This is a knowledge site about orchestration in agentic software: the logic that decides what runs next, under which conditions, and how the pieces coordinate. It starts from sequence, branch and loop and climbs to durable workflows with several agents, a pause for a person, failures, budgets and traces. At each step it asks one question: who decides what runs next here, code or a model? It is written for engineers and architects who build agent systems and have to decide where a model's choice belongs and where it does not.
One example runs through every page. An insurer receives a broker's request for a quote. The quote workflow turns the email into a submission, gathers evidence with three lookups, applies the rules of a policy fixture, drafts a recommendation, checks the process with a guard, stores the recommendation and waits for an underwriter. The model recommends; a person decides.
What it is and is not#
| It is | It is not |
|---|---|
| A ladder: one idea per page, each word in plain English with a tiny example before it is used | A standard, or the only way to design a workflow |
| One running example: the quote workflow, eighteen cases, followed through every chapter | A record of any real insurer. The cases, the rules, the fields, the provider and the timings are invented |
| A demonstration of mechanism: how steps, transitions, guards, waits, retries and traces fit together | A measurement of any model or product. No page reports how good or how fast a real system is |
| Code that was run: a small workflow engine in standard-library Python, with its real output | A framework to install. It is short so that it can be read whole, and it leaves things out |
| Frameworks described from their own documentation, by what each one runs for you | A ranking or a buying guide. No framework is called best, and no price is quoted |
What is original here and what is not#
Most ideas on this site are older than agents: state machines, directed acyclic graphs, queues and workers, checkpoints, idempotency keys, sagas, circuit breakers, deadlock and trace propagation all come from decades of distributed systems and operating systems work. This site applies them to workflows in which a model makes some of the choices.
| Part | Status |
|---|---|
| Sequence, branch, loop; state machines; DAGs; queues, workers, fan-out and fan-in; timeouts; deadlock, livelock, starvation | Foundational computer science, explained here without a single source |
| The saga and compensation | From "Sagas" by Hector Garcia-Molina and Kenneth Salem (1987), read for this site; see durable workflows |
| Trace and span identifiers | Their shape follows the W3C Trace Context recommendation; see tracing |
| Workflows versus agents; routing; when to use several agents | Published guidance by Anthropic, OpenAI and Cognition, quoted with attribution on one or many and topologies |
| The distinction between the control plane and the data plane | A networking idea applied to agent workflows |
| The hybrid design: a deterministic skeleton, a model's choice inside one bounded step, a code guard at its exit, a person at the decision | A design proposed on this site; see control plane |
| The site's one question ("who decides what runs next here, code or a model?") | The organizing question of this site |
| The quote workflow, the policy fixture, the eighteen cases | UW-001 to UW-010 are shared by the series; UW-901 to UW-908 and policy version 2026.3 were written for this site. All synthetic |
| The example code, its tests, the labs and the diagrams | Written for this site |
Where a page takes an idea from a source, the page says so. Where this site proposes something, it calls it a design.
How the facts were checked#
| Kind of claim | How it was checked |
|---|---|
| A named framework, SDK or standard | Read on its own documentation on the day of writing (2026-11-17) and logged with the page address and the date. Where the documentation is silent, the page says so. Statements about products live on Frameworks |
| A surprising fact | Fetched a second time by a different reader before publication. Four were confirmed this way: the AutoGen repository is archived and points to Microsoft Agent Framework; Google's Agent Development Kit marks its template workflows deprecated and its documentation moved to adk.dev; the Spring Retry repository is archived and superseded by Spring Framework 7; Anthropic's "Building effective agents" notes that much of its tooling landscape has changed since December 2024 |
| An idea from a source | The source was opened and read on the day of writing, and is listed below |
| The example | Run. Every command shown from examples/uw-orchestrator/ was executed in a scratch copy, and the output on the page is the output it printed. The folder has 45 unit tests |
| The labs | They read data that a script generates from the example with a fixed seed. Their logic is a second implementation of the Python functions in core.py, and a test fails if the two disagree |
| Numbers | Synthetic and illustrative unless a source is linked. A number from the example is the result of a script, never a measurement |
| Other code | A block that was not run says how far it was checked, for example "documented shape; not run here" |
| Links and structure | A build step checks every internal link, every diagram and every glossary reference before the site is published |
Documentation changes. Treat every statement about a framework as true on the day it was read, and read its page again before you build on it.
