info@bravent.net+1 305 285 8513
Switch It On · Article 02

Too many AI pilots, too few in production: what companies are facing in 2026

Most companies are using AI. Few have scaled it. What the latest studies say about the tools, costs and workload piling up, and what the companies that get to production do differently.

Oct 20, 20268 min readBy Bravent · Switch It On
Switch It On · Article 2 of 4 · Previously: The hidden cost of AI without a plan

If your company has more AI trials, tools and agent experiments running than results to show for them, it isn't just you. We read fourteen studies published in 2026, most of them between May and September, covering more than 68,000 workers and executives, to see what other companies are running into right now and what the ones that scale do differently.

22%of organizations have scaled AI across more than one business unit Gartner, Sep 2026
37%attribute any EBIT impact to AI, the same share as a year ago McKinsey, Aug 2026
47%of workers spend more time managing AI than doing the work itself BCG, Jun 2026
12%of companies consistently weigh what AI delivers against what it costs KPMG, Sep 2026

Almost everyone is using AI. Few have scaled it.

The adoption question is settled. Nearly nine in ten organizations in McKinsey's 2026 survey use AI regularly in at least one function, and 86% of middle-market companies in RSM's survey have partially or fully integrated it.23 What has not moved at the same speed is the step from use to results.

Gartner surveyed 1,303 functional leaders between January and April 2026: only 22% have scaled AI across multiple business units or adopted an AI-first approach. McKinsey, surveying 1,719 executives in May and June, found 44% scaling AI somewhere in the enterprise, but only 37% attribute any EBIT impact to it, essentially unchanged from 2025. The group McKinsey calls high performers is still about 6% of companies.12

From using AI to seeing it in the numbersShare of organizations, 2026 surveys
Use AI regularly in at least one function~9 in 10
Say AI is scaling somewhere in the enterprise44%
Attribute any EBIT impact to AI37%
Scaled across multiple business units22%
Classed as AI high performers6%

Sources: McKinsey, The State of AI in 2026 (n=1,719, fieldwork May–Jun 2026), rows 1–3 and 5; Gartner functional leaders survey (n=1,303, Jan–Apr 2026), row 4. Different surveys and definitions; read as a pattern, not a funnel.

Company size matters. Among organizations with $1 billion or more in revenue, 54% are scaling AI; among smaller ones, about a third. For AI agents the gap is wider: 40% of large organizations are scaling them, up from 27% last year, while smaller organizations stayed at 22%.2

The mid-market paradox. In RSM's survey of 1,030 middle-market companies, 97% rate their AI pilots a moderate or high success and 54% say AI has beaten their ROI expectations. Yet only 17% are pursuing change across the enterprise; 45% are concentrating on places where AI delivers clear value today.3 Satisfaction with a pilot and impact on the P&L are two different measures, and most companies are still waiting on the second.

Five things other companies are running into right now

1. More tools than anyone is tracking

The tool count is growing from two directions. From the bottom up, 66% of office professionals at companies with $500 million or more in revenue have used AI tools at work that they believed were not allowed. At companies with 1,500 or more employees, the figure is 72%. Forty-four percent did it to work around the limits of the tools their company approved, and 34% have entered customer data into public AI tools.6

From the top down, 70% of the 2,000 CIOs and CTOs IBM surveyed say teams are deploying technology faster than IT can track it, and 77% say AI adoption is already outpacing their governance.7 Agents add to the count: Microsoft reports 15 times more active agents in Microsoft 365 than a year ago.9

2. The bill arrives before the value

Zylo, which tracks $75 billion in software spend, found spending on AI-native applications up 108% in a year, and 78% of IT leaders reported unexpected charges tied to AI features or usage-based pricing.10 85% of technology executives lack full visibility into real-time AI spend, and Gartner found 11% of organizations do not know what their function spent on AI in 2025.71 Usage-based pricing adds a cost line many budgets did not plan for: 82% of US executives investing in AI told EY they are concerned about token costs.11

Spending is still going up. 85% of functional leaders plan to increase AI spend in 2026, and 84% of middle-market companies expect theirs to rise.13 But only 12% consistently compare what AI delivers with what it costs across the organization.4

3. Employees feel more work, not less

BCG's survey of 11,749 workers found that 47% now spend more time managing and directing AI than doing the work itself, and 41% report a higher cognitive load.5 In a separate study of 2,500 knowledge workers, 42% said they spend more time checking AI output than the tool saves them, and 52% regularly correct colleagues' AI-generated work.12

Use is broad but shallow. In Gallup's Q2 2026 survey of 22,573 US employees, 52% use AI in their role, 30% use it a few times a week or more, and 15% use it daily.8 Even where AI does save time, it is often not redirected: among frontline users who save a full workday a week, 66% get limited or no guidance on what to do with it.5

How often US employees use AI at workShare of employed US adults, May 2026
Use AI in their role52%
A few times a week or more30%
Daily15%

Source: Gallup Q2 2026 workforce study, n=22,573, fieldwork May 6–20, 2026, ±0.9 pts.

