Skip to main content

Overview

Chat agents handle every written channel—Instagram DMs, Facebook Messenger, web chat widgets, SMS, WhatsApp, and email. We’ve already created the baseline agents for you. This guide shows how to safely tweak prompts, tools, integrations, and advanced settings so you can iterate without spinning up brand-new agents from scratch.

Step 1: Review the Agents Tab

Head to the Agents tab to view everything we’ve launched for you. Each tile reflects the campaigns our team maintains.
Chat Agents Dashboard

Edit the Prompt

We seeded each agent’s prompt based on your onboarding brief. You can adjust wording, tone, or business rules directly in the editor—just follow the checklist below and remember to loop us in if the changes are significant.
Chat Agent Prompt Editor

What to Include:

  1. Agent’s Role – Who should the agent represent? (e.g., “You are a friendly customer service representative for XYZ Company”)
  2. Tone & Personality – Formal, casual, enthusiastic, empathetic, etc.
  3. Goals – What outcomes matter most? (qualify leads, book appointments, answer FAQs)
  4. Tool Usage Instructions – Call out when to use connected tools, e.g.:
When a customer wants to book an appointment, call the book_appointment tool.
When you need to check inventory, use the check_stock tool.
After editing, click Save and run a quick test conversation in the preview window. If you’re making a large strategic change, notify your strategist so we can review analytics after the update.

Manage Tools and Automations

Tools give your chat agent superpowers—booking appointments, pushing data to CRMs, fetching live information, and more. You can enable/disable existing tools, update configuration values, and add new ones from the Tool Library.
Use this when you need a bespoke workflow. Paste the webhook URL, select the method (GET, POST, etc.), add headers, and define the request/response formats. Test after saving to ensure the agent calls it successfully.
Custom URL Tool
Use Cases:
  • Send lead data to your CRM
  • Trigger automations in Zapier or Make
  • Connect to third-party APIs
  • Update external databases
Browse the ready-made automations. Toggle on the ones you need, fill in required configuration fields (API keys, calendar IDs, etc.), and hit Save. Reach out if you need a tool that isn’t listed—we can usually build it quickly.Available Tools:Cal.com Integration:
  • Cancel or Reschedule Booking – Cancel or reschedule a booking made in Cal.com
  • Fetch Free Slots – Fetch free slots between two dates for a specific event type
  • Get User Bookings – Get a list of bookings for a specific user so you can reschedule or cancel it
GoHighLevel Integration:
  • Cancel or Reschedule Appointment – Cancel or reschedule a specific appointment to a later date
  • Fetch Free Slots – Fetch a list of free slots for a calendar within a specific time range
  • Find Or Create Contact – Find or create a contact to use for appointment booking and other functions
  • Get Booked Appointments – Retrieve a list of booked appointments for a contact
Popular Tools:
  • Book AI Callback – Allow agents to call users back at a later time
  • Get Current Time – Get the current time for a given timezone in ISO 8601 format
  • Send SendGrid Email – Integrate SendGrid to send emails directly from your agent
  • Send Twilio SMS – Integrate Twilio to send text messages directly from your agent
  • Solar Savings (US Only) – Calculate estimated savings of switching to solar based on monthly bill and address
Tool Library
The tool library grows constantly. We’ll flag new additions that align with your campaigns.
Keep calendar booking connected so the agent can check availability and schedule appointments automatically. Adjust calendar IDs or buffer times if your availability changes.Currently Supported:
  • ✅ GoHighLevel calendars
  • ✅ Cal.com
Coming Soon:
  • 🔜 HubSpot
  • 🔜 Salesforce
Calendar Booking Tool
What the agent can do:
  • Check real-time availability
  • Book appointments
  • Reschedule existing bookings
  • Cancel appointments
  • Send confirmation messages
Need advanced integrations? You can add an MCP server URL from Zapier to unlock thousands of apps. If you’d like us to host/manage the MCP server, just provide the app list and we’ll take care of it.Our setup process:
1

1. Access Zapier MCP

We log into mcp.zapier.com with the integration account you provide or invite us to.
2

2. Create New MCP Server

Our team creates the server and selects Other as the MCP client type, tailored to Aidan’s platform.
Create MCP Server
3

3. Add Tools from 8,000+ Apps

We add the tools your workflow needs. Popular options include:
  • Google Sheets – Search, create, and update spreadsheets
  • Gmail – Send emails and manage inbox
  • Slack – Send messages and create channels
  • HubSpot – Manage contacts and deals
  • Salesforce – Update records and create tasks
  • Airtable – Query and update databases
4

4. Connect Apps

We authenticate or guide your team through OAuth so the MCP server can access each app securely.
Select MCP Tools
5

5. Share Server URL

After configuration we capture the MCP server URL and keep it on file for ongoing management.
Copy MCP Server URL
6

6. Connect Inside Aidan

Paste the server URL into the MCP Server field for the agent and select which tools it can access.
MCP Server in Aidan
7

