AI you can talk to, that answers fast enough to feel like a conversation.
Voice agents live or die on timing. I build pipelines around a latency budget — speech in, reasoning and tools in the middle, speech out — with turn-taking and interruption handled properly.
Customer support
Speech in, reasoning and tool calls in the middle, ElevenLabs speech out. Most of the engineering is about timing — a reply that arrives a beat late stops feeling like a conversation — so the pipeline is built around latency.
Contact
I'm open to AI engineering, architecture and training work. Tell me what you're building and what the constraints are — that's usually enough to start.