info@bravent.net+1 305 285 8513
Switch It On · Article 03

Asking AI questions is not putting AI to work

Most companies use AI to ask, summarize and draft. Few have a business process that runs differently because of it. The four levels of AI use, where companies stand in 2026, and what changed in the tools this year.

Nov 3, 20268 min readBy Bravent · Switch It On

Ask a leadership team whether the company uses AI and the answer is almost always yes. Ask which process now runs differently because of it, who owns that process, and which number moved, and the room goes quiet. That gap, between using AI and putting it to work, is where most of the 2026 data points.

15%of US employees use AI at work every day; 52% use it at all Gallup, Jul 2026
34%of organizations report significant employee adoption of AI agents KPMG, Sep 2026
22%have scaled AI across more than one business unit Gartner, Sep 2026
13%think they have the right governance in place for AI agents Gartner, Apr 2026

Using AI and putting it to work are two different things

Using AI means a person asks a question and gets a better answer: a summary of a long thread, a first draft of an email, a formula in a spreadsheet. It is useful, and it is where almost every company starts. Putting AI to work means a business process runs differently: a supplier invoice is matched and routed without anyone retyping it, an IT ticket is resolved before it reaches the queue, a quality report is assembled from the line data overnight. The first saves minutes for individuals. The second changes a number someone is accountable for.

The 2026 data shows most companies still sitting on the first side. In Gallup's survey of 22,573 US employees, 52% use AI in their role, but only 15% use it daily.1 In Microsoft's 2026 Work Trend Index, 86% of AI users treat what AI produces as a starting point rather than a finished piece of work, and only 14% of teams outside the most advanced group have AI-assisted workflows documented and repeatable across the organization.2 McKinsey finds 37% of companies attributing any EBIT impact to AI, unchanged from last year.4

None of this means the tools are failing. It means that a tool on everyone's desktop is not the same as a process that runs on it.

The four levels of AI use

We use four levels to describe where a company stands. They are not a maturity model to be completed in order over years; they are a way to name the current state honestly, so the next step is obvious.

Level 1

Asking

People use ChatGPT, Copilot or similar on their own to ask, summarize and draft. No process runs differently.

Signal: nobody can say what the company spends on AI or who owns it.

Level 2

Piloting

Copilot or another tool is switched on for a group. People like it. The business hasn't changed yet.

Signal: success is measured in licenses assigned and active users.

Level 3

Building

At least one process runs on AI in production: an agent or workflow with a business owner and a number it moves.

Signal: someone outside IT asks for the next one.

Level 4

In production

Several processes run on governed agents, with security, an inventory and a roadmap. Value is measured against cost.

Signal: stopping an agent that doesn't pay is a routine decision.

Where companies are in 2026

No single survey measures the four levels, so read the figures below as a pattern rather than a funnel. They come from different studies with different definitions.

How far AI has gone inside companiesShare of employees or organizations, 2026 surveys
Employees who use AI in their role52%
Organizations with significant employee use of AI agents34%
Organizations that scaled AI across several business units22%
Employees who use AI daily15%
Organizations with the right governance for AI agents13%

Sources: Gallup Q2 2026 (n=22,573 US employees), rows 1 and 4; KPMG Global AI Pulse Q3 2026 (n=2,131), row 2; Gartner functional leaders survey (n=1,303, Sep 2026), row 3; Gartner, Apr 2026, row 5. Different surveys and definitions; read as a pattern, not a funnel.

Level 1 and 2: where most companies are

Half of the 20,000 AI users in Microsoft's study fall into what it calls the "emergent" zone: using AI, but without the team practices that turn it into new ways of working. Only 19% are in the frontier group.2 Among manufacturers, Rockwell Automation's 2026 survey of 1,560 companies found 18% still in pilot mode with smart manufacturing technologies, and only 43% of the data they collect being used effectively.10 Pilots look good on their own terms: 97% of middle-market companies rate them a success, yet only 17% are pursuing change across the enterprise.9

