Back to list
New Conversation Flow Agent, Bot Builders Office Hour

Conversational Flow

We’ve launched the beta version of our Conversation Flow!

This new tool provides much finer control over conversation flows compared to single or multi-prompt agents, unlocking the ability to handle more complex scenarios with ease.

Key Features:

  • Dynamic LLM Selection: Change the LLM for each individual node to tailor responses as needed.
  • Precise Response Control: Fine-tune the exact words spoken during and after each function execution.
  • Enhanced Node and Transition Definitions: Define edges and transitions with greater accuracy to create seamless interactions.

Highlights:

  • Usage-Based Pricing: Call pricing is calculated based on the number of seconds spent within each node, providing transparent cost breakdowns.
  • User-Friendly Interface: Replace prompt engineering with an intuitive, graphical input system for building agents.
  • Minimized Hallucination Risks: Built-in ultra-guidance mechanisms to ensure accurate and reliable responses.

Get started with a pre-built template today and share your feedback with us!

See Docs

Don’t Miss Our Next Bot Builders Session!

We received fantastic feedback from the last session, and we’re excited to bring even more value this time. If it’s not already on your calendar, make sure to save the date!

What to expect:
1️⃣ Live troubleshooting for Retell voice bots
2️⃣ Integration help for your projects
3️⃣ Best practices and advanced use cases
4️⃣ Networking with fellow bot builders
5️⃣ Sharing successful case studies

🕒 Time: Friday, 2 PM Pacific Time
📍 Location: Our Discord Channel: https://discord.com/invite/DTzvrQfncB

Join Discord

Other Improvements

1. Ringtone when having warm transfer.
• A ringtone is now available during warm transfers for a smoother experience.
Note: For cold transfers with the option to show the transferee’s number, there is currently no ringtone. This issue will be resolved within 1 week.

2. DTMF from user now can show in transcript

• User-entered DTMF inputs are now captured and included in the call transcript for improved usability.