What the example does not show#
The insurance example is an illustrative reconstruction for teaching. The cases, the rules, the fields, the provider, the timings and every number are invented. Nothing here reports the quality of a real system or model. The agents here are scripted stand-ins and time is simulated, so the results show how the orchestration works, not how good or how fast any model is.
| In the example | What it really is |
|---|---|
| The intake, assessment and underwriting agents | Scripts. No model is called, there is no network and no key |
| The stand-in model of loop mode | A seeded random plan, so the path varies between trials and every reader sees the same variation |
| The tools and the roof-data provider | Stand-ins that return what the case file tells them to return |
| The underwriter cockpit and the underwriter | The case file, which sends the decision signal |
| The policy fixture | Five illustrative rules in three versions. They are not insurance practice |
| Durations and the clock | Constants and a simulated clock. Nothing sleeps |
| Checkpoints and the store | JSON files in an output folder |
The example also leaves things out, and the pages say so where it matters: rate limits, event-history replay, speculative execution, deadlock detection and fairness policies are explained, not implemented. The whole example is on the insurance lab.
Sources and reading list#
Each link below was opened on the day this page was written (2026-11-17).
Start here#
| Source | Why read it |
|---|---|
| Building effective agents, Anthropic, December 2024 | The distinction between workflows (predefined code paths) and agents (a model directs its own process), and the common workflow patterns. The page now notes that much of its tooling landscape has changed |
| A practical guide to building agents, OpenAI | When a single agent with tools is enough, and two multi-agent arrangements: a manager and decentralized peers |
| How we built our multi-agent research system, Anthropic, June 2025 | What several agents cost and buy in one production system |
| Don't Build Multi-Agents, Cognition, June 2025 | The argument for sharing context and traces, and why conflicting decisions between agents fail |
Foundations#
| Source | Why read it |
|---|---|
| Sagas, Garcia-Molina and Salem, 1987 | The origin of compensation for long-lived work. Depth for durable workflows |
| Trace Context, W3C Recommendation, 2021 | How trace and span ids cross process boundaries. Depth for tracing |
| ReWOO, Xu and others, 2023 | Separating planning from tool observations: one form of planner and executor. Depth for topologies |
| Spring Batch: controlling step flow | The familiar pre-AI version of sequence and branch in a batch job |
Framework documentation#
These are the entry pages of each framework's own documentation. What each one runs for you is described on Frameworks, and only there.
| Framework or standard | Documentation |
|---|---|
| LangGraph | docs.langchain.com/oss/python/langgraph/overview |
| Temporal | docs.temporal.io/workflows |
| AutoGen (archived) | github.com/microsoft/autogen |
| CrewAI | docs.crewai.com/en/introduction |
| OpenAI Agents SDK | openai.github.io/openai-agents-python |
| Claude Agent SDK | code.claude.com/docs/en/agent-sdk/overview |
| Google Agent Development Kit | adk.dev |
| A2A protocol | a2a-protocol.org |
| Model Context Protocol | modelcontextprotocol.io/specification |
Sister sites#
This site is one of a series. Each site takes one question, and none repeats a chapter of another. At a boundary, a page says in one sentence what the neighboring concept is not, and links the site that owns it.
| Site | The question it answers |
|---|---|
| Prompt Engineering | How instructions are written, composed, ranked, versioned and defended |
| Context Engineering | What the model can see now: selection, retrieval, budget, compaction |
| Memory Engineering | Durable information and saved execution state, and the difference |
| Agent Communication | Messages between agents, the A2A protocol, and A2A versus MCP |
| Observability Engineering | Evidence of what happened: logs, metrics, traces, audit events, replay |
| Guardrails Engineering | Enforceable checks around a probabilistic agent |
| Tools Engineering | Callable capabilities: schema, execution, MCP tools |
| Structured Output Engineering | Typed contracts: shape, validation, repair, evolution |
| Agent Orchestration Engineering, this site | Who decides what runs next, under which condition |
| Agent Reliability Engineering | Acceptable outcomes despite failures, retries, load and changing dependencies |
| Harness Engineering | The runtime around one model call: the agent harness |
| Eval Engineering | Measurement: graders, golden sets, judges, trials and release gates |
| Diff to Deploy | Shipping a change with coding agents: hooks, review, lanes, CI |
This site touches five neighbors most: messages between agents (Agent Communication), saved state (Memory Engineering), operational guarantees (Agent Reliability Engineering), evidence of what happened (Observability Engineering), and the loop inside one agent (Harness Engineering).
Who wrote it#
Sam Muthu, an engineer and architect who builds agent systems and holds Anthropic's Claude Certified Architect credentials (Foundations and Professional). More of his work is at sammuthu.com.
The site is a working version. If a claim is wrong or out of date, the fix is to read the source again and correct the sentence. Every term the pages use is collected in the Glossary.