--- title: "Your Agent Needs an SRE Handbook" newsletter: "User Community" date: 2026-10-29 source: https://aaif.live/newsletters/usercommunity/2026-10-29-your-agent-needs-an-sre-handbook --- # Your Agent Needs an SRE Handbook *Plus a goose that survives crashes, agent babysitters, and Git for teams of coding agents.* *User Community — Agentic AI Foundation, 2026-10-29* Wonder if we can get them to keynote [https://www.cbsnews.com/sanfrancisco/news/alameda-girl-creates-talking-skeleton-uncle-murray-halloween-display/] at one of our events. ## Gems ## HumanLayer and the Future of Coding Agents ## CODING AGENTS LUNCH & LEARN What does software development look like when coding agents become part of the team? Join us for an open discussion on HumanLayer [https://github.com/humanlayer/humanlayer], how it helps developers coordinate coding agents, and what it could mean for planning, building, and reviewing software. Bring your questions, share what you're working on, or just come along for the conversation. Friday, October 30 | 9–10 AM PT / 4–5 PM UTC JOIN LIVE [https://home.mlops.community/home/events/coding-agents-lunch-and-learn-session-29-humanlayer-and-the-future-of-coding-agents-ix7g72uk2y] Find recordings of our previous Lunch & Learn sessions here [https://www.youtube.com/playlist?list=PL3vkEKxWd-utz7ew8QmiuTFNjjkvvM_xM]. ## What’s happening across the chapters ## LOCAL ORGANIZERS It was great to see some well-deserved recognition at AGNTCon + MCPCon North America, with AAIF ambassadors and community organizers celebrated on stage. Special congratulations to Agentic Tokyo, which received the Community Builder Award at the inaugural AAIF Annual Technical Excellence Awards! Satoshi Ito shared the news [https://lnkd.in/p/e4KQwSm8], while Vijay Bhore [https://lnkd.in/p/eVtUTzRN] and Yelaine Wang [https://lnkd.in/p/etiSt6BZ] also reflected on the recognition and the people behind the community. It’s been a busy week across our local chapters, with seven meetups in New Zealand, Luxembourg, Denver, Pune, Shenzhen, Chennai, and Aalborg. Speakers covered everything from hands-on agent building and MCP to production architectures, security, and even live robotics demos. Catch up on all seven in AAIF’s community roundup [https://www.linkedin.com/posts/agentic-ai-foundation_seven-cities-seven-meetups-one-growing-activity-7520903121989079041-kzLO], and thanks to the organizers, speakers and supporters who made them happen. ## Building AI so everyone can flourish An AI research assistant recommended hiring another engineer; after consulting the Google SRE handbook, it instead called for an operational toil audit. That reversal frames a wider question: how should human expertise shape increasingly autonomous AI systems? * Context engineering: Curated expert knowledge can redirect an LLM from surface symptoms to underlying organizational problems. * Agent infrastructure: Inconsistent shell environments and tool configurations trigger repeated failures and wasted tokens; shared setups can preserve hard-won fixes. * Open architectures: MCP, portable memory, and interoperable protocols offer ways for agents and people to cooperate across platforms. Reliable AI depends on deliberately choosing the knowledge, constraints, and incentives guiding its work. [https://podcasts.apple.com/gb/podcast/tim-oreilly/id1505372978?i=1000798194214](https://podcasts.apple.com/gb/podcast/tim-oreilly/id1505372978?i=1000798194214) [https://home.mlops.community/home/videos/building-ai-so-everyone-can-flourish](https://home.mlops.community/home/videos/building-ai-so-everyone-can-flourish) [https://open.spotify.com/episode/2uR1Rbz4Gw0gFYefXqIDZw?si=gXa0p2U4RSqX5XYjH1RcIA](https://open.spotify.com/episode/2uR1Rbz4Gw0gFYefXqIDZw?si=gXa0p2U4RSqX5XYjH1RcIA) ## AI agents need a babysitter A computer-use benchmark reportedly achieved 18% accuracy on first attempts, reaching 33% only after retries. Those results frame a look at how agents select tools, navigate workflows, and verify generated code. * Intent-based selection: Agents could describe desired actions and reasons to a classifier rather than access every tool directly, preserving an audit trail. * Hybrid routing and WebMCP: Smaller LLM fallbacks can handle uncertain classifications, while websites expose different task-specific tools as workflows progress. * Agentic verification: QA subagents can click through changed interfaces, record screenshots, and test outcomes before code reaches a pull request. Reliable agent workflows need explicit intent, constrained actions, and evidence that intended outcomes