How to build an AI Telegram bot without coding

In short: to build an AI Telegram bot without coding you need three things: a bot token from @BotFather, an API key for a model (OpenAI, Anthropic, Google), and a no-code tool like n8n or Make that passes messages from the chat to the model and back. Your first working bot takes an evening — but you pay per answer, so "free forever" isn't a thing here.

What such a bot actually does

The plumbing is simpler than it looks. A user messages your bot → Telegram sends that message to your endpoint (a webhook) → your scenario takes the text, drops it into a prompt and sends it to the model → gets an answer → sends it back to the chat. That's it. Programming in this chain is replaced by a builder where you connect blocks with the mouse.

That also explains how the bot differs from "just ChatGPT": it has a role (a system prompt you write once), its own audience (people who configure nothing), and its own data (you can plug in a sheet, a knowledge base, a catalogue). It's a small product, not a chat window.

What you'll need

• A bot token. Message @BotFather in Telegram, run /newbot, pick a name and a username (it must end in bot) — you get a token string. It's your bot's password; treat it like one.
• A model API key. Register in a developer console (OpenAI, Anthropic, Google AI Studio, any provider) and create a key. This is separate from a ChatGPT subscription — more on that below.
• A scenario builder. n8n (flexible, free if self-hosted), Make (visually clear), Zapier (simplest, priciest at volume), or a dedicated bot builder.

None of these steps require code. They require carefully copying keys into the right fields and not mixing them up.

Step-by-step build

1. @BotFather → /newbot → name → username → save the token
2. AI provider console → API keys → Create key → save the key
3. n8n / Make → new scenario
4. Trigger: Telegram Trigger (paste the token) → event "message"
5. AI node: model + system prompt + the message text from the trigger
6. Action: Telegram → Send Message → chat_id from the trigger, text from the model
7. Turn the scenario on → message the bot → test

Step 5 is where all the value lives. The system prompt is the bot's character and rules. Not "be a helpful assistant", but specifics: who it is, who it serves, what it does, what it refuses, what format it answers in. If writing prompts still feels hard, start with what a prompt is and how to write one.

A ready system prompt you can adapt

You are the assistant bot of "Name" nail studio.
Job: answer questions about services, prices and booking.
Tone: friendly, informal, short — 4 sentences max.
Rules:
- Answer only from the price list and rules below.
- If a question isn't covered, say "let me check with the stylist"
  and offer to take their contact.
- Never invent prices, discounts or free slots.
- Don't discuss topics outside booking and services.
Price list and rules:
[paste your text here]

Note the "never invent" line. Without it the model will happily produce a plausible price and time slot — not out of malice, but because of hallucinations, an ordinary property of language models. For a bot talking to customers, that's the most expensive class of error there is.

Honest talk about money and limits

This is where promo videos usually lie. The honest version:

• A ChatGPT Plus subscription ≠ API access. Different products, different bills. The subscription is for you in a browser; the API is for your bot and is billed separately, per usage (per token).
• API access is nearly always paid. Some providers have a free tier with hard per-minute limits — enough for testing, usually not for a live bot with dozens of users.
• You pay for every message. A long system prompt is sent to the model every single time. A 2,000-word wall of text multiplies by the number of conversations.
• Builders' free plans cap operations. One user message is several scenario operations. The free plan runs out faster than you'd think.
• Someone has to find your bot. Technically it's ready in an evening; traffic, retention and revenue are separate work that has nothing to do with AI.

Sane starting math for a small bot: a few euros a month on the API at dozens of conversations a day, plus a builder plan if you outgrow the free tier. Not a money firehose, not ruin either — just do the math up front and set a spending limit in the provider console on day one.

Bots that actually make sense

1. A consultant over your own knowledge base — prices, services, FAQs. Obvious value, easy to verify.
2. A personal notes helper — you dump a thought by voice or text, the bot structures it and files it into a sheet.
3. An editor bot — send a draft, get clean text in the tone you want.
4. An inbound lead filter — asks 3–4 qualifying questions and hands a human a filled-in form.

A bad idea for a first bot is "a universal AI for everything". It has no edge over the plain ChatGPT app — and you're the one paying for it.

Beginner mistakes

• Exposed tokens. A bot token or API key in a screenshot, a public scenario or a chat means someone else's bot running on your bill. If it leaks, revoke it and issue a new one immediately.
• No spending cap. A loop bug or a spam run turns into an unpleasant invoice. The cap takes one minute to set.
• No conversation memory. By default the bot doesn't remember the previous message. Memory is a separate block — without it the dialogue falls apart on question two.
• User personal data. If the bot collects names, phone numbers or anything sensitive, you're processing personal data and rules like the GDPR apply: you need a lawful basis, you must inform people, and you must know where the data sits. More in our piece on privacy when working with AI.
• Zero testing on real humans. Give the bot to three friends before launch — they'll find what you missed in ten minutes.

What comes next

Once the bot answers, the next level is giving it tools: read a sheet, create a booking, call an external service. That's AI agent territory. And if you want a site or a dashboard around your bot, read about vibe coding — the same "describe it, get it" approach.