--- title: "Scaling Agents, Paying the Bill" newsletter: "MLOps Community" date: 2026-07-30 source: https://aaif.live/newsletters/mlopscommunity/2026-07-30-scaling-agents-paying-the-bill --- # Scaling Agents, Paying the Bill *Plus MCP migration, latency design, and agent benchmarks* *MLOps Community — Agentic AI Foundation, 2026-07-30* Like Justin’s career after cutting 80% of *NSYNC [https://www.ycrootaccess.com/p/boris-cherny-building-claude-code?r=2yz3fo&selection=32990103-28c1-466f-a165-067dd960ca3f&utm_campaign=post-share-selection&utm_medium=web&aspectRatio=instagram&textColor=%23ffffff&bgImage=true&triedRedirect=true#:~:text=%20You%20actually%20deleted%20over%2080%25%20of%20the%20system%20prompt%20from%20Claude%20Code]. Just don't mention the tour. ## Frequent f-Liar Low-value hallucinations may be cheaper to tolerate than prevent. What should guardrails minimize: Frequency or Consequence? [FREQUENCY](https://go.mlops.community/NL_HT1_Jul30) [CONSEQUENCE](https://go.mlops.community/NL_HT1_Jul30) ## Tough Call Models aren't the only ones who struggle to make a call - a dead 50/50 on whether the server or client should own tool overload. ## Curated finds to help you stay ahead ## Five Guides to the New Specification ## MCP 7-28 The MCP community marked the 7-28 release with launch parties around the world this week. To help teams understand what changed and plan their transition, we’ve collected five AAIF blogs covering migration, stateless architecture, platform governance, deprecation, authorization, and long-running tasks. MCP 2026-07-28: What’s Changing and How to Migrate [https://aaif.io/blog/mcp-2026-07-28-whats-changing-and-how-to-migrate] A practical migration guide to the release’s stateless core, Tasks and MCP Apps extensions, authorization changes, and deprecations, with concrete checks for MCP client and server maintainers. Migrate Sessions to Stateless Requests with MCP 2026-07-28 [https://aaif.io/blog/migrate-sessions-to-stateless-requests-with-mcp-2026-07-28] A code-led TypeScript migration guide showing how to replace session IDs and transport registries with per-request server instances, explicit state handling, standard load balancing, and controlled legacy-client support. 7-28 Hands MCP to Platform Teams [https://aaif.io/blog/7-28-hands-mcp-to-platform-teams] A platform engineering guide to the release’s stateless architecture, authorization boundaries, schema validation, and observability changes, with practical steps for governing and scaling MCP services. MCP Just Handed You a Deprecation Policy. Steal It. [https://aaif.io/blog/mcp-just-handed-you-a-deprecation-policy-steal-it] A practical framework for applying MCP’s new feature lifecycle to internal tools and connectors, covering ownership, versioning, migration paths, sunset dates, and communication with dependent teams. MCP Graduates to Enterprise Infrastructure [https://aaif.io/blog/mcp-graduates-to-enterprise-infrastructure-stateless-architecture-formal-governance-and-security] A broad technical overview of MCP’s stateless architecture, authorization hardening, formal feature lifecycle, and official extensions for interactive interfaces and durable long-running operations. More MCP on August 6 Couldn’t make one of the launch parties, or still working through what 7-28 means for your systems? MCP Jam is a free virtual event on August 6, featuring technical talks, live demos, and lessons from developers, maintainers, and platform teams building with MCP. Register here [https://home.mlops.community/home/events/a-virtual-mcp-community-event-for-ai-builders-14x29g2kqp] ## JOB OF THE WEEK ## What an Anthropic Engineer Thinks About MCP MCP’s biggest protocol change removes persistent server sessions, clearing a major scaling obstacle for deployments handling millions of requests. * Stateless transport lets load balancers move requests between servers without synchronizing session data. * Multi-round-trip requests carry required context across tool calls while preserving agent state. * SDK updates should keep migrations small, while tool search and programmatic