occurred. [https://podcasts.apple.com/gb/podcast/ai-agents-need-a-babysitter/id1505372978?i=1000797819643](https://podcasts.apple.com/gb/podcast/ai-agents-need-a-babysitter/id1505372978?i=1000797819643) [https://home.mlops.community/home/videos/ai-agents-need-a-babysitter](https://home.mlops.community/home/videos/ai-agents-need-a-babysitter) [https://open.spotify.com/episode/49KbOX88IIZB84IL8Th9Is?si=-ABZ4PW1RBye7x-6wp9zkg](https://open.spotify.com/episode/49KbOX88IIZB84IL8Th9Is?si=-ABZ4PW1RBye7x-6wp9zkg) ## Token maxxing is over and here is what comes next Getting stuck sooner helped keep engineers in control of an 800,000-line platform rebuild completed in six months. With Sonnet writing 60% of the project, the team prioritized human steering over longer autonomous coding runs. * Model choice: Shorter reasoning loops surfaced questions earlier, especially around transaction engines and complex banking rules. * ROI measurement: Dashboards compared token spend with shipped features and merged PRs, flagging discrepancies for discussion rather than judgment. * Workflow design: A meta-harness moved Claude Code through refinement, specification, implementation, and verification, resetting context and skills between stages. The practical lesson is to design agent workflows around visible decisions, measured outcomes, and controlled context. [https://podcasts.apple.com/gb/podcast/token-maxxing-is-over-and-here-is-what-comes-next/id1505372978?i=1000797098623](https://podcasts.apple.com/gb/podcast/token-maxxing-is-over-and-here-is-what-comes-next/id1505372978?i=1000797098623) [https://home.mlops.community/home/videos/token-maxxing-is-over-and-here-is-what-comes-next](https://home.mlops.community/home/videos/token-maxxing-is-over-and-here-is-what-comes-next) [https://open.spotify.com/episode/0SGCUDk7UHLtPsfQHCy1FC?si=FfS4sOGGS4aGlvaWreZunw](https://open.spotify.com/episode/0SGCUDk7UHLtPsfQHCy1FC?si=FfS4sOGGS4aGlvaWreZunw) ## Where voice agents fail in production: Part 1 - latency, turns, and interruptions Stopping a voice agent mid-sentence doesn't cancel a booking already sent to an external service. Production failures often begin when turn detection, playback, model generation, and application state fall out of sync. * Latency tracing: Measure end-of-speech to first audio across endpointing, recognition, inference, tools, synthesis, and transport rather than blaming the model. * Turn detection: Semantic and acoustic signals can distinguish thinking pauses from completed requests, balancing premature responses against unnecessary waiting. * Interruptions: Truncate unplayed speech from history, distinguish backchannels from corrections, and track whether external operations remain active. Reliable voice agents need playback-aware histories, explicit confirmation state, and traces that explain what actually happened. [Read the blog](https://aaif.io/blog/where-voice-agents-fail-in-production-part-1-latency-turns-and-interruptions) ## Introducing Dapr Durable Execution for goose: AI agents that pick up where they left off Crash a coding agent halfway through a deployment plan, restart its worker, and pick up where it left off. An open-source goose–Dapr integration makes that possible by running agent work inside durable workflows rather than relying on saved chat history alone. * Checkpointed turns: Dapr records completed conversation turns as workflow activities, avoiding replay and wasted model calls after recovery. * Minimal integration: The diagrid-goose Rust crate registers goose with a Dapr Workflow worker and schedules multi-step tasks. * Recovery boundaries: Persistent goose session storage is required; side effects within an interrupted turn still need idempotency protection. Turn-level durability provides recoverable agent execution without rebuilding the existing tool stack. [Read the blog](https://aaif.io/blog/introducing-dapr-durable-execution-for-goose) ## In-person events ## Come and connect * Kochi [https://luma.com/x1wimzk4] - October 31 * Dallas, Workshop [https://luma.com/tm2rh6gd] - October 31 * Boston [https://luma.com/aaif-sandbox] - November 2 * Sydney [https://luma.com/0ex5yg1q] - November 3 * Melbourne [https://luma.com/7qtmasup] - November 5 * Helsinki [https://luma.com/rzrt9958] - November 5 * San Francisco, Voice Agents Forum [https://luma.com/voiceagentssf] - November 5 * Mumbai [https://luma.com/sywq28p8] - November 7 * Ulaanbaatar [https://luma.com/vczb32ch] - November 15 Find your city here [https://aaif.io/events?tab=community], or start a chapter if there isn't one yet. ## Virtual events ## Join from anywhere * Lunch and Learn: HumanLayer and the Future of Coding Agents [https://home.mlops.community/home/events/coding-agents-lunch-and-learn-session-29-humanlayer-and-the-future-of-coding-agents-ix7g72uk2y] - Oct 30 --- Source: https://aaif.live/newsletters/usercommunity/2026-10-29-your-agent-needs-an-sre-handbook