What is a scripted chatbot?
A scripted (rule-based) chatbot follows fixed menus and decision trees: "Press 1 for orders, 2 for returns". It does exactly what it was designed to do. That makes it predictable, cheap to run and easy to audit. It also makes it rigid: if a customer types something unexpected, it fails or loops.
What is an AI chatbot?
An AI chatbot uses a language model to understand free text and respond in natural language, usually based on a knowledge base such as your FAQs, policies or product information. It handles phrasing variety and mixed languages far better than menus. Its main risk is answering confidently when it shouldn't, which is why the source content and the rules matter.
What is an AI agent?
An AI agent goes further: it can take actions using tools. It looks up an order, creates a CRM lead, books a slot, drafts an invoice or routes a ticket. Think of it as a chatbot with hands. That's powerful, and it's exactly why agents need a stop rule defining which actions are allowed alone, which need approval and when to hand over.
How do they compare?
| Scripted chatbot | AI chatbot | AI agent | |
|---|---|---|---|
| Understands free text | Poorly | Well | Well |
| Takes actions in your systems | Limited, predefined | Usually no | Yes |
| Predictability | High | Medium | Medium, needs rules |
| Best for | Simple menus, fixed choices | FAQs and information | Workflows: leads, orders, tickets |
| Main risk | Frustrated users | Wrong answers | Wrong actions |
Which one should you choose?
Often all three, combined. A practical design:
- Buttons and menus for predictable choices such as order status, book an appointment or talk to a person. They're cheap and fast, and they reduce WhatsApp message counts (relevant after the October 2026 pricing change).
- AI understanding for free-text messages that don't fit a button.
- Agent actions for low-risk, reversible steps such as creating a lead or fetching a status.
- A person for decisions, exceptions and anything in the hard-stop list.
What questions should you ask a vendor?
- Which actions can the bot or agent take without a person?
- What happens when it isn't sure?
- Where does its knowledge come from, and who updates it?
- Can we see logs of every conversation and action?
- Can we export our flows and data?
How do we apply this in client work?
Everything on this page feeds into how we run pilots. We start with a consultation to understand the process and the people involved, then write a one-page scope: the trigger, inputs, steps, outputs, a success measure and a stop rule that says what the agent may do alone, what needs approval and when it must hand over. We build inside the tools you already use, test on real or realistic cases including awkward ones, and review the results with your team before anyone talks about expanding.
We keep a few habits on every project: we never publish invented results, we label examples as illustrations, we list third-party costs separately, and we say so plainly when something isn't worth automating yet. If that sounds like the kind of partner you want, read the pilot process or message us on WhatsApp.
What should you prepare before talking to us?
You don't need a technical brief. A useful first conversation needs only a few things, and gathering them is valuable even if you never work with us:
- The process in plain words: what triggers it, who does what, and where it usually goes wrong.
- Rough volumes: how many messages, orders, tickets or invoices per week. A one-week tally is enough.
- Your tools: WhatsApp app or API, CRM, sheets, accounting or helpdesk software, including versions or plans where you know them.
- Three real examples: typical messages or cases, plus one awkward one, with personal details removed.
- What must never happen: the mistakes that would hurt most. These become the first lines of your stop rule.
- An owner: the person who will review the workflow once it runs.
Send these on WhatsApp or by email, or run the pilot scorecard first.
How does a pilot with us work?
Every engagement follows the same four steps. Consult: you walk us through the process, the tools and where it breaks. Pick the pilot: we choose one workflow and write down its inputs, outputs, tools, stop rule and success measure. Ship: we build it into the tools you already use and test it on real cases. Review: your team checks what the agent did and what it escalated, then decides whether to tune it, expand it or stop. Read the full pilot process.