The briefing
Harnesses: where cheap models turn back into value
A harness is the memory, tools and loops wrapped around a model, and it now moves results more than the model does: the same model can swing dramatically in score and cost depending on the harness. This is where falling model prices turn back into value. Tanya Dixit of Google explains what a harness is and why a good one matters, shows examples from software engineering, finance and research, and maps the open ground: harnesses built for specific professions, and harnesses that improve themselves.
About Tanya Dixit
Tanya Dixit is a Forward Deployed Engineer at Google, partnering with enterprise customers across APAC to ship production AI systems. Her work spans agentic AI, voice AI, and multimodal architectures, with deep focus on banking, financial services, and healthcare. She also supports Google's university partnerships program in healthcare AI. Based in Sydney, Tanya writes and speaks regularly on moving voice and agent systems from demo to production reliability.