7. Select Specific Tools

Choose which tools from your MCP server to make available to your chat agent.
Select Tools for Agent
Example Use Cases:
Search customer data during conversations:
  • Look up customer information from spreadsheets
  • Update appointment bookings in real-time
  • Track conversation outcomes and lead quality
Update customer records:
  • Create new contacts during conversations
  • Update deal stages based on chat interactions
  • Add conversation notes and follow-up tasks
Send follow-up messages:
  • Email appointment confirmations
  • Send Slack notifications to team
  • Create tasks in project management tools
Advanced Features:
  • Real-time Data Access – Query live data during conversations
  • Multi-app Workflows – Chain actions across different services
  • Custom Authentication – Secure access to your business tools
  • Error Handling – Graceful fallbacks when tools fail
Pro Tip: Start with 2-3 essential tools and gradually add more as you become comfortable with MCP integration. Too many tools can slow down response times.
MCP servers provide a standardized way for AI agents to interact with external tools and data sources. Zapier’s MCP integration gives you access to 8,000+ apps without custom development.

Platform Integrations

Use this panel to check which channels are active. You can toggle channels yourself, but we recommend alerting us so we can confirm routing rules and update analytics dashboards.
Platform Integrations

Available Channels:

Instagram DMs

We enable coverage for Instagram direct messages tied to your Business Account.

Facebook Messenger

Messenger conversations route through the agent once we activate your page connection.

Email

We can automate branded email replies using your verified sending domain.

SMS

Two-way SMS powered by the numbers our telephony team manages for you.

WhatsApp

Managed WhatsApp Business messaging with templated responses and opt-in flows.

Web Chat

We’ll provide embed code so your web team can add the widget wherever needed.
Before turning a channel on, make sure the connected platform (e.g., Facebook Page, Instagram Business account) is authenticated and you’re ready for the agent to respond to all new conversations.

Triggers for Campaigns & Keyword Flows

Triggers give you precise control over when your agent should respond. Tell us the keywords or flows you need and we’ll configure them.

How Triggers Work:

  1. We add a trigger word or phrase (e.g., “start”, “book”, “info”)
  2. The agent only wakes up when the incoming message matches the trigger
  3. Messages that don’t match the trigger are ignored by the AI

Example Use Cases:

“DM me START to claim your free voucher!”The agent only responds to messages containing “start”, ignoring casual comments and other DMs.
  • “book” → Activate booking agent - “support” → Activate support agent
  • “refund” → Activate refund agent
Ask us to add a trigger so the AI stays quiet when you’re personally chatting with VIP clients.
Want full coverage? We’ll remove triggers so every message receives an instant response.

Delay Settings

We use response delays to make conversations feel natural. Here’s how we tune them together.

Configuration:

  • Minimum delay – The shortest time before the agent responds
  • Maximum delay – The longest time before the agent responds
  • We randomize the actual delay between these values

Instant Response

Min: 0 seconds Max: 5 seconds For time-sensitive inquiries or customer support

Human-like Response

Min: 30 seconds Max: 120 seconds For conversations that should feel natural and unhurried

Casual Response

Min: 2 minutes Max: 10 minutes For lower-priority channels or when mimicking a busy human

Business Hours Simulation

Min: 15 minutes Max: 60 minutes For email responses or non-urgent inquiries
Why randomize? A fixed delay (e.g., always 60 seconds) feels robotic. Random delays make the agent feel more human and authentic.

Knowledge Base

Keep the knowledge base fresh so the agent always references accurate information. You can add content yourself or ask us to handle larger updates.
Click Upload File, drop in PDFs, DOCX, CSV, TXT, or Markdown files, and hit Save. The agent will ingest the content automatically. For sizeable handbooks, let us know so we can confirm token usage.
Use Add Source → Website to scrape live pages. Paste the URL, choose whether to follow links, and save. Great for product pages, help centres, or menus that change often.
For quick updates, open Add Source → Paste Text, drop in the instructions, and save. Perfect for promotions, objection handling, or limited-time messaging.
After adding material, run a quick test conversation to ensure the agent retrieves the new information. If you spot gaps or hallucinations, DM your strategist—we can adjust relevance weights or restructure the content.

Agent Settings

You have access to all advanced settings. Feel free to tweak them as your campaigns evolve—just document what you change (we recommend noting it in Slack) so we can help monitor results.

Time Zone

Open Settings → General and pick the time zone that matches your audience. This keeps statements like “tomorrow at 3pm” accurate. Update it any time you enter a new market.

