Thoughtly Community LogoThoughtly Community Icon
Join our Slack Community
  • 🏠Home
  • 👥Directory
  • 📅Events

  • 🏢Agencies
  • 📣Announcements
  • 🔁Automations
  • 🎁Best Practices
  • 💡Feature Requests
  • 📄General
  • 🔌Integrations
  • 🆘Support
  • 🤖Voice Agents
  • 🏆Wins

  • ⚖︎Community Guidelines

  • ↗Website
  • ↗Documentation
  • ↗Dashboard

Powered by Tightknit
Announcements

Introducing Mid-Call Actions: Join Our Beta for Real-Time Integration!

Avatar of Torrey Leonard
Torrey Leonard
November 28, 2024

Reading time: 1 minute

Hey @channel, we have an exciting release just around the corner! 🎉 Introducing Mid-Call Actions. Give your Agent the full ability to connect to other integrations, send custom webhooks, or book on a calendar in real-time during a phone call 🤯 Here are some details:

There are three main types of Actions on Thoughtly: 1. Pre-Call Actions: happen before a call, or may trigger a call to be made. (Automations ✅) 2. Mid-Call Actions: occur during a call in real-time while an Agent is speaking. (This! ⬅️) 3. Post-Call Actions: occur after a call ends. (Automations ✅) A Mid-Call Action is only required if you need to submit and return data during a call, such as for scheduling or user lookup. If you are simply creating or updating a lead in a CRM, sending an email or Slack message, or adding information to a database, these can often happen after a call.

Does this sound interesting to you? Signup for our exclusive beta and get access weeks before anyone else. Mid-Call Actions will be generally available by the end of December. Beta access is limited. Beta testing begins on Monday, December 2nd. [Signup Link]

🎉10

3 comments

  • Avatar of Ida Ma
    Ida Ma
    ·
    ·

    I am interested. Thank you for actively listening and making things easier for us.

    🙌2
  • Avatar of Lasse
    Lasse
    ·
    ·

    Signed up as well 🙏

  • Avatar of Ida Ma
    Ida Ma
    ·
    ·

    Torrey Leonard When will mid-call action be released? I can’t deploy the AI agent without SMS support or this feature. Right now, I’ve got neither. • SMS Issue: I can’t buy an AU mobile number, despite repeated attempts to get support. If I need to purchase one from Twilio and port it to Thoughly, I’m fine with that. But I need clarity:

    1. a.

      Can Thoughly accept an AU mobile number?

    2. b.

      What’s the cost once the number is ported? I want to avoid double charging by Twillio & Thoughtly.

    This isn’t just my problem—many AU users face the same issue. Agent Context Awareness I’m also trying to understand why the AI agent:

    1. a.

      Can’t retain context from previous conversations.

    2. b.

      Repeats conversations unnecessarily.

    3. c.

      Struggles with escalation handling.

    I’ve posted these issues in the support channels, but no one is responding. Here’s the full post and the questions I’ve raised and tagged Will Del Principe: I have rebuild the agent 2 more times after our chat. And, now facing issues with contextual awareness, escalation handling and repetition questions.

    1. a.

      I have noticed that when users provide answers to specific questions early in the conversation, the agent sometimes asks redundant or related follow-up questions instead of progressing contextually. Is there a way to configure Thoughtly to better recognise and retain contextual information from earlier parts of the conversation to avoid this? I have added rules & custom prompts to avoid unnecessary repetitions but it does not work.

    2. b.

      Thoughtly allows for custom prompts, additional rules, and conversation scripts. Can you clarify the best use cases for each? Specifically, where should I focus on injecting these elements to make the conversation flow more natural and context-aware?

    3. c.

      I’d like to implement escalation to a human agent at any point in the conversation where the user’s query falls outside the AI’s capabilities. Given Thoughtly’s process-driven approach and structured nodes, how can escalation be managed effectively to allow it to occur dynamically, regardless of the conversation step?

    4. d.

      Are there specific settings or features within Thoughtly that can help improve the agent’s adaptability to handle “off-script” responses without sounding robotic or redirecting unnecessarily to predefined questions?

    5. e.

      For conversation design, what are the best practices to ensure the AI agent can handle layered intents (e.g., when a user provides multiple pieces of information in one response) without breaking flow or asking redundant clarifications?