With AI chatbots, you can now create smarter, more conversational flows, without building complex decision trees or hundreds of manual routes. The AI understands intent, finds answers from your Knowledge Base, and responds naturally to each customer.
This guide also covers key terms and settings you’ll see while building your chatbot, so you’ll know exactly what each option means as you work through the process.
▶️ Basic Navigation Video [5 minutes]
Before building your first chatbot, we recommend watching this short video.
You’ll get a quick tour of the Talkative Chatbot Builder, including how to navigate the flow diagram, edit nodes, and use handy tools like search, zoom, and collapse.
You’ll also see how to preview and test your chatbot as you build, ensuring your flows work exactly as intended.
🛠️ How to create a Talkative Chatbot Config
Step 1: Open the Chatbot Builder
Head to ‘Chat Bots’ in the left-hand menu, then click on the blue 'Create Talkative Chatbot' button.
Step 2: Complete the Chatbot Config Form
Select your chatbot’s basic settings, you can edit these settings at any time:
Queue label – Internal name for the chatbot.
Transcript Emails – Email addresses transcripts will be replied to.
Chatbot first name – The name customers will see when interacting with the chatbot.
Inactivity timeout (optional) – Time before ending the chat after inactivity. Leave blank for no timeout.
AI phrase matching – Toggle on to use AI to interpret customer intent and match messages to training phrases.
Chatbot avatar (optional) – Upload an image.
Template – Choose your starting point:
- Example Chatbot – A ready-to-go flow.
- Generative AI Chatbot – Prebuilt with AI integration.
- Blank Slate – Start from scratch.
Ignore first message in WhatsApp/SMS – Skips the first customer message so they see the welcome message first.
Rephrase enabled – Allows the chatbot to rephrase messages and suggestions based on the intent you provide. Good for customers speaking a different language.
Rephrase intent (optional) – Define the type of rephrasing you want (e.g. “reply in the language the customer speaks”).
Rephrase language model – Choose between GPT 4.1 mini (basic rephrasing) or GPT 4.1 (complex rephrasing/translations).
Once complete, click Create Talkative Chatbot Config to save.
Step 3: Access and Manage Your Chatbot
Once your chatbot config is created, it will appear in your Chatbot Configs list, select to be selected.
Use the three-dot menu on the right to access more options:
- Edit config – Opens the chatbot builder editor so you can build or update your flows.
- Edit metadata – Returns to the config form from Step 2 so you can update details like name, template, or settings.
- Manage versions – View and restore a previous version of your chatbot.
- Delete – Permanently remove the chatbot config.
Watch the navigation video above to see how to start editing your chatbot. Then, use the Key Concepts & Glossary section below to understand the different options and customisation settings available.
📚 Chatbots: Key Concepts & Glossary
1. General Chatbot Layout Overview:
General | Edit the titles of your nodes to quickly identify what section of the journey a customer is at. This does not appear to the customer. |
Node | A card in your chatbot flow that represents a step in the conversation. Nodes can contain messages, actions, or routes to other nodes. |
Global Nodes | Can be triggered from anywhere in your chatbot, useful for actions like letting a user type “transfer” to speak to an agent. |
Actions | This is what the chatbot will be doing at each node (e.g. send message). |
Exit Approach | The method the chatbot uses to decide what happens after the current node (e.g. branch based on user input, transfer to queue, redirect). |
Fallback | The node used when the chatbot doesn’t understand a customer’s input. |
Training Phrase | Example customer messages that help the chatbot match intent to the right node. |
Purple Highlight | The node you’re currently editing. |
Green Text Boxes | Messages sent to customers; customise these to match your tone and content. |
Preview | Test your flow regularly before moving to the next section. |
Publish | Only publish when you’re happy for the chatbot to be connected to a live widget on your site. |
1a. AI Chat Bot Layout
AI Chatbots include additional AI-specific sections, highlighted in purple within the builder. These sections allow you to connect your chatbot to a Knowledge Base and define how it uses AI models to find and respond to customer queries.
In the menu on the right-hand side, you can:
- Select which Knowledge Base the AI should reference.
- Choose the model used for generating answers.
- Adjust the Exit Approach, which controls how the AI handles successful or unsuccessful lookups.
2. Options & Customisation:
2a. Add Actions:
This is what the chatbot will be doing at each node. There are 5 action options you can choose from:
Send Message(s) | A text-based customisable message sent to the customer. |
Send File | A file is sent to the customer within the chat. You can upload any file type, but the size limit is 10 MB. |
Make a web request and write int. Data | Integrating with external systems. For example, you can track an order for a user after retrieving their tracking number from the chatbot. Click here for more information. |
Custom Message Suggestions | Custom message suggestions allow you to create a suggestion chip without a corresponding follow up node. Use this if you want multiple suggestions to take you to a single follow up node, or when you want the user to free type to get to a specific node |
Write Interaction Data | If you want to take the user’s input (e.g., email address) and have it create interaction data, you can set it to Static Text (a fixed value), the Entire Previous Message, Email in the Previous Message (the system auto-detects email values), or custom regex in the previous message (useful for detecting things like order numbers or account numbers). |
link to Make a web request and write int. Data docs
2b. Training Phases:
When using the exit approach branch off based on user input, you can add training phrases; example messages the chatbot will use to match a user’s typed answers to the correct node. The more phrases you include, the more accurately the chatbot can recognise intent and route the conversation.
