How it works
From first question to closed ticket
Claudia asks, your technician approves, and the fix is documented before the ticket closes. We agree the first ticket types and who approves what with your team before your pilot begins.
Supervised flow ↓
Concierge
Response drafted, missing detail collected
Triage
Ticket type and priority suggested
Dispatch
Technician assignment recommended
Resolution
Plan prepared for human approval
Watchdog
SLA clock watched, breach risk flagged
One ticket · Five channels · No new console
Every action requires human approval at the fleet's current level.
Initial launch stacks
Claudia is invite-only for a limited supervised launch. Your pilot starts with the ticket types and approvals we agree with your team.
Getting started
From a new ticket to a closed one
- 01
Confirm your stack and scope
Start with Autotask + Datto RMM or ConnectWise PSA + ConnectWise Automate. Together, we agree the ticket types Claudia handles first and who approves what.
- Your PSA and RMM pairing
- The first ticket types
- Who approves, per client
- 02
Claudia asks and checks
When a ticket opens, Claudia asks the user the targeted questions a senior technician would, and checks what it can without changing anything.
- Targeted questions
- Read-only checks first
- A diagnosis you can read
- 03
Your technician approves
Claudia proposes the fix in one line and asks the technician who owns the client. Nothing changes until they approve.
- A named approver
- The exact change
- How it will be checked
- 04
Fixed, documented, closed
Claudia runs the approved fix, confirms it with the user, writes the closure note from the work done and closes the ticket.
- Confirmed with the user
- A closure note on the ticket
- The ticket closed
The guide · 10 pages · PDF
Graduated autonomy: the MSP owner's guide to L0 to L4
How a desk raises an agent from advisory to supervised on evidence, and never past a human by default.
Who does what
Most of the work is ours
Onboarding is a two-hour session, included on every plan and every invite at no charge.
We handle
- Review your PSA/RMM pairing and setup requirements
- Agree the first ticket types and approvals with you
- Guide the pilot and review the results with your team
You handle
- Choose the ticket types to start with
- Name the technicians who approve fixes
- Review the outcomes and closure notes with us
The broader platform
One ticket, through the line-up
Claudia's five service-desk agents, in the order the operating model hands the ticket on. This describes the broader lifecycle; the limited launch starts with the supervised workflow agreed for your pilot.
- 01AI Client ConciergeThe model defines a client-facing stage for password-reset guidance, ticket status, guided setup and collecting the detail the service desk needs. Pilot capabilities are agreed separately.
- 02AI Intake & Triage AgentThe model defines an intake stage that matches requests to ticket types and proposes priority against the client's SLA. The current launch is supervised and scoped with your team.
- 03AI Dispatch & Scheduling AgentThe model defines assignment recommendations using skill, tier fit, pod load and calendar availability, with supporting rationale and access checks. Pilot capabilities are agreed separately.
- 04AI Autonomous Remediation AgentThe model defines a resolution plan, verification steps and closure notes for each ticket type. In the launch, Claudia runs the fix only after your technician approves it.
- 05AI Service Desk WatchdogThe model defines a watchdog stage for SLA monitoring, client follow-up and breach-risk alerts. These responsibilities describe the broader model; pilot capabilities are agreed separately.
Not the same thing
You already have automation. This is a different tool.
Compare execution approach, permissions and human oversight, then agree the scope of your supervised pilot.
Scroll sideways to compare all three approaches.
| Approach | RPA / workflow builders | Helpdesk chatbots | Claudia's supervised launch |
|---|---|---|---|
| Execution approach | Runs configured workflows and scripted steps. | Handles conversations; tool actions depend on the product and configuration. | Claudia’s AI agents resolve tickets end to end: they ask the right questions, get your technician’s approval, fix the problem, document it and close the ticket. |
| PSA and RMM access | Depends on the workflow, connector and tenant permissions. | Depends on the product, enabled tools and tenant permissions. | Tenant permissions and permitted actions are confirmed before pilot work begins. |
| Human oversight | Approval steps depend on the configured workflow. | Review and escalation depend on the product and configuration. | A technician reviews the script, execution scope and actual result. |
| Initial deployment scope | Depends on the configured workflows and connected systems. | Depends on the product, knowledge sources and enabled tools. | Autotask + Datto RMM or ConnectWise PSA + ConnectWise Automate. The task and endpoint scope are agreed for each supervised pilot. |
Products and configurations vary. Claudia's broader operating model describes intended capabilities, not verified availability in your environment. Pilot access, permissions and workflow scope are agreed separately; completed execution needs its own evidence.
Questions
What people ask before starting
Which stacks are the first launch focused on?
Starting with Autotask + Datto RMM and ConnectWise PSA + ConnectWise Automate. Claudia is invite-only for a limited supervised launch. Claudia’s AI agents resolve tickets end to end: they ask the right questions, get your technician’s approval, fix the problem, document it and close the ticket. Pilot scope and prerequisites are confirmed with your team.
What does my team actually have to change?
For the limited launch, choose the ticket types Claudia handles first and name the technicians who approve fixes for each client. Claudia works inside your existing PSA and RMM; your team reviews the approvals, outcomes and closure notes with us before the scope widens.
Can the agents act without a human approving?
The current limited launch is supervised. The broader product uses graduated autonomy, but unattended execution is not part of this launch offer. Any later change in autonomy needs a separately agreed scope and evidence.
What if a suggestion is wrong?
Your technician sees the diagnosis and the exact change before approving, and can reject it; nothing changes until they approve. If a fix does not resolve the problem, Claudia hands the ticket back with everything it found rather than trying something else on its own.
Will this work on our messy documentation?
Documentation and ticket history are part of the broader operating model. Their quality, access and relevance are reviewed when the pilot is scoped. Incomplete documentation is something we plan around, not something we promise will produce a reliable answer.
Do we have to migrate off our PSA?
The initial launch is designed around your existing Autotask + Datto RMM or ConnectWise PSA + ConnectWise Automate pairing. Confirm tenant access, permissions and the technician's workflow during scoping; catalogue coverage alone does not establish that every setup is ready.
Who does the setup work?
The published offer includes a two-hour onboarding session at no charge. Our team reviews the agreed workflow, integration prerequisites and technician walkthrough with you. The session is not a guarantee that every tenant or broader catalogue workflow will be ready in two hours.
Want to take Claudia for a spin in your IT environment?
Claudia is invite-only for a limited supervised launch. Invited MSPs receive a 30-day free trial in an agreed test or pilot environment — no card, and no onboarding fee. Scope is confirmed before access.