The November 2025 MCP spec release introduced tasks, a way to make tool calls in an async manner. But more than 5 months later (an eternity in AI-time) there are still NO clients that support it - not Claude, not Codex, not even goose! I believe there are two reasons: Designing the client experience when there are potentially 1000s of background tasks running on their own schedule and engaging humans at unpredictable times is a challenge. And tasks place new infrastructure requirements on such a client. This talk will share the findings from having built against the tasks protocol and will suggest solutions these problems. Yup, we'll have a working client!
Context Engineering sessions at AI Engineer World's Fair 2026 in San Francisco.
Wednesday, July 1, 2026
2:50 PM - 3:10 PM·20m
Track 8 · Room 2020
Capacity: 250 attendees
Sign in to add this talk to your schedule.

Cornelia Davis
Sr. Staff Developer Advocate
Temporal
@cdavisafc
Cornelia's career has spanned several major shifts in software, from image processing algorithm development to web-centric computing in the late 90s, and then more than a decade working in cloud-native software, infrastructure and platforms (Cloud Foundry, Kubernetes and friends). Those experiences in distributed systems, combined with a longstanding interest in programming models, led her to Temporal where she is helping to bring a new programming paradigm to an industry that was increasingly in need of one - a need that has accelerated dramatically with the advent of modern AI systems. Much of her work today focuses on the architectural needs and evolving practices of these AI systems. Her current research explores asynchronous processing and the development of AI-native distributed systems abstractions, with an emphasis on the emerging patterns and programming models shaping this new era of software. She is the author of Cloud Native Patterns: Designing Change-Tolerant Software.