calling reduce context bloat. The release shifts MCP closer to standard web infrastructure without stripping away the state agents still need. [https://podcasts.apple.com/gb/podcast/what-an-anthropic-engineer-thinks-about-mcp/id1505372978?i=1000778566450](https://podcasts.apple.com/gb/podcast/what-an-anthropic-engineer-thinks-about-mcp/id1505372978?i=1000778566450) [https://home.mlops.community/home/videos/what-an-anthropic-engineer-thinks-about-mcp](https://home.mlops.community/home/videos/what-an-anthropic-engineer-thinks-about-mcp) [https://open.spotify.com/episode/62rPUXq0cmYfwJLKr7UGhs?si=jETIPse0SIOlTgS_9X98IA](https://open.spotify.com/episode/62rPUXq0cmYfwJLKr7UGhs?si=jETIPse0SIOlTgS_9X98IA) ## AI Hype vs. Real Value AI projects can look productive until token and compute bills erase the gains. The discussion argues that real value comes from redesigning complete workflows, rather than scattering pilots across the business. * Compare AI-assisted teams with control groups and measure changes in speed, cost, revenue, or output. * Match models to tasks, limit token use, and apply FinOps at workflow level. * Keep humans involved in sensitive decisions, then reduce oversight as accuracy improves. AI pays off when workflow gains survive cost and risk checks. [https://podcasts.apple.com/gb/podcast/ai-hype-vs-real-value/id1505372978?i=1000778227428](https://podcasts.apple.com/gb/podcast/ai-hype-vs-real-value/id1505372978?i=1000778227428) [https://home.mlops.community/home/videos/ai-hype-vs-real-value](https://home.mlops.community/home/videos/ai-hype-vs-real-value) [https://open.spotify.com/episode/6QLuRQLZQN8A6Jm3L1I823?si=moS-J2ssQf-qb7ATzq0E5Q](https://open.spotify.com/episode/6QLuRQLZQN8A6Jm3L1I823?si=moS-J2ssQf-qb7ATzq0E5Q) ## How iFood Designed Rosie Around Latency When dinner is late, a fast wrong answer can cost more than a slow correct one. iFood’s support agent is built around that production reality, treating latency as something to design for. * Async callbacks keep slow tools from blocking the conversation. * Rollback merges rapid-fire messages before the agent replies. * A small reviser model checks outgoing messages, while end-state evals measure whether the user’s problem was resolved. The system stays responsive without assuming every dependency will be fast. [Read the blog](https://mlops.community/blog/how-ifood-designed-rosie-around-latency) ## A Discussion on Loop Engineering A coding loop can launch 75 agents and burn through its token budget in minutes if its controls are wrong. Making agents autonomous requires more than repeating prompts until the tests pass. * Machine-readable plans, tests, and independent reviewers give each loop a measurable target. * Observability and evals show where systems drift, stall, or waste tokens. * Persisted failure modes and learnings let later runs avoid repeating the same mistakes. The useful loop is the one that knows when to stop. [Watch the reading group](https://home.mlops.community/home/videos/a-discussion-on-loop-engineering-aaif-reading-group-july) ## IN-PERSON EVENTS * San Francisco [https://luma.com/unzyev3c] - July 30 * Pune, India [https://luma.com/ioxenpxl] - August 1 * New York [https://luma.com/kylt79cf] - August 14 * Toronto [https://luma.com/p6vg7zag] - September 10 * San Francisco, Voice Agents Forum [https://luma.com/voiceagentssf] - September 16 ## MCP RELEASE PARTIES * Amsterdam [https://luma.com/xpbgu0t7] - July 29 * London [https://luma.com/klu2tegz] - July 28 * New York [https://luma.com/aaif-zwdl] - July 28 * San Francisco [https://luma.com/ugfl1mn2?tk=C9eRhQ] - July 28 * Seattle [https://luma.com/aaif-znfn] - July 28 ## VIRTUAL EVENTS * MCP Jam [https://home.mlops.community/home/events/a-virtual-mcp-community-event-for-ai-builders-14x29g2kqp] - August 6 ## Buying Time [https://docs.google.com/forms/d/e/1FAIpQLScLyUmV7B_fvmiQni6cF0iIFMEvjrL5fivzUjdFci14G_nQCA/viewform](https://docs.google.com/forms/d/e/1FAIpQLScLyUmV7B_fvmiQni6cF0iIFMEvjrL5fivzUjdFci14G_nQCA/viewform) --- Source: https://aaif.live/newsletters/mlopscommunity/2026-07-30-scaling-agents-paying-the-bill