Browse 7 articles tagged action-providers across approvals, auditability, plugins, and controlled AI operations.
A Latch plugin that reads handwritten fields from a cheque — payee, amount, cheque number — validates them, and gates credit or reject actions on the result.
Read Building a Latch Plugin That Reads Handwritten Cheques →Replace forwarded-email approvals with case-centric four-eyes control that keeps role boundaries, denied attempts, and execution outcomes visible.
Read How to Run Four-Eyes Control Without Inbox Approvals →Plugins should start with workflows that need governed approvals, immutable audit logs, and safe external execution in production.
Read The First Three Workflows to Govern with Action Providers →Use extensible plugin architecture to preserve discovery, authorization, and result capture without long-term integration debt.
Read How to Add External Actions Without Creating Integration Debt →Make reprocessing explicit, permissioned, and auditable so teams can retry failed work without tribal knowledge or weak controls.
Read Turn Reprocessing from Tribal Knowledge into a Governed Action →What to record when an operator triggers an external action, so the audit trail still answers the question months later.
Read What to Log When Operators Trigger External Actions →Extensible plugin architecture lets teams extend workflows safely without brittle custom code or fragmented control logic.
Read Extend the Platform with Providers Instead of Hard-Coded Custom Workflows →