Level 3: agents are arriving faster than the rules for them

Agents, AI that carries out steps in a process rather than answering a question, moved from demo to daily use this year. 34% of organizations in KPMG's September survey report significant employee adoption of AI agents, up from 25% in the first quarter.3 Active agents in Microsoft 365 grew 15 times in a year.2 Size still matters: 40% of large organizations are scaling agents, against 22% of smaller ones.4 In manufacturing, 56% of middle-market companies in RSM's 2026 survey already use agentic AI in some form.9

Level 4: few are there, and governance is the reason

Only 22% of organizations have scaled AI across more than one business unit.5 Only 13% believe they have the right governance for AI agents, and Gartner expects the average Fortune 500 company to have more than 150,000 agents in use by 2028.6 IBM's CIOs and CTOs averaged 54 agent incidents last year that needed human correction, and only 11% say they are fully ready for the agent deployment they expect.8

What separates the levels is not the tool. In BCG's survey of 11,749 workers, companies that redesign workflows are 24 points more likely to see measurable business improvement, and a clear strategy adds 25 points. Better tools without either add about 5.7

What changed in the tools this year

In 2026 the software moved from answering to doing, and much of it now sits inside the Microsoft 365 plan companies already pay for. For a business leader, four changes matter:

  • Copilot Chat does more without an extra license. Since the July 2026 packaging update, the Copilot Chat included in Microsoft 365 plans is aware of the user's inbox and calendar and gives access to Word, Excel and PowerPoint agents.11
  • Building an agent no longer needs a development project. Users with a Microsoft 365 Copilot license can build and use internal agents on company data with Copilot Studio at no additional cost. Copilot Business, for companies up to 300 users, lists at $21 per user per month.12
  • Agents that act are billed by use. Advanced experiences such as Copilot Cowork and Copilot Autopilot are charged through Copilot Credits, with spending controls in the Microsoft 365 admin center. This is a new cost line that needs an owner.12
  • Governance became a product. Agent 365, generally available since May 1 at $15 per user, gives IT one place to observe, govern and secure agents; Microsoft 365 E7 bundles it with E5 and Copilot at $99 per user.13

Manufacturers are already using these pieces in production. Microsoft reports that AGCO has several hundred employee-built agents in production on Copilot Studio, and that in some quality workflows reviews that used to take weeks now take about an hour. These are customer-reported results published by Microsoft.14

The technology reached Level 3 and 4 faster than most organizations did. The constraint in 2026 is not what the software can do; it is ownership, data and governance.

How to move up one level

  • From Asking to Piloting: pick one process, not ten use cases. Work the team does every week, with a visible cost today: hours spent, tickets waiting, a task that depends on one person.
  • From Piloting to Building: name a business owner and the number that should move before you start. Measure the process, not the logins. Redesign the steps around the AI rather than adding AI to the old steps.
  • From Building to In production: keep an inventory of every agent, give each one an identity and an owner, decide what data it may see, monitor what it does and retire the ones that don't pay. These are the controls Gartner recommends for agent sprawl.6
Five questions to find your level. How many people work here? Which Microsoft 365 plan do we mainly use? How do we use AI today: asking, piloting, building or in production? Is there a named owner for AI and a rule about which company data AI tools may access? Which process hurts most today? Those are the five questions in our three-minute AI Activation Check, which returns your level and what switching on the next step is worth.
How we chose the data. We used studies published in 2026 and linked each figure to its primary source. Vendor figures, including customer results published by Microsoft, are labeled as such. We do not combine figures from different surveys into a single number.
For manufacturing leaders in South Florida

Manufacturing AI Executive Breakfast: From AI Potential to Business Outcomes

Microsoft and Bravent host an executive discussion and a short workshop to identify and prioritize the highest-impact AI opportunities in your operation. Not a product presentation.