2c. Exit Approaches
Exit approaches are how the system decides what to do next. There are multiple options:
Branch off based on user input | This is the most popular exit approach; the user’s message selection defines which node follows. |
Always go to next item | It waits for the user to message and then goes to the next input. |
Redirect to next node immediately | Does not wait for the user input. |
Transfer to queue | Links to the queues created within the Talkative queues settings section. The transfers will occur regardless of queue presence. |
Route based on interaction data value | This allows you to pull through information you require, such as account numbers. You can then continue the flow to actions if it matches specific information. |
Route based on interaction data existence | For example, only transfer to the sales queue if you have first captured the user's email address. |
Based on queue status | Useful if you want to vary the message flow depending on whether your queue is online (or not). |
Redirect to node | Allows you to redirect across the flow to a different section. |
Lookup previous message in AI Knowledge base | Using generative AI to respond to a customer's question, based on a pre-approved data set (e.g. your website). Find out more here. |
Escalate to email (web only) | This will generate a form for the customer to fill in. The form will be emailed, and the agent will pick it up. |
Redirect to the start of the chatbot flow | Returns the chatbot to the starting point. |
End interaction | The interaction will close. |
Warning: Changing an exit approach will delete all nodes beneath it. Copy and paste any nodes you want to keep before making changes.
2d. Message Suggestions
If you select the exit approach of Branch off based on user input, and enter node names, they’ll appear as suggestion buttons in the original node. Adding a suggestion creates a new branch. To add buttons without creating new branches, go to Actions and select Custom Message Suggestions.
2e. Retry Settings / Fallback
Fallbacks are the nodes the chatbot moves to when it doesn’t understand a user’s input. The fallback node is set on the first (top) node in your flow.
Retry settings are also found on the starting node. Here you can set the messages shown when the chatbot can’t understand an input, and you can add multiple retry messages.
Maximum retry attempts counts consecutive retries rather than total retries. For example, if set to 3 and the user enters their email incorrectly twice but succeeds on the third try, the counter resets to 0. If they later hit another fallback, the retry count starts again.
2f. Errors
If your chatbot has any errors in the logic/set up, you will see a warning in the top right corner.
Each error will tell you what is incorrect and how to correct.
3. Shortcuts
Talkative supports several keyboard shortcuts:
Ctrl Z - Undo | Ctrl Y - Redo | Ctrl C - Copy | Ctrl V - Paste |
Ctrl M - Minimise nodes | Ctrl P - Search | Ctrl S - Save | Ctrl Shift S - Publish |
Ctrl+ Enter - Preview from start | Ctrl+Shift+Enter - Preview from current node | Ctrl B - Exit preview | Ctrl H - Scroll current node into view |
Ctrl + - Zoom in | Ctrl - - Zoom out | Backspace/delete - Delete current node |
Helpful onscreen Icons:
Search is useful if you want to find a specific message or node.
Minimise can be useful to get a simplified view of your chatbot displaying only the node title.
❓FAQ’s: Chatbot Builder
Can I have more than one chatbot?
Yes, you can create multiple chatbots for different use cases, languages, or departments.
If you are on our starter plan you are limited to 1 chatbot, please reach out to support@gettalkative.com if you’d like to increase this.
Can I copy an existing chatbot to use as a template?
Yes, open the chatbot you want to copy, select the node (or branch) you’d like to reuse, click Copy, and then paste it into your new chatbot.
How do I delete one node without deleting everything underneath?
The best way to do this is Copy everything underneath that you want to keep, delete the node you want to delete, then paste.
How do I restore a deleted node?
Deleted nodes can’t be restored directly. You can click the Undo icon in the bottom left to go back or if you’ve saved a previous version, you can restore it from Manage Versions.
Can I connect my chatbot to AI for free-text responses?
Yes, if your plan includes AI integration, you can use the Lookup in AI Knowledge Base exit approach to provide AI-powered answers. Check out our AI Chatbot Builder Guide for that full breakdown.
How do I delete suggestion buttons without deleting the linked node?
Use Custom Message Suggestions to add or remove buttons without creating or deleting branches in your flow.
Can I undo a published change?
No, publishing makes changes live immediately, but you can restore a previous version from Manage Versions.
Chatbot Not Responding After Initial Query:
This can indicate an issue with your AI knowledge base or integration. Ensure your knowledge base is up-to-date and properly connected. If you have a GenAI lookup on your fallback node, please check "retry settings" are set to zero (this can be found in the topmost node in your chatbot config).
Inconsistent Answers or Failing to Find Answers:
Check for any outdated information or discrepancies in your knowledge base. Utilize the "AI Knowledge Base Lookups" and "AI Knowledge Base Misses Reports" to analyze chatbot performance and identify areas for improvement. Consider adding more relevant information to the knowledge base based on frequently asked customer questions and agent responses.
Reaching AI Chatbot / Token Limit:
Talkative licences the GenAI chatbot on a per-interaction model. You are allocated a set number of interactions per month. If you exceed this limit, your chatbot will not be able to query your knowledge base. You can monitor your usage in the "Billing and Usage" section and purchase additional interactions if needed.
How do I improve Chatbot Performance?
Keep Knowledge Base Up-to-Date:
Regularly review and update your knowledge base to ensure accurate and relevant information.
Utilise Custom Prompts:
Use custom prompts to guide customer interactions and improve the bot's ability to understand queries.
Analyse Chatbot Performance:
Regularly review the "AI Knowledge Base Lookups" and "AI Knowledge Base Misses Reports" to identify areas for improvement.