Approval Workflows — When Mingo Asks Permission

AI INTEGRATIONBEST PRACTICESOPENFRAMEPSAWORKFLOW AUTOMATION

Phase 6 — Tickets & PSA Workflow · Step 5

Section

June 23, 2026

Published

Vladislav Marchenko

Vladislav Marchenko

Head Of Marketing

Approval Workflows — When Mingo Asks Permission

Phase 6 — Tickets & PSA Workflow · OpenFrame Onboarding

Here's the rule that makes AI-assisted tickets safe to run: the AI never changes a machine on its own. When Fae or Mingo wants to do something on a device — run a command, apply a fix — it stops and asks you first. This guide covers what triggers that, what you're actually approving, and how to handle it.


What triggers an approval

The AI can read and reason freely, but the moment it wants to execute an action on a device, it pauses for a human. That's when:

  • A ticket flips to Technician approval required — you'll see the badge right on the board card and inside the ticket.
  • An action card appears in the chat with the proposed action and two buttons: Approve and Reject.

So approvals are about doing, not talking. Asking Mingo a question is free; letting it touch a machine needs your sign-off.


What you're approving

The action card is built to be reviewed, not rubber-stamped. It shows:

  • The exact action — e.g. the PowerShell command the AI wants to run, shown in a code block you can expand and read in full.
  • A plain-language description of what it does and what it'll return — e.g. "Find the pending update KB4589208 among pending updates and return its properties (KB IDs, description, flags, URLs, categories, size)."

Read both before you click. The description tells you the intent; the command tells you exactly what will execute.


Approve or reject

  • Approve — the action runs on the linked device, and the result comes back into the chat. Use this once you've read the command and you're comfortable with what it does.
  • Reject — the action is declined and nothing runs. Use this if it's the wrong fix, the wrong machine, the wrong time, or you just want to handle it yourself. The AI can then propose a different approach.

You're the control point. Nothing reaches the endpoint until you say so.


Good habits

  • Actually read the command. The whole point of the step is the review — an approval you didn't read is just an autopilot you pretended to supervise.
  • Confirm the target. Make sure the ticket's linked device is the machine you mean before approving anything that changes state.
  • Reject freely. Rejecting isn't a failure — it's you steering. The AI adapts to it.
  • Escalate when unsure. If an action looks risky and you're not certain, reject it and handle it manually (or via Run Script with a tested script from Phase 5).

Quick checklist

  • Recognized the Technician approval required badge as "AI wants to act"
  • Read the command and the plain-language description on the action card
  • Confirmed the linked device is the right target
  • Approved only what you understood; Rejected anything off
  • Reviewed the result that came back after approving

What's next

That completes Phase 6 — Tickets & PSA Workflow. Your tickets now flow from AI triage through human-approved action to resolution — and sync to your PSA if you connected one (Connect Your PSA). Next is Phase 7 — Remote Access, for when you need to get hands-on with a device directly.


Based on OpenFrame v0.9.19. The approval experience and what actions require sign-off are actively evolving — re-check the console before assuming any action runs without approval.

Vladislav Marchenko

Head Of Marketing

Hi all! My name is Vlad and I’ve been brought on to head the marketing team at Flamingo. Thankfully, this isn’t the first time I will be building a marketing department from scratch, so the experience should come in handy. Now it’s time to dive into the world of MSPs and find myself in this new world.

Related Content

Product Releases

Webinars

Case Studies

Blog Posts

Frequently Asked Questions

MSP AI Agents

Yes. In production MSP shops today, 10% to 25% of tickets close before a human opens them. Thread alone has processed 173 million tickets across 750-plus MSP partners at 96% triage accuracy, handing back 490,000-plus technician hours. Agents own the low-risk, high-volume work (password resets, MFA enrollment, known installs, onboarding and offboarding) and flag anything that touches production data or needs judgment for a human to take.
On a five-person desk, reported deployments show $78,000 to $130,000 in annual direct labor savings, roughly 30% fewer escalations, and 15% to 20% better SLA compliance. Broader MSP adoption data adds ticket handling time cut by 45% and five to 12 points of margin, all from reclaimed capacity rather than headcount cuts.
ConnectWise AI is the umbrella for ConnectWise's AI features on the Asio platform: the Sidekick GenAI assistant and ConnectWise RPA. It handles ticket triage, sentiment analysis, AI-assisted scripting, and natural-language automation across PSA and RMM, delivered through the ConnectWise Pro package.

AI MSP

Most MSPs start with AI features inside their existing PSA, RMM, and ticketing systems rather than standalone products. Common categories include AI ticket triage, alert correlation, scripting assistants, and AI-native all-in-one platforms like OpenFrame that run intelligence across the whole stack.
Start with a readiness assessment, not a tool purchase. Confirm your ticket history is clean and your RMM, PSA, and monitoring systems connect. Then pick one high-volume, low-risk workflow, usually ticket triage, and pilot it on internal tickets before any client sees it.
Automate high-volume, low-risk tasks first. Ticket triage and alert noise reduction top the list because they run constantly and a human still resolves the underlying issue. Save security approvals, billing changes, and client-facing actions for later, always with a human in the loop.

AI Safety

It can be, with governance. Keep a human in the loop on high-risk actions, log every automated step for audit, and choose platforms that keep your data yours with no vendor lock-in. Pilot on internal data first so you catch issues before client systems are involved.

AI for MSPs

Set a baseline before rollout, then track tickets closed per technician, mean time to resolution, percentage of tickets resolved with no human touch, technician hours reclaimed, and cost per ticket. AI-driven automation commonly cuts operational cost per ticket by 25 to 40%.

About OpenFrame

OpenFrame isn't built to plug into your stack. It replaces it. Instead of duct-taping a dozen tools together (RMM, MDM, SIEM, patching, remote access, each its own login and bill), we bundle it into one unified platform: RMM, MDM, monitoring, automation, remote access, patch management, security monitoring, and ticketing, plus built-in AI copilots. So "does it integrate with X?" usually means: you won't need X anymore.

Open Source ITSM

FreeITSM is a free, open-source IT service management (ITSM) platform with twenty modules, including ticketing, a CMDB, a knowledge base, business-process mapping, and an AI integration. It was built by Ed Mozley, an IT manager at a London law firm.