The building blocks for every AI automation. Click any node to explore — then decide which fits your team's processes.
⏱ Day 2 · Interactive ReferenceWhen your tech team proposes an AI automation, they'll describe it using these 4 patterns. Understanding them helps you:
"Is this a chaining or orchestration problem?" helps you assess complexity and timeline.
Parallelization is faster but costs more tokens. Chaining is cheaper but slower. You decide the tradeoff.
Orchestration includes human-in-the-loop gates. You define where humans must approve.
Match your team's manual processes to the right pattern — that's your automation roadmap.
Sequential steps — the output of one becomes the input of the next. Like an assembly line where each station does one job well.
or click any node aboveMultiple tasks run simultaneously on the same input. Like sending a document to 3 reviewers at once instead of waiting for each one sequentially.
or click any node aboveClassify the input and direct it to the right processing path. Like a smart mailroom — each document type gets its own optimized workflow automatically.
or click any node aboveA central orchestrator dynamically manages the workflow, spawning subtasks and coordinating human-in-the-loop decisions based on conditions.
or click any node aboveMost real workflows combine 2–3 patterns. This AnyCompany PayLater application uses routing → parallelization → chaining in one pipeline.
or click any node aboveMatch your process to the right pattern:
| If your process looks like… | Use this pattern | Example |
|---|---|---|
| Do A, then B, then C (sequential) | Chaining | Invoice: extract → validate → approve |
| Get 3 opinions on the same thing | Parallelization | Risk + Product + Compliance review |
| Sort first, then process differently | Routing | Classify document type → right workflow |
| Complex with "if/then" decisions | Orchestration | Credit approval with threshold gates |
| Multiple of the above | 🧩 Combine | Route → parallel checks → chain to decision |