At the time of the conversation, Mehmet Murat Ezbiderli was building AI at ServiceTitan. He joined the enterprise AI deployment panel on Chain of Thought to share firsthand lessons on cost, model selection, and the trade-offs of shipping GenAI systems at scale.
What this guest adds
Mehmet Murat Ezbiderli says model selection at ServiceTitan has to account for LLM costs alongside stronger capabilities. Read transcript at 35:00
Open Source AIRAG & RetrievalAI Evaluation & ReliabilityAI ObservabilityEnterprise AI
Latest episode with Mehmet Murat Ezbiderli · EP 6
The Enterprise AI Deployment Playbook | ServiceTitan, Indeed & Twilio
Mehmet Murat Ezbiderli, Vinnie Giarrusso, Grant Ledford & Atindriyo Sanyal ·