Building an agent that works once is easy; building an agent that works reliably for thousands of users is an architectural challenge. This session bridges the gap between experimental notebooks and deployed systems, focusing on the specific engineering disciplines needed for success. Join us to learn practical strategies for: 1. System Design: architecting decoupled, scalable agent backends from day one. 2. Continuous Evaluation: moving beyond "vibes-based" testing to metrics-driven evaluation suites that ensure reliability. 3. DevEx & Tooling: streamlining the developer experience to tighten feedback loops and ship improvements faster using open-source frameworks.
What this session is about
Live updates related to this session LIVE
Sourced via Parallel AI Monitor — continuous web watch on 21 topical streams. Updated .
- callsphere.ai high confidence Scaling infra for agent workloads
Scaling AI Agents to 10,000 Concurrent Users: Architecture ...
CallSphere published a detailed architectural guide on scaling AI agents to 10,000 concurrent users, outlining the use of a Gateway Layer, stateless Agent Worker Pools with Redis session state, and LLM Connection Pools with async semaphores to manage API load and concurrency.
- azion.com Scaling infra for agent workloads
Understanding Agentic AI Infrastructure
Gravitee published an update explaining that the stateless Model Context Protocol (MCP) specification simplifies horizontal scaling for agent workloads. The update also highlights AI gateway governance as a way to manage agent tool traffic, security, and scaling across MCP-based
- axell.ai Scaling infra for agent workloads
AI Kill Switch Act: $20M/Day Fines Won't Stop Your Agents
Waxell published a post on 2026-07-29 titled 'AI Kill Switch Act: $20M/Day Fines Won't Stop Your Agents — Closing the Enterprise Kill-Switch Gap' discussing the architectural need for an enforceable kill switch in the agent's execution path. It highlights that a 'stop' decision m
- axell.ai Scaling infra for agent workloads
AI Agents Touch 2x Approved Data: 1Password Survey [2026]
Waxell published a post on 2026-07-29 titled 'AI Kill Switch Act: $20M/Day Fines Won't Stop Your Agents — Closing the Enterprise Kill-Switch Gap' discussing the architectural need for an enforceable kill switch in the agent's execution path. It highlights that a 'stop' decision m
- axell.ai high confidence Scaling infra for agent workloads
Waxell Blog — Agentic Governance for AI Teams
Waxell published a post on 2026-07-24 titled 'Speakeasy vs Waxell: MCP Gateway Governance vs. a Full Control Plane,' discussing the architectural difference between gating MCP tool calls at the gateway (Speakeasy) versus extending enforcement across the entire agent lifecycle (Wa
External links matched to this session via topic relevance. The KB does not endorse third-party content; verify before citing.