demos

Three bots in demo. All whitelabel. All calibrated.

Sid runs at acquisition. Felix runs at retention. Louis runs at occasions and gifting. All whitelabel, all calibrated per partner deployment, all built on the same Analyzer Engine.

@sid
demo
acquisition
Sid
Replaces the promo code box with an offer earned in conversation.
Sits at first purchase or signup. Probes for alignment with the product through specific, calibrated questions. Discount tier earned, not granted. Bargain-hunters held at list price, warmly. Aligned customers welcomed at the deepest rate.
Moment First purchase
Strategy Paradox
Replaces Vouchers
See how Sid works →
@felix
demo
retention
Felix
The loyalty layer that listens, and gets to know every member.
Sits at redemption inside loyalty programmes. Reads occasion, mood, taste profile through warm dialogue. Members who share more, generously, end up with more. Score hidden from member; structured preference data flows to brand.
Moment Redemption
Strategy Variable reward
Replaces Static menus
See how Felix works →
@louis
demo
occasions
Louis
Builds a package for an occasion, remembers what you shared, and adds a surprise chosen for you.
Sits at the moment a customer is choosing what to buy for an occasion, such as a date night, a gift or a celebration. Builds a package from the brand's own range using what the customer has chosen to share, the season and the weather, and adds a surprise picked for them. Every detail he remembers is shown to the customer and can be deleted.
Moment Occasions and gifting
Strategy Concierge
Replaces Generic bundles
See how Louis works →
in design

More moments. More bots in development.

Sid, Felix and Louis are the first three BehaviorBots, all in demo. More are being built, each calibrated against a different commercial moment, sharing the same dialogic architecture and Analyzer Engine. Founding partners considered for each.

In design · Q3 2026
Iris
The renewal conversation that asks honest questions.
Sits at subscription renewal. Reads whether the customer is genuinely engaged or auto-renewing through inertia. Surfaces churn risk early; surfaces upgrade signal where it exists.
Moment · subscription renewal
In design · Q4 2026
Otis
The complaint bot that turns escalation into insight.
Sits at the moment a customer signals friction. Reads the difference between a frustrated advocate and an extractive complainer. Routes accordingly. Captures product-defect signal as structured data.
Moment · service recovery
Concept · 2027
Rae
The referral bot that knows who's worth asking.
Sits at the post-purchase moment, after a customer has shown alignment. Reads whether they're likely to refer well, and if so, scaffolds the ask. No spray-and-pray referral programmes.
Moment · advocacy
thesis

Most AI in commerce is generic. We don't think it should be.

The dominant approach is one large bot trying to handle every customer interaction across the funnel. Tempting model: single deployment, single dashboard. But it sacrifices depth at every decision moment. We've taken the opposite bet.

Status quo
"One big bot for everything."
Why it fails
Generic bots optimise for breadth, not depth. They handle support, sales, retention and acquisition with the same conversational shape, and miss the behavioural mechanics specific to each. Polite chatbots that don't actually move metrics.
Status quo
"AI is the answer to every funnel question."
Why it fails
Most commercial moments are governed by long-studied behavioural patterns: reciprocity, procedural justice, intermittent reinforcement. Bots that ignore these are text-prediction over a dashboard. They don't change behaviour because they don't engage with what behaviour responds to.
Status quo
"More personalisation = better outcomes."
Why it fails
Personalisation alone optimises for what a customer prefers, not what a brand needs. A discount-hunter "personalised" with bigger discounts becomes a more loyal discount-hunter. Without behavioural framing, personalisation entrenches the wrong patterns. The bot needs an opinion.
definition

A BehaviorBot is narrow on purpose.

