The Orchestrator

This field is moving quickly and its vocabulary is not settled, so do not treat any current list of frameworks as a permanent map. Learn enough to compare systems by asking what they can see, what they can change, how they retain context, how they are evaluated, and who can stop them.

For practical starting points, read the OpenAI Agents SDK documentation for examples of tools, handoffs, sessions, guardrails, tracing, and human approval.¹ Study the Model Context Protocol if you want to understand how agents connect to external tools and data — and study Microsoft’s Agent Control Specification if you want the closest open artifact to a portable permission envelope.²³ Google’s Agent Development Kit and LangGraph are useful places to study more structured and stateful workflows; Temporal is the place to study durable waits and crash-safe history when a human approval may arrive hours later.⁴⁵

For the wider picture, follow the Stanford AI Index, METR’s research on the length of tasks frontier models can complete, the NIST AI Risk Management Framework, and MIT Sloan’s reporting on the organizational work required to make agentic systems useful.⁶⁷⁸⁹ Read Tim O’Reilly’s “Why Open Source Matters for AI” if you want the architecture-of-participation argument in one place — Goose, Pi, open weights, MCP — before you lock your stack to a single appliance.¹⁰

A few books are worth putting on the shelf as well. The second edition of Micheal Lanham’s AI Agents in Action is a hands-on introduction to building and connecting agents, and what it gives an orchestrator is running code — an agent with memory, tools, and a feedback loop you can step through.¹¹ Victor Dibia’s Designing Multi-Agent Systems concentrates on coordination patterns, evaluation, and agent experience, and it builds a small framework from scratch, which is the quickest cure for treating the frameworks in the toolkit survey as sealed boxes.¹² Michael Albada’s Building Applications with AI Agents compares practical approaches to agent applications: one scenario across several frameworks under one evaluation harness, a discipline this book asks for and does not demonstrate.¹³ Sebastian Raschka’s Build a Large Language Model from Scratch is not about orchestration at all and remains one of the better ways to understand what sits underneath these systems; it shows you why the variation in a model’s output is a property of sampling rather than a defect, by making you write the sampler.¹⁴ Valliappa Lakshmanan and Hannes Hapke’s Generative AI Design Patterns is the broader reference for retrieval, reliability, reasoning, and production concerns, with named patterns, working code, and trade-offs for the problems you meet once the system is running.¹⁵

That is a long shelf, and nobody reads it in a week. If you read seven things before Monday, read these, in this order. For each, I have said what it does not cover, because that is where the orchestrator’s work begins.

1. Anthropic, “Building effective agents” (December 2024). Two engineers report what worked across dozens of teams: simple, composable patterns — prompt chaining, routing, an evaluator-optimizer loop — with an autonomous agent loop added only when simpler designs fall short. Anthropic now flags its tooling as dated; the argument for starting simple has aged well. It says nothing about who holds authority over the system or who answers when it is wrong.¹⁶
2. OpenAI, “A practical guide to building agents” (April 2025). Thirty-four pages for product and engineering teams. Its durable contributions are the instruction to exhaust one agent’s capabilities before adding a second, and its two triggers for handing control to a person: a failure threshold crossed, or a high-risk action — cancelling orders, authorizing large refunds, making payments. It also explains how to trade model cost against accuracy and latency. The organization around the agent remains your job.¹⁷
3. Simon Willison, “The lethal trifecta for AI agents” (June 2025). One page, readable by anyone who has used email, and the single security idea a first-week orchestrator most needs: private data, untrusted content, and a way to send data out, in one system, create a path for an attacker to steal data. It names the problem and one fix; the layered defense is in Chapter 14.¹⁸
4. OWASP, “Top 10 for Agentic Applications for 2026” (December 2025). The vocabulary your security team will use when they review what you built — goal hijack, agentic supply chain, memory poisoning — assembled by more than a hundred contributors. A risk list, not a design.¹⁹
5. METR, “Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity” (July 2025), with its February 2026 update. Sixteen experienced developers, 246 real tasks, randomized: with AI tools they took 19 percent longer and believed they had been 20 percent faster. Read it for the gap between the feeling and the clock. Then read the update, in which METR calls its follow-up data unreliable because developers increasingly refused to work without AI. Its researchers suspect newer tools help more, but the follow-up cannot establish how much. Neither study tells you what your uplift is; only your own measurement does.²⁰
6. Agent Skills, the specification. The format for the procedure you will write on Friday: a directory with a SKILL.md, YAML front matter with a name and a description, a Markdown body, and optional scripts and references loaded only when needed. Read it before you write the file, so the file is portable. Its allowed-tools field is marked experimental, and nothing in the format records who authorized what; it is a runbook standard, not a permission or audit standard.²¹
7. Andrej Karpathy, “Software Is Changing (Again)” (June 2025). A forty-minute talk to students, and the clearest statement of the stance a first week needs: partial-autonomy products with an autonomy slider and a fast generation-verification loop — “less Iron Man robots and more Iron Man suits,” because “this is the decade of agents” and “we need humans in the loop.” A talk about products and developers; the institution, the budget, and the question of who is accountable are not in it.²²

None of that reading is a prerequisite for the week below. Read while you run it.