--- title: "Agents Aren’t Scripts" newsletter: "MLOps Community" date: 2026-06-18 source: https://aaif.live/newsletters/mlopscommunity/2026-06-18-agents-aren-t-scripts --- # Agents Aren’t Scripts *Plus... multiplayer AI, MCP as agent UI, Claude Code hooks, and safer agent infrastructure.* *MLOps Community — Agentic AI Foundation, 2026-06-18* NICE TO SEE A SMALL STARTUP TAKE OFF [https://techcrunch.com/2026/06/16/spacex-to-acquire-cursor-for-60b-in-stock-days-after-blockbuster-ipo/]. ## Trail Mix The next agent outage won’t be a hallucination. It’ll be a tool call nobody logged. What do you trust more - evals or audit trails? [EVALS](https://go.mlops.community/NL_HT1_Jun18) [TRAILS](https://go.mlops.community/NL_HT1_Jun18) ## Talk therapy It was close, but chat edged it - most would rather talk through their debugging than shout at their dashboard. ## The Current State of Agentic Retrieval Join MLOps Community and Qdrant on June 25 for a virtual roundtable on how agents retrieve and use context. The discussion will cover vector search applications for agents, including agent tools, embedding methods, agentic evals, memory, and the challenges still shaping how retrieval works in agentic systems. Featuring Ewa Szyszka, Dylan Couzon, Neil Kanungo, and Evgeniya Sukhodolskaya from Qdrant. Register here [Register here](https://home.mlops.community/home/events/the-current-state-of-agentic-retrieval-g3ssvap40q?agenda_day=6a1ee42216f5cb7213db38dc&agenda_track=6a1ee42316f5cb7213db3911&agenda_stage=6a1ee42216f5cb7213db38e0&agenda_filter_view=stage&agenda_view=list) [https://home.mlops.community/home/events/the-current-state-of-agentic-retrieval-g3ssvap40q?agenda_day=6a1ee42216f5cb7213db38dc&agenda_track=6a1ee42316f5cb7213db3911&agenda_stage=6a1ee42216f5cb7213db38e0&agenda_filter_view=stage&agenda_view=list](https://home.mlops.community/home/events/the-current-state-of-agentic-retrieval-g3ssvap40q?agenda_day=6a1ee42216f5cb7213db38dc&agenda_track=6a1ee42316f5cb7213db3911&agenda_stage=6a1ee42216f5cb7213db38e0&agenda_filter_view=stage&agenda_view=list) ## Curated finds to help you stay ahead ## From Single-Player to Multi-Player: Operating AI Agents at Scale One engineer burned through an entire Anthropic budget in seven hours from a laptop. That is the problem here: agents are useful, but they need infrastructure built for non-deterministic actors. * Policy needs to cover access, actions, budgets, sandboxing, compliance, and eval-based confidence. * Agent workloads strain old assumptions around source control, search, runtime, audit logs, and provenance. * Composable agents may matter more than one giant agent, especially as shared context becomes critical. The risk is treating agents like scripts when they behave more like unpredictable teammates. [https://podcasts.apple.com/gb/podcast/from-single-player-to-multi-player-operating-ai-agents/id1505372978?i=1000771898493](https://podcasts.apple.com/gb/podcast/from-single-player-to-multi-player-operating-ai-agents/id1505372978?i=1000771898493) [https://home.mlops.community/home/videos/from-single-player-to-multi-player-operating-ai-agents-at-scale](https://home.mlops.community/home/videos/from-single-player-to-multi-player-operating-ai-agents-at-scale) [https://open.spotify.com/episode/2MXIyc89c7giFl4RuX1qqd?si=fbdb8f90a9624a79](https://open.spotify.com/episode/2MXIyc89c7giFl4RuX1qqd?si=fbdb8f90a9624a79) ## Agents & the $40M Bet on Multiplayer AI When an agent starts a week-long task, one person cannot steer it alone. This discussion looks at the shift from solo AI sessions to shared workspaces where agents and humans hand work across teams. * Longer agent tasks need shared state, hosted sessions, and clearer handoffs between specialists. * Product design may matter as much as model quality for real collaboration. * Fast-changing models make planning, pricing, and alignment harder. The next AI bottleneck may be coordination, not