Real processes, drawn as graphs
Everyone talks about graph engineering; these are worked examples. Every graph is a complete process — each node with its contract, each branch with its condition, each loop with a stop rule. Open one, make it yours, hand it to your AI.
Content Pipeline
Brief to published piece with a review loop that has actual criteria — so "make it better" never enters the process.
7 nodes · 7 connections Customer SuccessCustomer Onboarding
From signup to activated customer: the split between self-serve and assisted, and an activation check that actually defines what "activated" means.
9 nodes · 10 connections FinanceInvoice Approval
From inbox to approved payment: every step, every branch and the compliance loop — as a graph your AI can execute instead of a policy document it has to interpret.
9 nodes · 11 connections OperationsMeeting Notes to Tasks
The smallest process with the biggest daily payoff: from a messy transcript to owned, dated tasks — with a merge step and a check before anything reaches the task board.
9 nodes · 11 connections SupportSupport Ticket Triage
Every ticket lands somewhere — the question is whether a rule decided that or a mood. This graph makes the routing rules explicit enough for an AI to apply them.
9 nodes · 11 connectionsYour process is not here?
Draw it yourself: drop a node, give it a contract, connect the flow. The specification takes it from there — and your AI does the rest.