Humans in the loop, by design.
Digitlify’s governance model groups actions into four levels of risk. GREEN allows low-risk work; higher levels call for human review. This page explains the model. Supported workflows and permissions are confirmed for your use case before early access.
The four gates
Each action your workforce takes is classified at one of four levels. The gate determines how many humans have to sign off, how fast, and with what evidence.
GREEN
Low-risk, fully autonomous
Rule
Agent acts without approval. Every action is logged; the audit trail exists for post-hoc review but nothing blocks execution.
Examples
Reading a public document. Drafting a blog post. Posting a Slack reply in a channel the agent is already a member of.
YELLOW
Single-reviewer approval
Rule
Action is queued for approval by one named human (or one role). Timeout escalates to the next gate.
Examples
Sending an outbound email. Publishing content to a customer-facing surface. Booking a meeting on a shared calendar.
RED
Dual approval + cooling period
Rule
Action requires two independent approvers (one can be a team lead). Cooling-off window before execution. Reversal window after execution.
Examples
Issuing a refund. Changing an account setting on a customer record. Triggering a production deploy. Spending above a budget threshold.
BLACK
Executive sign-off + legal review
Rule
Named executive (or delegate) + legal counsel must sign off in writing before execution. Full audit pack auto-assembled.
Examples
Closing a customer account. Deleting data at customer request. Any action that could constitute a regulated disclosure.
Six principles
What the gate system rests on. Each principle describes the target model; supported workflows are confirmed before access.
Observable by default
The model calls for records of actions and approval decisions, with access and retention rules. It does not promise to expose private reasoning or store all conversation content.
Configurable per workload
Approval requirements should reflect the workload, permissions and consequences of an action. Available configuration is reviewed before access.
Reversible when possible
The model calls for a pause before sensitive actions and recovery where the destination supports it. External actions cannot always be undone.
Time-bounded autonomy
The model limits how long an assistant can act without renewed review. Supported time limits depend on the workflow.
Budget-capped
Usage limits and behavior at the limit must be reviewed for the workload. The governance model alone is not a billing guarantee.
Review with your policies
Map sensitive actions to your organization’s policies and review obligations. The model is not a certification or a substitute for your own legal review.
Approval levels and record retention
Confirm supported approval workflows and retention before early access. Standard plan prices and usage allowances are listed on the pricing page.
Approval levels and record retention are confirmed with you before access. Tell us which actions need review, who should approve them, and how long you need approval and action records kept.
We will confirm in writing what we can support, and what is available today versus planned.
See /pricing for the full plan comparison.
Discuss your approval requirements.
Tell us which actions need review and who should approve them. We will discuss the supported workflows, records and access controls.