Model Selection

Choose the AI model that powers your agent. Use the dropdown in Settings → Model and click Save. Each option balances speed, reasoning, and cost differently.
Model Selection
OpenAI’s flagship model with superior performance.
  • 🎯 Superior reasoning ability
  • 📚 Better handling of complex knowledge bases
  • 💡 More creative responses
  • 💸 Higher cost per conversation
Pricing: ~$0.015 per conversationBest for: High-value conversations, complex product lines, technical support
Ultra-cheap, only for very basic auto-responses.
  • 🏃 Extremely fast
  • 💵 Very low cost
  • ⚠️ Limited reasoning ability
  • 📝 Best for simple, scripted responses
Pricing: ~$0.001 per conversationBest for: Simple FAQs, basic greetings, keyword-based responses
Premium accuracy with advanced reasoning capabilities.
  • 🔍 Can search the web in real-time
  • 🎓 Exceptional reasoning and problem-solving
  • ⏱️ Slower response times (5-15 seconds)
  • 💎 Premium pricing
Pricing: ~$0.05 per conversationBest for: Research-heavy conversations, fact-checking, complex technical queries
Cost Management: Higher-tier models can significantly increase spend. Start with GPT-4.1 and only upgrade if the business case warrants it. If you’re unsure, ask us to review projected volumes with you.

Embed Code

We provide the HTML snippet you can hand to your web team to embed the chat widget on any site.
Embed Code

How to Use:

  1. Copy the HTML snippet from the Embed Code section (or ask us to send it to your developer)
  2. Add it to your website’s HTML just before the closing </body> tag
  3. The chat widget will appear automatically once published

Example Code:

<script
  src="https://app.callaidan.com/widget/chat.js"
  data-agent-id="6531f2d6-7067-458b-a782-2cae809a7dc6"
  data-open="false"
  async
></script>
Copy the snippet directly from the agent’s Embed Code section so the data-agent-id value matches the agent you’re using.
Customization: Want it on-brand? Let us know and we’ll provide CSS or coordinate directly with your developer.

Initial Message

Set the first message contacts see when they open the chat widget. Update the text inside Embed Settings → Initial Message and click Save.

Example Initial Messages:

”👋 Hi there! How can I help you today?”
”🎉 Welcome! Ask me about our special promotion—20% off all services this week!”
“Hi! I’m here to help you find the perfect solution. What brings you here today?”
“Ready to book your appointment? I can check availability and get you scheduled in seconds!”
The initial message only appears in the web chat embed. Other platforms (Instagram, SMS, etc.) start with the user’s message instead.

Interrupt Mode

Interrupt Mode lets your human team take over a conversation instantly. Toggle it under Settings → Behaviour whenever you need to change availability.

How It Works:

When Interrupt Mode is enabled:
  1. ✅ The AI agent handles all conversations automatically
  2. 👤 A human team member sends a manual message in GoHighLevel
  3. 🛑 The AI agent is immediately interrupted for that contact
  4. 🙋 The human takes over the conversation
  5. 🤖 The AI stays silent unless manually reactivated

When to Enable:

Enable Interrupt Mode

Best for most use cases: - Gives your team flexibility to jump into conversations - VIP clients get personal attention - Complex situations get routed to humans instantly - You can hand conversations back to the AI when you’re ready

Disable Interrupt Mode

When you want full automation: - Always-on support channels - After-hours campaigns - High-volume, low-touch scenarios - Controlled testing of agent performance
We recommend enabling Interrupt Mode during business hours so your team can step in, then disabling it after hours for full automation.

Test & Publish Safely

  1. Use Test Agent inside the editor to run through the scenario you just updated.
  2. If the change touches external systems, place a live test (or have us do it) to confirm logs, tools, and delays behave as expected.
  3. Monitor the first few conversations in Call Logs. If anything feels off, revert the edit or message us immediately.

Best Practices

We launch with a focused use case, validate performance, then layer in additional tools and channels based on results.
The more specific your notes, the better the conversations. Send us sample transcripts, objection handling, and brand guidelines so we can keep prompts razor sharp.
Our team runs structured tests across every channel. When you review transcripts, flag anything that feels off—we’ll iterate quickly.
We monitor logs, scoring, and campaign metrics to surface improvements. Expect proactive recommendations in your strategy calls.
We recommend delay settings based on channel intent and audience expectations, then adjust as results come in.

Troubleshooting

Double-check the channel toggle, ensure the agent isn’t paused, and confirm triggers aren’t blocking the message. If everything looks good, share the contact link with us and we’ll investigate.
Review the prompt and knowledge sources for outdated messaging. After adjusting, retest the conversation. Still off? Send us the transcript so we can fine-tune retrieval and guardrails.
Reopen the tool, confirm credentials/API keys are current, and run a manual test. Provide the contact and timestamp if you need us to audit logs.
Adjust the minimum/maximum delay in Settings → Behaviour. If responses still feel unnatural, note the channel + scenario and we’ll help tune it further.
Confirm the toggle state, make sure the manual message was sent from a human profile (not the AI), and refresh the thread. If it continues, ping us so we can review permissions.

Next Steps

Ready for the next round of improvements? Here’s how to partner with us: