Butterfly effects cripple AI agents. But there's an art to failure. Multi-step evaluations for conversational agents are fundamentally different from classic single-call evaluations. When a voice agent needs to perform multiple tool calls without human intervention, one small

🚀 Optimizing Voice AI with Coval + Retell AI 🚀 Are you building your voice agents with Retell AI? Then you'll be excited about this partnership! Coval & Retell AI join forces to enable infrastructure for end-to-end voice agent reliability. Why should you use Coval for testing

When you want to launch your new voice agent but you haven’t run any evals yet...

🔒 Proud to announce that Paweł is now HIPAA compliant! Healthcare stands at the forefront of the voice AI revolution. From improving patient care to streamlining clinical workflows, voice AI is fundamentally reshaping the healthcare industry. This makes security and compliance

🎉 Excited to announce that coval and langfuse.com are officially integrated - so you can test & debug Voice AI with confidence. Voice agents require both conversation-level testing + message-level observability to be production-ready. Our integration bridges this gap, giving

Cartesia's latest model Sonic 2.0 just dropped and the coval team couldn't wait to try it out, so we already ran some benchmarks. Some of our takeaways: ⚡ Sonic 2.0 is lightning fast 🔢 Cartesia has gotten way better at alphanumeric sequences ($52,000, [email protected], )

Coval + Rime: Bringing Lifelike Voices to AI Simulation Excited to announce our new integration with Rime! 🎉 Coval's mission is to provide the most comprehensive voice simulation platform for testing AI agents, and today we're adding Rime's incredibly lifelike voices to

🎙 OpenAI’s dropped new voice AI Models- get Coval's scoop and see the benchmark results 🫢 OpenAI just dropped a new text-to-speech model, We’ve been testing gpt-4o-mini-tts and the prosody, pronunciation, and controllability are next-level. 💭 Prosody that feels real: The

The folks at coval did a deep dive with our audio models, some great examples of pronunciation with difficult words

very detailed and fair evals and impressions on the new STT+TTS models. thx coval

don't miss that OAI also published a prompting guide WITH RECEIPTS for GPT 4.1 specifically for those building agents... with a new recommendation for: - telling the model to be persistent (+20%) - dont self-inject/parse toolcalls (+2%) - prompted planning (+4%) - JSON BAD - use

🎉 Exciting News! Please join us in welcoming Kobi Hudson to the Coval team! Prior to Coval, Kobi spent 8 years at Waymo working alongside our own Brooke, where he played a pivotal role in building Waymo's early simulation infrastructure - some of the foundational systems

🎙️ Testing non-deterministic AI requires a new approach. Forget exact outputs; it's about probabilistic success. Brooke Hopkins of coval breaks down the shift on the latest Generationship episode. Tune in! 🎧 hubs.ly/Q03kj05Z0

🎉 Exciting News! Please join us in welcoming Loren Phillips to the Coval team! Before joining Coval, Loren worked on autonomous vehicle safety validation at Zoox, Amazon’s self-driving subsidiary. He also brings a diverse research background spanning nanophotonics, soft

🧵 This week in conversational AI: 🎤 OpenAI Realtime takes a big step forward — sub-500ms latency, sharper function calling, non-verbal cue detection, seamless language switching, and SIP (telephony) support. Already benchmarked at coval.ai, and the gains on

🎉 Exciting News! Please join us in welcoming Rob Young to the Coval team! Before joining Coval, Rob designed products at Google and Apple, and founded and led the product design studio OM. He brings a wealth of experience crafting elegant, user-centered experiences at some of