
Composable by design
The same intent graph powers a publishing experience, a bidstream integration and a CRM export. One representation of intent, activated through different APIs.
03
Low latency, high fidelity
Inference is built to run inside the ad call and inside the conversation - not as an offline enrichment step that arrives too late to matter.
04
Legible, not opaque
Outputs are structured and interpretable. Partners see the intent signals behind a decision, not just a number they have to trust.
Where it runs
Part 2 · Our data
Where our data comes from
Two first-party sources, both consented: Camino's own conversational apps, and the partner publishers that run Camino for Publishers.
Sources
Camino Apps
Astrology Daily, My Daily Bible and Thrillly are conversation-first apps used by 20M+ registered people, with 1.5B+ interactions so far. Those conversations are the Engine's core signal.
20M+registered users
1.5B+interactions
500M+unique data points
Partner publishers
Publishers running Camino for Publishers add signal from their readers' conversations and reading behavior, across a growing network of sites in multiple verticals and markets.
Topic breadth
Broader than any single app
Camino's signals span the topics people bring to conversation every day: faith and spirituality, astrology and wellbeing, relationships, entertainment and more, across our own apps and our partner publishers' content.
Consent, privacy & brand safety
Built on consent
Is Camino's data consent-based?
Yes. Signal capture is consent-based, built from the conversations and reading behavior on Camino's own apps and partner publisher pages.
How does Camino handle GDPR, CCPA and consent frameworks?
Camino processes data in line with applicable privacy laws, including the EU/UK GDPR and the California Consumer Privacy Act, and respects the consent choices people make in our apps and on partner sites.
How long is data retained?
We keep information only as long as it's needed for the purposes described in our privacy policy. Retention periods depend on the type of data and why it was collected.
How does Camino handle brand safety and sensitive topics?
Sensitive topics are handled with care. Signals are reviewed before they're activated, and publishers and buyers can exclude categories they don't want to be associated with.
Part 3
Insights
What is conversational intent data?
Conversational intent data is information about what people want, taken from the questions they ask and the topics they explore in AI conversations rather than inferred from clicks or cookies. Camino collects it with consent in its own apps and on partner publisher pages.
What people ask AI
Evening is when people ask the big questions
Questions about relationships and life decisions peak between 9pm and midnight, at 2.4× the daytime rate.
Full article coming soonTravel planning starts in conversation, weeks before search
People ask open-ended “where should we go?” questions about six weeks before booking searches spike.
Full article coming soon