capability. [https://podcasts.apple.com/gb/podcast/agents-the-%2440m-bet-on-multiplayer-ai/id1505372978?i=1000772390805](https://podcasts.apple.com/gb/podcast/agents-the-%2440m-bet-on-multiplayer-ai/id1505372978?i=1000772390805) [https://home.mlops.community/home/videos/agents-and-the-dollar40m-bet-on-multiplayer-ai](https://home.mlops.community/home/videos/agents-and-the-dollar40m-bet-on-multiplayer-ai) [https://open.spotify.com/episode/25vhLxLpdXuXNfkFkknfpT?si=05872655ba0d4fd4](https://open.spotify.com/episode/25vhLxLpdXuXNfkFkknfpT?si=05872655ba0d4fd4) ## MCP Servers Are Becoming the UI for AI Agents Your MCP server can fail only for Cursor users, burn context with giant responses, or leave agents stuck on useless errors, while your team sees only a vague GitHub issue. This discussion is about treating MCP like a real product surface. * Analytics can expose user goals, client versions, failing tool calls, and session-level intent. * Better errors help agents recover instead of retrying blindly. * Tool design should follow user outcomes, not mirror every API endpoint. Mature MCP means measuring what agents are trying to do. [https://podcasts.apple.com/gb/podcast/mcp-servers-are-becoming-the-ui-for-ai-agents/id1505372978?i=1000772993796](https://podcasts.apple.com/gb/podcast/mcp-servers-are-becoming-the-ui-for-ai-agents/id1505372978?i=1000772993796) [https://home.mlops.community/home/videos/mcp-servers-are-becoming-the-ui-for-ai-agents](https://home.mlops.community/home/videos/mcp-servers-are-becoming-the-ui-for-ai-agents) [https://open.spotify.com/episode/7bwOMWZBsM7ipDaFKPlFvG?si=85d0eca8fa814b33](https://open.spotify.com/episode/7bwOMWZBsM7ipDaFKPlFvG?si=85d0eca8fa814b33) ## The Complete Guide to Claude Code Hooks: Automating Your AI Coding Workflow Claude can now be interrupted before it does something expensive, risky, or just annoying. This guide explains Claude Code hooks as lifecycle triggers that wire agents into the engineering workflow rather than leaving them as a chat box beside it. * Session and prompt hooks load context, set env vars, block PII, and route work before the model starts. * Tool and permission hooks enforce safety, run linters, rewrite commands, and log MCP calls. * Stop, compaction, file, worktree, and MCP hooks cover cleanup, audit trails, state, and approvals. The useful bit is control at the exact moment agents act. [Read the blog](https://mlops.community/blog/the-complete-guide-to-claude-code-hooks-automating-your-ai-coding-workflow) ## Making Agents Stop Rereading Everything A lot of agent waste looks less like bad reasoning and more like bad state management. In this Coding Agents Lunch & Learn write-up, Devansh explains why multi-stage agent systems often burn tokens rereading and resummarizing the same material, and how a shared blackboard can give agents structured memory across long document, research, legal, finance, and codebase analysis tasks. Read the short PDF write-up here [https://learn.mlops.community/wp-content/uploads/2026/06/Lunch_and_Learn_Session_15_Asset.pdf]. Coding Agents Lunch & Learn is taking a short break this week, but we’ll be back on June 26 for a session on Real-World Coding Agent Workflows. Sign up here [https://home.mlops.community/home/events/coding-agents-lunch-and-learn-session-16-real-world-coding-agent-workflows-drpuzfuq6q?agenda_day=6a30467ed33e5acb9d2e6f06&agenda_track=6a30467fd33e5acb9d2e6f1d&agenda_stage=6a30467ed33e5acb9d2e6f0c&agenda_filter_view=stage&agenda_view=list]. ## IN PERSON EVENTS * Amsterdam [https://luma.com/6i8pf89q] - June 24 * NYC [https://luma.com/nyc-i97h] - June 24 ## VIRTUAL EVENTS * The Current State of Agentic Retrieval [https://home.mlops.community/home/events/the-current-state-of-agentic-retrieval-g3ssvap40q] - June 25 * Lunch & Learn Session 16 [https://home.mlops.community/home/events/coding-agents-lunch-and-learn-session-16-real-world-coding-agent-workflows-drpuzfuq6q?agenda_day=6a30467ed33e5acb9d2e6f06&agenda_track=6a30467fd33e5acb9d2e6f1d&agenda_stage=6a30467ed33e5acb9d2e6f0c&agenda_filter_view=stage&agenda_view=list] - June 26 ## A Tidy Mistake [https://forms.gle/43scF9NfM33aorYH7](https://forms.gle/43scF9NfM33aorYH7) --- Source: https://aaif.live/newsletters/mlopscommunity/2026-06-18-agents-aren-t-scripts