Hey PH! We’re Chetan, Akshay, and Andrew, and we’re the creators of Elixir - a platform that provides automated testing and call review for your AI voice agent. We built Elixir while trying to solve some of our own problems when building Code Coach, an AI technical interviewer. We found ourselves spending significant time manually listening to calls for issues ranging from interruptions and transcription errors to user frustrations and poor conversation experiences, as well as trying to test the agent on different scenarios to make sure it wouldn’t break. That’s where Elixir comes in: ✔ Track call metrics and identify mistakes at scale. Streamline your manual review process with call auto-grading ✔ Simulate 1000s of calls to your voice agent for full test coverage across different languages, accents, speech patterns and more ✔ Debug issues quickly with the help of audio snippets, LLM traces, and transcripts With multimodal models like GPT-4o right around the corner, we believe voice agents will grow in capability and complexity, making testing and call review even more important for reliability. We’re excited for you to try it out and are looking forward to hearing your feedback in the comments!

Congrats on the launch! I'm excited to try out Elixir - building reliable voice AI apps is super hard, so I'm glad there's a strong team solving this!

Comment Deleted

I'm interested to see how it performs in real-world circumstances and how it might be applied to other workflows.