A bot that segments a person on the fly and delivers the right thing
A menu of four buttons makes a person guess which option he belongs to — and half of them leave at that step. Below is the mechanics of a bot that understands a request from the first sentence, delivers the right material and hands a hot enquiry to a live person.
A menu of four buttons makes a person guess which option he belongs to — and half of them leave at that step. Below is the mechanics of a bot that understands a request from the first sentence, delivers the right material and hands a hot enquiry to a live person.
A menu of six buttons with no option for you
You have written to a bot like that. "Hello! Choose: 1 — about our products, 2 — book a consultation, 3 — ask a question." You press the third, write your question — and get "our manager will be in touch".
That is not a funnel. It is an answering machine with extra steps.
The problem is not even the inconvenience. The problem is that a bot like that learns nothing about the person. A beginner who does not understand the basics and a business owner with a budget both see one menu and get one answer. It overwhelms the first and insults the second.
And somebody who wrote in his own words drops out of the logic altogether: there is no scenario for free text.
Meanwhile, in his very first sentence a person usually says everything about himself that is needed.
What a bot must determine before offering anything
Three things, in order.
First: who is in front of us. Which segment the person belongs to — by intent rather than demographics. A beginner who wants to start earning. A specialist who needs it for his profession. An owner building a system. That determines what to talk to him about at all.
Second: how ready he is. Which rung of awareness he is on: just looking, looking for a solution, choosing whom to buy from, ready to buy. That determines what to offer at the end. A person on an early rung must not be offered a purchase; a person on a late one must not be offered another free piece of material.
Third: what is in the way right now. The specific objection: too expensive, did not know it existed, did not understand what I would get, afraid I will not cope, no computer, restrictions.
The material is delivered at the intersection of the three answers. Not "here is our catalogue" but one specific piece that removes this objection for this person on this rung.
How the bot works out a person's segment
Not by asking. A five-question form kills half the people at the second one.
By marker phrases. Every segment has its own language and it is consistent.
Someone who can do the work but cannot sell writes: "I do not know where to look for jobs", "no ready case histories", "I am afraid I will take a job and not manage it".
A specialist bringing the tool into his profession: "I did a contract analysis in ten minutes", "they do not know at work", "I need it for my profession".
Somebody building systems: "implement it in the company", "assistants for a department", "build a system in my own business".
These are not guesses — they are phrasings collected from real audience answers during the research. That is why a bot cannot work without prior segmentation: the marker phrases come from it.
The rung is determined by behavioural signs: what the person has already tried, what he does not have, what he asks about. "Tried it but without a system" and "I use it daily but have earned nothing" are different rungs, and they are audible immediately.
The rule without which a bot breaks
One, and it matters more than all the mechanics.
If a person does not fall into any segment, the bot does not guess. It asks one clarifying question and only then delivers.
A wrong delivery is worse than no delivery. A business owner sent material for beginners leaves and does not come back. A beginner sent an analysis of a corporate rollout feels he has come to the wrong place.
One question is fine. Three questions in a row is already a form, and half the people are lost on it.
What a bot gives that a contact form does not
A reasonable objection: why all this when you could put up a form and call people back.
It works at night. An enquiry outside working hours is either handled immediately or lost — the person finds the next supplier within five minutes. That is the clearest and most underrated line of losses.
It qualifies before the conversation. By the time a live person joins, it is already known who is on the line and what they need. The conversation does not start with "tell me what you are interested in".
It does not tire and does not have moods. The twentieth enquiry of the day is handled like the first.
And it leaves data. Every conversation is raw material: which phrases recur, where people drop away, which objection comes up most often. A contact form gives you nothing but a name and a phone number.
What the bot's base is assembled from
A bot is not a dialogue script. It is a knowledge base plus delivery rules.
What is in the base:
- Segments with marker phrases — from the audience research
- Readiness rungs with their signs — from the same place
- A bank of objections verbatim, as people phrase them
- A library of materials — one for each intersection
- Next-step rules: what to offer on each rung and what not to
- The voice — from the positioning, so the bot speaks like you rather than like a support desk
Note where it all comes from. Not one line of the base is invented at the bot-building stage — it all arrives from earlier stages. Which is exactly why a bot built first comes out empty: it has nothing to know.
What the bot delivers on each rung
The matrix becomes clearer with an example. The same person on different rungs gets different things.
Just looking. An everyday result, one tool, something simple and applicable today. Nothing about money and jobs — too early.
Tried without a system. A route, a choice of direction, a case with figures. Not a catalogue of hundreds of options — that makes things worse on this rung.
Can do the work but cannot sell. A price list, a platform, a script, a portfolio. Here you must not show "what a model can do" — the person knows that already.
Choosing whom to learn from. The composition of the product, what exactly he gets, plans by task. A discount works worse than clarity here.
Ready to pay. Terms and the first three actions. Another free piece of material on this rung is a way to lose the person.
What the business gets
- A funnel scheme: which branches exist and where each leads
- A bot script with the logic for determining segment and rung
- A bank of marker phrases — which words identify whom
- A delivery matrix: segment × rung × objection → a specific piece of material
- Escalation rules: when the bot hands over to a live salesperson
The last is often forgotten and it is the part with the most money in it: a bot must know when to stop being a bot. The sign of a hot client is a question about price, timescales or specific terms. At that point the conversation goes to a human.
By the methodology I use, the funnel and sales stage takes three days — with the research, positioning and content system already done.
