How the Agent Works
The Core Principle
The Agent only knows what you give it. It has no access to the internet, can't browse websites on its own, and won't make things up. Every answer it gives comes from one of two sources:
- Knowledge you've added to its Places (hotel info, policies, FAQs, documents, reviews)
- Guest context from connected external sources like the TrustYou CDP (booking details, stay history, preferences)
If the information isn't there, the Agent is designed to acknowledge that it doesn't know or hand over to a human rather than improvise an answer.
Knowledge vs Features
This is the most important distinction to understand.
Knowledge: what the Agent knows
Knowledge is the content you add to Places as Resources. Think of it as the Agent's reference library. It includes things like:
- Hotel descriptions and amenity lists
- Policies (cancellation, check-in/check-out, parking, pets)
- FAQs and local tips
- Website content you've pointed the Agent to
- Guest reviews and feedback
When a guest asks a question, the Agent searches through this knowledge to find relevant information. It uses semantic search, meaning it understands the meaning of the question, not just keywords. If a guest asks "Can I bring my dog?" the Agent will find your pet policy even if it never uses the word "dog."
The Agent searches across all the Places you've assigned to it, but only those Places. That's how you control what each Agent knows and talks about.
Features: what the Agent can do
Features are capabilities you turn on or off in the backoffice. They don't add knowledge. They add abilities. For example:
- Human Handover lets the Agent route a conversation to your team when it can't help
- Quick Actions adds shortcut buttons to the chat interface
- Personalized Welcome Messages lets the Agent greet guests differently based on context
- Guest Context lets the Agent access a guest's personal data from connected sources
You decide which Features to enable for each Agent. The Agent can only use the ones you've turned on. It can't decide on its own to enable a Feature.
A simple way to think about it: Knowledge is what the Agent reads. Features are what the Agent does.
How a Conversation Flows
Here's what happens behind the scenes when a guest sends a message:
1. The message arrives
A guest writes something through your website widget, SMS, or WhatsApp. The Agent receives the message along with the conversation history.
2. Guest context loads
If the Guest Context Feature is enabled and there's a linked guest profile (from the TrustYou CDP or another connected source), the Agent loads that guest's personal data: booking details, stay dates, preferences, past interactions. This happens automatically at the start of the conversation.
3. Knowledge search
The Agent searches the Knowledge Base of its assigned Places for information relevant to the guest's question. This is a semantic search. It looks at all assigned Places at once and pulls the most relevant pieces of content.
4. Response generation
The Agent puts it all together: the guest's question, the conversation so far, any guest context, the retrieved knowledge, and your custom instructions. It generates a response that's grounded in what it found, styled to your configured tone of voice.
5. Handover check
If the Agent determines it can't help (the question is outside its knowledge, the guest asks for a human, or a handover rule you've configured is triggered), it routes the conversation to your team instead of responding. Handovers go to the email address or ticketing system (like Freshdesk) you've configured.
What the Agent Can't Do
Understanding the limits is just as important as understanding the capabilities:
- No internet access. The Agent can't browse the web, search Google, or fetch information from external websites. It only works with the knowledge you've provided.
- No memory across conversations. Each conversation starts fresh. The Agent doesn't remember past chats with the same guest (unless that history is available through guest context from a connected source).
- No self-configuration. The Agent can't enable or disable its own Features, add knowledge, or change its settings. You control all of that from the backoffice.
- Grounded in your knowledge. The Agent is designed to base its answers on the knowledge you've provided. While AI responses can occasionally be imprecise, the Agent prioritizes accuracy and will typically defer to a human rather than speculate.
Custom Instructions Shape Behavior
You can write custom instructions for each Agent to fine-tune how it behaves. These instructions become part of the Agent's core prompt, shaping things like:
- What topics to prioritize or avoid
- How to handle specific types of questions
- When to suggest a booking or upsell
- What tone to use in certain situations
Custom instructions don't change what the Agent knows. They change how it uses what it knows. Think of them as coaching notes for the Agent's personality and approach.
Putting It All Together
Here's the full picture:
- You create Places and fill them with knowledge (Resources)
- You create an Agent and assign it to the right Places
- You enable Features to give the Agent capabilities (handover, quick actions, guest context)
- You write custom instructions to shape how the Agent communicates
- You connect Channels (website, SMS, WhatsApp) so guests can reach the Agent
- Guests start chatting. The Agent searches its knowledge, uses its enabled Features, and responds within the boundaries you've set.
The Agent is the bridge between the knowledge you've curated and the guest asking a question. You control what goes in. The Agent handles how it comes out.
What's Next
- Creating Your First Agent -- set up your first Agent step by step
- Understanding Your Agent's Knowledge: Places and Resources -- go deeper on the knowledge side of the model
- Adding a Website Resource -- start building knowledge from your website
- Adding Document and Markdown Resources -- add knowledge from files or write it directly
Comments
0 comments
Please sign in to leave a comment.