Each bot in the family shares four characteristics. Together, they're what makes a BehaviorBot different from a generic conversational layer.

trait_01
One decision moment
Each bot occupies a single commercial moment: first purchase, redemption, renewal, refund. Never two. The discipline of narrowness is what allows depth.
trait_02
Behavioural-science calibrated
Each bot built on a specific theoretical foundation: Life History theory, procedural justice, paradox strategy, variable reinforcement. Grounded in published research.
trait_03
Dialogic, not interrogative
Acknowledges before asking, responds with specificity, walks away gracefully when the customer signals it's not the moment. Hosts, not interrogators.
trait_04
Score hidden, data captured
Five-axis behavioural read runs silently. Customer experiences a warm conversation. Brand receives a structured behavioural fingerprint plus preference data.
engine

One engine. Many bots, all calibrated against it.

Underneath every bot
The Syntacy Analyzer Engine
Every BehaviorBot runs on the same five-axis behavioural fingerprint, the same anti-hack verification layer, and the same dialogic conversation architecture. What changes per bot is the moment it's pointed at and the weights applied to each axis for that specific job. Deployed together, the bots build a shared record of who your customers actually are, captured with consent, owned by you, and useful far beyond loyalty.
i
Five-axis Life History scoring
Long-term orientation, price focus, politeness, urgency, manipulation risk. Scored live by an LLM prompted as a behavioural psychologist. Hidden from the customer, surfaced as structured data to the brand.
long_term price_focus politeness urgency manip_risk
ii
Anti-hack verification
Detects copy-paste manipulation, performative politeness, and incongruence between language and metadata. Customers who try to game the bot end up with the same outcome as customers who arrive with no signal: a polite hold.
iii
Dialogic conversation architecture
Acknowledgement before next question. Adaptive follow-ups based on the prior reply. Graceful exit when signal goes hostile. Same shape across every bot, calibrated to the moment each occupies.
iv
Structured zero-party data
Every conversation produces a record of zero-party preference data: fields the customer knowingly volunteered, with provenance and consent flags. Flows to the partner's CRM. Owned by the partner.
partners / fit

Sectors where behaviour matters more than volume.

These are the sectors BehaviorBots is starting with: businesses where a returning customer is worth far more than a one-off discount. Businesses in other sectors are welcome to get in touch.

Sector
Why BehaviorBots fit
Bots most relevant
Beauty and personal care
Welcome codes leak to voucher sites, and loyalty points feel the same for everyone. A conversation finds out what each customer actually wants.
Felix · rewards matched to each member. Sid · welcome offers earned, not leaked.
Food and drink
Discounts go to one-off bargain hunters rather than the regulars who keep coming back.
Sid · first-order offers for customers likely to return. Louis · the right pieces for an occasion, from your own range.
Restaurants, bars and cafés
Regulars get treated like first-timers, and the occasions that bring them in go unnoticed.
Louis · the right choices for each occasion. Felix · rewards that remember your regulars.
Arts, culture and events
Blanket ticket offers go to people who would have booked anyway, so the discount buys nothing.
Sid · offers earned at booking, for new audiences.
Subscriptions and memberships
Renewals rely on inertia, and members quietly leave without saying why.
Felix · rewards that keep members engaged. Iris (in design) · renewal conversations.
research

The research behind the bots

i
Lewis, M. (2006)
Customer acquisition promotions and customer asset value. Journal of Marketing Research, 43(2), 195 to 203.
ii
Datta, H., Foubert, B. and Van Heerde, H. J. (2015)
The challenge of retaining customers acquired with free trials. Journal of Marketing Research.
iii
Belli, A. and colleagues (2022)
40 years of loyalty programs: how effective are they? Generalizations from a meta-analysis. Journal of the Academy of Marketing Science.
iv
Liu-Thompkins, Y. and colleagues (2022)
What drives retailer loyalty? A meta-analysis of the role of cognitive, affective, and social factors across five decades. Journal of Retailing.
v
Schmitt, P., Skiera, B. and Van den Bulte, C. (2011)
Referral programs and customer value. Journal of Marketing.
Founding partners
Become a founding partner.
We're building our founding partner pilot programme now: a free eight to twelve week pilot of Sid, Felix or Louis on your own store, with the results measured against a control group. If you're a CMO, Head of Retention, or founder rethinking how your brand talks to its customers, we'd like to hear from you.
Talk to us →