Skip to content
AI Employee Allowance or Pay Per Use

Managed Agents From a Prompt

Describe the job, connect the tools it needs, and set its permissions. Managed Agents can remember useful context, split complex work between specialists, and follow up on a schedule. For research and file work, enable Computer and run the task in chat.

  • Build from a prompt
  • Memory you can review
  • Specialists for complex tasks
  • Permissions you control

From prompt to published agent

  1. Describe the agent

    Write what you need in plain English, or start from a use case like Knowledge Base Assistant or Email Campaign.

  2. Set the guardrails

    Choose events or schedules, approve permissions, attach your knowledge base, and set the capabilities the agent can use.

  3. Test before activating

    Test routine requests, unclear instructions, and handoffs using your own contact and sample records. Tests can perform real actions. Review the results before publishing, then monitor runs and refine the instructions.

app.smbcrm.com
Managed Agents prompt setup view in SMBcrm

Setup view shown. Workspace layout may vary as the updated interface rolls out.

From one request to repeatable work

Build around a task your team understands. Add memory, connections, or a follow-up plan as the job requires, then inspect what happened in each run.

  1. Keep useful context

    Memory stores relevant preferences and reusable procedures for recurring work. Inspect what the agent remembers and correct it when your business changes.

  2. Give parts of a job to specialists

    An agent can assign research, record checks, and other focused tasks to subagents, then review their results. Independent work can run in parallel; dependent steps wait for the information they need.

  3. Start from another system

    An inbound webhook passes an order, form response, or other event directly to a published agent. Tell it how to interpret the data and which actions it may take.

  4. Wait for the right time

    Schedule steps around an appointment or add a delay within a run. Conditions and stop rules can prevent follow-ups after a reply, booking, or other change you define.

  5. Use current business details

    Reference custom values and your business profile in agent instructions. Updated booking links or contact details apply on the next run without republishing the agent.

  6. Bring an n8n workflow into Agent Studio

    The beta importer prepares an agent from your workflow export. Review the converted steps, reconnect the required apps, and test any logic that changed before activating it.

Research, analyze, and make the file

Give an agent the browser and file tools it needs to gather information and produce a document or spreadsheet. Enable Terminal when the task calls for scripts or calculations.

For chat and manual runs

Computer does not run from workflow or event triggers. Keep scheduled CRM work separate from tasks that need browser interaction.

Review sensitive actions

Configure approval requests for actions such as sending messages or publishing. Payments and deletions always need approval. You can inspect browser activity and take control when needed.

What will you put an agent on?

These are example instructions to adapt and test. The agent needs the relevant connections, knowledge, and permissions before it can do the work.

  1. “Prepare a brief before tomorrow's customer call.”

    Use approved CRM access to gather context, then schedule a follow-up task after the appointment.

  2. “Compare these suppliers and put the findings in a spreadsheet.”

    Run it in chat with Browser and Files enabled. Review the sources and the file before using the results.

  3. “When an order arrives, find the customer and add an internal note.”

    Connect the order system through an inbound webhook and define which CRM records the agent may update.

See an agent task with staff review →

You decide what it can do

Set access, knowledge, and starting conditions deliberately. Review the results of a test before letting an agent act on customer records.

  1. Only the skills you allow

    Choose access to contacts, conversations, calendars, invoices, email, and other CRM tools. Review its connected tools and restrict access to the records and actions the job needs.

  2. Answers from your own content

    Attach approved material as a reference for answers, then test the responses for accuracy. Web search and image generation are separate switches, off unless you turn them on.

  3. Triggers you define

    Choose a supported event, webhook, or schedule for CRM work. Computer tools have a separate boundary: they work in chat and manual runs only.

  4. A person can take over

    Write a handoff rule into the instructions so complex conversations go to your team. The agent handles the routine, and your people handle the judgment calls.

Managed Agents permissions panel in SMBcrm

Permissions setup view. Grant only the CRM access each agent needs.

See it scoped live

See how to scope and test an agent for your work

Bring a task your team handles by hand. We can help you identify the tools, permissions, and review steps it needs.

See what the agent actually did

Inspect a run

Start in Activity, then use Agent Logs to review the conversation, actions, and execution steps. Subagent Activity shows delegated tasks and their results.

Track progress over time

Customize a Metrics dashboard or set a Monitor target for recorded activity. Daily checks and configured email or webhook alerts can flag progress that needs attention.

Agent Health and Self Healing are separate tools for Voice AI and Conversation AI. They prepare prompt improvements for human approval; they do not automatically rewrite Managed Agents. Explore the AI tools.

