Skip to main content
Skip to main content
LaureoLaureo
Product
Why Laureo
Solutions
Pricing
Resources
Contact
Sign InStart 14-Day Trial
Start TrialStart 14-Day Trial

Product updates, no noise.

New features and the occasional sales tip. Unsubscribe anytime.

We'll send occasional product updates. Unsubscribe anytime. Privacy Policy

LaureoLaureo

CRM + Marketing + Automation + AI agents. One platform. Zero grunt work.

Product

Features

  • Sales & CRM
  • Marketing & Communication
  • Deals & Revenue
  • Customer Support
  • Automation & Insights
  • AI Agents
  • Integrations

Tools

  • Smart Inbox
  • Follow-up Sequences
  • Cold Outreach
  • Team Chat
  • Quotes & Invoices
  • Scheduling
  • Forms
  • Help Desk
  • Knowledge Base
  • Surveys

More

  • All features
  • Browse integrations
  • Pricing
  • Compare
  • Migrate

Solutions

For teams

  • Small Business
  • Startups
  • Sales Teams
  • Agencies
  • Consultants

By industry

  • Professional Services
  • Real Estate
  • Manufacturing
  • SaaS & Tech
  • Recruiting
  • See all solutions

Company

  • About
  • Contact
  • Partners
  • Security
  • Changelog

Resources

  • All resources
  • Blog
  • Help Center
  • Glossary
  • FAQ

Legal

  • Privacy
  • Terms
  • Acceptable Use

All third-party product names, logos, and brands mentioned on this site are the property of their respective owners, are used for identification and comparison only, and do not imply any affiliation with or endorsement of Laureo.

© 2026 Laureo. All rights reserved.

·

Help Center

Docs

Everything you need to know about using Laureo

Help Center

Overview
OverviewBuilding an AutomationTriggersConditions, Waits & ActionsAI Agent StepsThe Approvals QueueRuns & AnalyticsTemplates
Help CenterAutomationsAI Agent Steps

AI Agent Steps

Hand a step to an AI Agent that decides what to do within the approvals and limits you set: allowed actions, a confidence threshold, and automatic spending limits.

What an AI Agent step does

A reasoning step inside an otherwise deterministic flow.

Most steps do exactly one fixed thing. An AI Agent step is different: it hands the record to a model that looks at the context and decides which of its allowed actions to take. You do not script the decision; you set the boundaries, and the agent reasons within them.

Use an agent step when the right move depends on judgement a fixed rule cannot capture, like drafting a reply that fits the thread or deciding which of several follow-ups suits a given deal.

AI Agent steps are metered against your organization’s AI budget. If the budget is exhausted, the trial has ended, or your allocation is used up, the step is skipped with a descriptive reason instead of failing the whole run. Check Settings > Usage to monitor limits.

Approvals and limits

Every agent step is bounded by the same set of controls.

FieldDescription
Name*A label for the agent step so its purpose is clear in the flow and the run history.
ModelHow hard the agent thinks: Light Tasks (the default), Standard, Advanced, or Advanced reasoning. Higher tiers cost more per run. See the Model section below.
Allowed actionsThe exact set of CRM actions this agent may take. The agent can never act outside this list.
AutonomyWhether the agent’s proposed actions wait for a human. See the autonomy dial below.
Confidence thresholdHow sure the agent must be before an action is eligible to run on its own. Anything below the bar is sent for approval.
Spending limitsAutomatic. Agent usage counts against your plan’s AI allowance, and each agent is limited to a share of it (25% per month, 5% per day) so a runaway agent is caught quickly. Nothing to configure.
These controls are version-pinned and enforced at run time from the live automation. Removing an allowed action, tightening approval, or pausing the automation takes effect on the next run, including runs already mid-flow.

Model

Choose how hard the agent thinks.

Each agent has a Model setting with four tiers:

  • Light Tasks (default): quick and inexpensive, right for simple, high-volume work such as tagging inbound leads.
  • Standard: a balanced model, a good default for most agents.
  • Advanced: a stronger model for nuanced, multi-factor judgement.
  • Advanced reasoning: the strongest tier, for the hardest multi-step judgment calls. Highest quality and highest cost per run.

The setting applies on every way the agent runs — scheduled, triggered, or run manually — so what you pick is what the agent uses everywhere.

The model tier is set per agent by whoever can edit the agent. Higher tiers cost more per run and use more of your plan’s AI allowance.

The autonomy dial

How much the agent may do unattended.

  • Suggest only: every action the agent proposes waits in the approvals queue until someone approves it. This is the safe default.
  • Draft and hold: reads and drafts happen on their own; anything that would change a record still waits for approval.
  • Act with review trail: actions run unattended once the agent’s confidence clears your threshold; every action is recorded in the run history. This level requires a confidence threshold before you can switch it on, and spending stays bounded by the automatic limits above. High-risk actions such as sending email always wait for approval, at every level.

The confidence threshold works alongside the mode: even an unattended action only runs without review when the agent’s confidence clears the bar you set. Below it, the action is routed to the queue.

Inbox reply drafts (the Inbox Reviewer)

A preset agent that drafts two reply options to your inbound email — you pick one and send.

The Inbox Reviewer is the preset agent that watches your inbox. When a new email arrives, Laureo reads the thread and the linked CRM context and prepares two reply draftswith different angles. When you open the email, the chooser is waiting in the reply box — pick the draft you prefer, edit anything you like, and send when you’re happy. Newsletters and no-reply mail are skipped.

You manage it from the Agents home like any other preset: pause or resume it, and open its run history to see every draft it produced, with cost and outcome. Drafts are only visible to the mailbox owner.

The Inbox Reviewer is metered against your organization’s AI budget, the same as any other agent, and rides the same automatic per-agent spending limits. If the allowance is used up, it simply skips drafting until the allowance refreshes. Your inbox is never blocked.
The Inbox Reviewer never sends an email on its own. It can only offer drafts in your reply box. Sending always takes a deliberate action from you, so a draft you don’t like costs nothing but a glance.

Gating an agent step

Only let the agent run when the record is worth its cost.

Because agent steps are metered, it is often worth placing a Filter or If / Else before one so the model only runs on records that matter. The agent step itself can also carry a condition the record must meet first, keeping spend focused.

Related Articles

AI Agents Overview— The dedicated home for agents, the presets, and the agent builderThe Approvals Queue— Where agent-proposed actions wait for a decisionAutomations Overview— Rules vs AI AgentsBuilding an Automation— Add an agent step to a flowRuns & Analytics— Confidence, cost, and audit per run
Previous
Conditions, Waits & Actions
Next
The Approvals Queue