This is the sixth of seven stages of full positioning: 3–4 weeks, 25–35 hours, around $2 000 for the package (the Freelance 2.0 course methodology). Honestly: that is the price of the service by our methodology, not market statistics.
Do it yourself or commission it
Doing it yourself. The mechanics above are the "Funnels" and "Sales" blocks of "Freelance 2.0": 62 prompts across 11 stages, including funnel structure, a bot script, call and message scripts and simulators where the model plays a realistic client.
The course costs $9 and is included in Basic. Registration is free. Three days of the Basic plan switch on with one button, no card needed: Basic includes 200+ AI assistants across 14 categories, the course "Sales" (a main module of ten lessons); automation templates for the technical build come from the Creator plan.
Commissioning it. The service exists. And now you know the main thing about it: a bot built in isolation from the audience research always comes out as a menu of six buttons. The order matters more than the execution here.
Do one thing today: open the last twenty incoming messages to your business and sort them by three questions — who is writing, how ready they are, what is in the way. Usually it turns out there are not twenty variants but three or four, and they recur. That is your delivery matrix.
What this looks like on a real project
Below is the same work on a live client: a dental studio run by two doctors, a husband and wife. The work was delivered in eleven sections, the tenth being the funnel and the bot as its hub.
Why this example is here. It shows that positioning is not an abstraction but a service with a clear composition. And it sells to any business with an audience and a product: a clinic, a school, an agency, a shop. The mechanics are the same; the content changes.
An analysis of a deal like that from first message to payment is included in the course "Sales" on the Basic plan (the "First order" series).
Two tracks, one hub
The funnel runs in two modes in parallel, and both converge in one place.
The cold track: content → bot → booking. Medium-term, dominant after 6–12 months. It provides scale.
The warm track: the existing base → bot → booking. Fast, money in the first month or two. It provides speed.
The bot is the central hub of both.
Five stages of the cold track
Traffic across five channels and 29 subjects → nine lead magnets behind code words → warming by level of awareness → a converter with a location fork → closing without pressure.
The key principle: the warm-up lasts as long as awareness requires. The bot does not sell until it has understood who is writing.
Each channel for its own rung
Short-form video — rungs 1→2, virality on fear and aspiration · long-form video — 2→3, search and depth · the channel hub — 3→5, warming and conversion · the social feed — 4→5, cases, testimonials, the offer · the local community platform — local presence.
How the bot itself works
Four steps in its logic:
Entry — a code word or a free-text message.
Diagnosis on three axes — segment, level of awareness, location.
Usefulness and material — the contact is saved to the base.
The offer — only after qualification.
It hands out value, qualifies and remembers the person. It does not sell until it has understood who has arrived — and that is not politeness but what holds the conversion up.
A ready bot script instead of a blank page
Freelance 2.0, prompt №45 "A bot script for the funnel" — 55 minutes, Basic plan. The output is a table of messages you can take to a developer or assemble yourself in any bot builder: entry points with code words and triggers, the greeting and delivery of material, a warm-up chain of four to seven messages with timings, the offer.
Before that comes prompt №43 "Sales funnel structure", 45 minutes: where people come from, what catches them, how they get warmed, what takes them to a sale. Without that scheme a bot segments people into nowhere.
Assistants, Basic plan: Bot architect — logic and scenarios before the build. Telegram funnel analyst — where exactly people drop out of the chain.
When a bot outgrows a builder. The Make and N8N plans — everything in Creator plus a course on building your own logic without the ceiling of somebody else's platform. Plus over 3 000 ready automation templates: over 3 300 n8n workflows and 185 Make scenarios, Creator plan, advanced ones Full.
Skills for building a bot
- Chatbot design — not the build but the design: scenarios, an implementation plan, a risk matrix and metrics. Useful before anything gets assembled
- Building conversational assistants — managing context and memory, error handling and, most of all, the moment of handover to an operator
- Messenger bot development — if the bot outgrows a builder: state machines for multi-step dialogues and protection against race conditions
- Chatbot analytics — the share of conversations completed, the average number of messages, escalations. Without this it is unclear whether the segmentation works
- DocsBot AI — if the bot has to answer from your knowledge base rather than in generalities
- Landbot — managing bots and clients, including handing a conversation to a live agent
The first four skills in the list are advanced (Creator and above, or $9 once, or 1000 XP); DocsBot AI and Landbot are regular, files from Basic.
What matters more here than the choice of platform. The fourth item. A segmenting bot with no analytics is a hypothesis nobody has tested: you do not know whether people reach the end of a branch or which question they drop out on.
What to take on the platform for this task
- Telegram bot with hand-off to a live operator — the escalation rule in a ready n8n scenario; Creator, Make, N8N or Full plan
- Email lead qualification with Telegram alerts — scores an enquiry and signals a hot one to a manager
- AI routing of incoming requests by department — sorting enquiries without manual triage
- AI sales chatbot for WhatsApp with OpenAI — a ready n8n chatbot
- Firestarter — a RAG chatbot from any website — Open Source: a bot that answers from your site's content (description open to all, repository link from Creator)
What to read next
Lead magnets behind code words — what the bot delivers at the entrance.
Anatomy of a system instruction — how this works inside.
AI for developers — a real system prompt taken apart.
Four scripts and two simulators — what happens after the handover.
AI agents: what they are and what they pay — the full guide to agents, with market rates.