Managed Agents live in Agent Studio, not AI Studio

Agent Studio setup view for Managed Agents in SMBcrm

Agent Studio

Where you build and run Managed Agents: prompt-based agents that work in chat, from an event, or on a schedule. Growth includes 100 runs per month; Unlimited includes 1,000.

AI Studio

Builds websites and web apps from a description, with a database, user logins, and checkout connected to your CRM. Pay-per-use or covered by AI Employee.

One Managed Agent run is one chat session, one event invocation, or one scheduled invocation. The test area includes 30 free runs per month before production allowances or pay-per-use billing apply.

AI Employee Growth costs $97 per month and includes 100 Managed Agent runs. Unlimited costs $147 per month and includes 1,000 runs; Unlimited is included with Enterprise. Account usage-limit settings control whether applicable pay-per-use service continues after an allowance is used.

Building a site or app, not an agent? That's AI Studio.

Frequently Asked Questions

What are Managed Agents in SMBcrm?

Managed Agents are prompt-based AI agents that run in chat, from an event, or on a schedule. Give an agent a job, knowledge, and permissions. It can remember useful context, delegate parts of a job, and work with connected tools. Computer capabilities are limited to chat and manual runs.

Are Managed Agents the same as Agent Studio?

Essentially, yes. Agent Studio is the place in SMBcrm where you build and run Managed Agents, so both names refer to the same product and the same run-based billing.

Do I control what a Managed Agent can do?

Yes. You choose its CRM permissions, attach the knowledge it should use, decide which capabilities are on, and set the event or schedule that starts it. You can also define when it should hand work to your team.

How are Managed Agents billed?

AI Employee Growth ($97/mo) includes 100 Managed Agent runs per month, while Unlimited ($147/mo) includes 1,000. A run is one chat session, event invocation, or scheduled invocation. Pay-per-use service is also available, and the test area includes 30 free runs each month.

Are Managed Agents the same as AI Studio?

No. AI Studio builds websites and web apps. Managed Agents, built in Agent Studio, carry out CRM work in chat or from events. AI Studio and Agent Studio sound alike, but they do different jobs and have different AI Employee allowances.

Can a Managed Agent use a browser or create files?

Yes, with Computer enabled. Choose Browser, Files, and Terminal separately for research, documents, spreadsheets, or analysis. Computer works in chat and manual runs, not workflow or event-triggered runs. Payments and deletions always require approval; other actions follow your approval settings.

What does an agent remember?

When Memory is enabled, an agent can retain relevant user details and learn reusable procedures. You can review, edit, or delete stored facts and remove procedures. Memory is specific to each user and agent. Turning Memory off does not delete what was already stored.

How do subagents work?

The main agent can delegate focused jobs to specialists, then combine their results. Independent tasks can run in parallel. Specialists use the main agent's app connections within the permissions of their task; Computer and Custom API operations remain with the main agent. You can inspect delegated work in Subagent Activity.

Can an agent pause and follow up later?

Yes. Scheduled follow-ups let a running agent wait and resume with its context. Set conditions to skip a step or stop the sequence when it is no longer needed. You can review waiting runs and cancel them from Activity. Test Agent skips delays but can still send real messages and change records, so use your own test contact.

Can another app start a Managed Agent?

Yes. An inbound webhook can start a published agent directly when another system sends it data. Configure how the agent should read the request and use shared-token verification to protect the connection. Review the resulting run in Activity to confirm what happened.

Can I import an n8n workflow?

The n8n importer is available as a beta. It turns an exported workflow into a proposed Managed Agent and shows which steps carried over or changed. Credentials are not transferred. Reconnect apps, review record IDs and adapted logic, and test the result before publishing.

Does Agent Health change Managed Agents automatically?

No. Agent Health and Self Healing currently apply to Voice AI and Conversation AI, and proposed prompt changes need your approval. For Managed Agents, use Activity, Subagent Activity, and Agent Logs to inspect runs and refine the instructions yourself.
60-day money-back guarantee

Ready to put an agent on it?

Start with one task, connect the tools it needs, and review a test run before publishing.

  1. 60-day money-back guarantee

    Eligible Startup and Professional initial subscription fees only. Usage and add-ons are excluded. Read the refund terms.

  2. No setup fees

    Plan your setup with training and support

  3. Monthly or annual billing

    Monthly plans renew each month, and you can cancel before the next renewal. Annual plans are paid upfront for the year.