Wednesday, December 2, 2026 · 8:30–11:00 AM ET · Microsoft office, 830 Brickell Plaza, Miami

Register on Microsoft Events

Sources
1. Gallup — Q2 2026 workforce study (n=22,573 employed US adults; May 6–20, 2026; ±0.9 pts). Jul 20, 202652% use AI in their role, 30% a few times a week or more, 15% daily. Gallup
2. Microsoft — 2026 Work Trend Index (n=20,000 AI-using knowledge workers, 10 markets; fieldwork Feb–Apr 2026; plus Microsoft 365 telemetry). May 5, 202686% treat AI output as a starting point; documented, repeatable AI workflows at organization level: 25% of frontier teams vs. 14% of others; readiness zones: frontier 19%, emergent 50%; active agents in Microsoft 365 up 15x year over year. Microsoft WorkLab
3. KPMG — Global AI Pulse, Q3 2026 (n=2,131 senior leaders, 20 countries). Sep 24, 202634% report significant employee adoption of AI agents, up from 25% in Q1; 55% operate a formal AI harness layer; 12% consistently assess AI value against cost. KPMG
4. McKinsey — The State of AI in 2026 (n=1,719; fieldwork May 4–Jun 8, 2026). Aug 25, 202637% attribute EBIT impact to AI; agents scaling at 40% of large vs. 22% of smaller organizations. McKinsey
5. Gartner — survey of 1,303 functional leaders (fieldwork Jan–Apr 2026). Sep 1, 202622% have scaled AI across multiple business units or adopted an AI-first approach. Gartner newsroom
6. Gartner — Six steps to manage AI agent sprawl. Apr 28, 202613% think they have the right AI agent governance in place; by 2028 the average Fortune 500 enterprise will have over 150,000 agents in use; recommended controls: governance rules, central inventory, identities and lifecycle, data access, monitoring, training. Gartner newsroom
7. BCG — AI at Work 2026 (n=11,749 workers, 14 markets). Jun 3, 2026Workflow redesign +24 pts; clear strategy +25 pts; better tools alone ~5 pts. BCG press release
8. IBM Institute for Business Value — CIO/CTO study (n=2,000; fieldwork Jan–Apr 2026). Jun 8, 2026Average of 54 agent incidents last year needing human correction; 11% fully ready for expected agent deployment. IBM newsroom
9. RSM — Middle Market AI Survey 2026 (n=1,030; manufacturing cut n=129). Jul 21, 202697% rate pilots a moderate or high success; 17% pursue enterprise-wide change; 56% of manufacturers use agentic AI. RSM newsroom · Manufacturing insights
10. Rockwell Automation — 2026 State of Smart Manufacturing Report (n=1,560 manufacturers, 17 countries; Sapio Research). May 19, 202659% actively use smart manufacturing technologies, 18% remain in pilot mode; 34% of operations AI-augmented; 43% of collected data used effectively. Rockwell Automation
11. Microsoft — Microsoft 365 pricing and packaging updates, effective July 1, 2026Copilot Chat enhancements across suites include inbox and calendar awareness and access to Word, Excel and PowerPoint agents. Microsoft Licensing Resources
12. Microsoft — Copilot plans and pricing for business (accessed Oct 29, 2026)Copilot Business add-on $21 list ($18 promotional through Dec 31, 2026); Copilot Studio included for internal agents with a Microsoft 365 Copilot license; Copilot Cowork, Copilot Code, Copilot Autopilot and Work IQ APIs billed through Copilot Credits. Microsoft
13. Microsoft — Introducing the first Frontier Suite built on intelligence + trust. Mar 9, 2026Agent 365 generally available May 1 at $15 per user; Microsoft 365 E7 (E5 + Copilot + Agent 365) at $99 per user. Official Microsoft Blog
14. Microsoft — Industrial intelligence unlocked: the next competitive advantage in manufacturing. Sep 15, 2026AGCO: several hundred enterprise agents in production; some quality reviews from weeks to about an hour. Customer-reported results published by Microsoft. Microsoft Cloud Blog
Switch It On · Bravent

Want to know what this looks like in your company?

Tell us who you are and what you'd like: more information about the Switch It On program, or a meeting with the Bravent team to look at your Microsoft 365 tenant together. Someone from Bravent will get back to you.

By sending this you agree that Bravent may contact you about your request, per its privacy policy. Or write to switchiton@bravent.net.
Contact with us