@thdxr: i'm working on some sdk design for v2 what i keep coming back to is not fully understanding one segment of the usecase …
Summary
A developer is working on SDK v2 design and inquiring about the use case of supporting millions of agents, asking for input from those building such products.
View Cached Full Text
Cached at: 05/16/26, 09:23 PM
i’m working on some sdk design for v2
what i keep coming back to is not fully understanding one segment of the usecase
every infra company is prepping for “millions of agents to run on us”
are you working on a product that needs this? tell me more
Similar Articles
Customer discovery insights from talking to operators about agent products - looking for builder perspective
Insights from customer discovery interviews with operators about AI agent products, seeking perspectives from builders.
@kentcdodds: Good DX is good UX when agents are users. My chat with @RhysSullivan on Executor, MCP, and product primitives.
Kent C. Dodds discusses a conversation with Rhys Sullivan about Executor, MCP, and product primitives, emphasizing that good developer experience for AI agents translates to good user experience.
Anyone actually running AI agents in production with real users - not demos, not 10 beta testers. What's your stack? And has anyone moved back to traditional code after trying agents in prod - why?
A discussion prompt asking about real-world AI agent deployments with 100+ users, covering tech stacks and scaling issues, plus experiences of moving back to traditional code.
Has anyone else noticed that the hardest part of building agent workflows isn't the model anymore?
A developer observes that the biggest challenge in building agent workflows has shifted from models and prompts to maintaining context, business rules, and external data synchronization, and asks the community about their primary bottleneck.
@googledevs: Most agent demos are stateless. Ask → answer → context gone. Production agents need to run for days — pausing, resuming…
Google Devs introduces Agent Factory series with ADK 2.0 and Gemini 3.5 Flash, demonstrating how to build production-grade stateful agents that can run for days, featuring insights on skills, MCP, and code review strategies from engineers like Rohde Davis.