4. Leadership and teams are not on the same page

85% of middle-market leaders agree that their executives are more enthusiastic about AI than their employees.3 Only 26% of AI users in Microsoft's 2026 Work Trend Index say leadership is clearly and consistently aligned on AI.9 CEOs in IBM's 2026 study estimate that only 25% of their workforce uses AI regularly, yet 86% believe their people have the skills to do so.13 And 81% of office professionals believe leadership plays by different AI rules than everyone else.6

5. Pilots stall on data and governance, not on the model

Asked what holds back deployment, middle-market companies put data quality first (34%), followed by security and privacy (30%), legacy systems integration (28%) and skills (28%). Among manufacturers whose pilots fell short, 51% pointed to data quality and 43% to integration.3 Agents raise the stakes: IBM's respondents averaged 54 AI agent incidents last year that needed human correction, and only 11% say they are fully ready for the scale of agent deployment they expect.7

What the companies that scale do differently

Across the studies, the companies that get AI into production share a short list of habits. None of them depends on buying a specific tool.

Companies that scale vs. the restShare of organizations with each practice
Leading groupEveryone else / all respondents
Fundamentally redesigned workflowsMcKinsey: high performers vs. others
~3 in 4~1 in 4
Consistently assess AI value against costKPMG: established ROI vs. all
48%12%
Formal “AI harness” layer to run AIKPMG: established ROI vs. all
86%55%
Employees use AI frequentlyGallup: with vs. without manager support
78%44%

Sources: McKinsey, Aug 2026; KPMG Global AI Pulse Q3 2026 (n=2,131); Gallup, Jul 2026.

  1. They redesign the work, not just add a tool. In BCG's data, companies that redesign workflows are 24 points more likely to see measurable business improvement. A clear strategy adds 25 points of impact; better tools without strategy and redesign add about 5.5
  2. They run AI as a portfolio and stop what doesn't pay. Gartner's high performers track ROI continuously and reallocate or stop underperforming projects; they report positive returns on 81% of their AI initiatives. Low performers did not know the return on 29% of theirs.1
  3. They build controls into the system. Organizations that embed control in their AI systems, rather than relying on manual review, report 25% fewer incidents, deploy 16 times more agents and report 18% higher operating margins.7
  4. Managers go first. Where employees say their manager actively supports AI use, 78% use it frequently; without that support, 44%. Only 36% of employees in organizations integrating AI strongly agree they have that support.14
  5. They start where returns already show up. The use cases leaders pursue most are cybersecurity threat detection and IT service desk automation (54% each). The ones most often reported with positive returns are IT asset and cost optimization (40%), synthetic data (28%) and code generation (23%).1

What this means for a 100 to 1,000 person company

Mid-market companies do not have a transformation office or a dedicated AI team, and they don't need one to act on this. The studies point to a few decisions that fit in one leadership meeting:

  • Count what you have. List the AI tools the company pays for, including expensed subscriptions and features inside existing licenses, with an owner and a monthly cost next to each. Most companies find more than they expected; that is where our first article started.
  • Choose one or two workflows, not ten pilots. Pick work the team does every week, with a cost you can see today (hours, tickets waiting, a process that depends on one person), and a business owner who wants the result.
  • Measure the process, not the logins. An "active user" count tells you people opened the tool. Decide before you start which number in the process should change.
  • Settle governance before rollout. Data quality, access and oversharing are where pilots stall. Agree with security on what the AI may see before it is switched on, not after.
  • Tell people what to do with the time. If a workflow saves hours, decide in advance where those hours go. Otherwise the saving is real but invisible.

There is also a cost to leaving things as they are. Microsoft raised commercial Microsoft 365 prices on July 1, 2026; Microsoft 365 E3, for example, went from $36 to $39 per user per month, with more Copilot capability included in the suites.15 Capability that is paid for but not running a business process costs more every month it stays switched off.

Three questions for your next leadership meeting. How many AI tools are we paying for, and who owns each one? Which of our pilots has a business owner and a number it is supposed to move? What did we spend on AI last quarter, and what changed because of it?

This is the second article in our Switch It On series. Next: the four levels of AI use, from asking to production, and a three-minute check to see where your company stands.

How we chose the data. We used studies published in 2026, most of them between May and September with fieldwork in 2026, and linked each figure to its primary source. Surveys measure different things: some ask whether respondents are satisfied with AI, others whether it shows up in financial results. We say which one each figure measures and do not combine figures from different surveys into a single number.
Sources
1. Gartner — survey of 1,303 functional leaders (organizations with $50M+ revenue; fieldwork Jan–Apr 2026). Press release, Sep 1, 202622% have scaled AI across multiple business units or adopted an AI-first approach; ~11% don't know what their function spent on AI in 2025; 85% plan to increase AI spend in 2026; high performers report positive returns on 81% of initiatives, low performers don't know the return on 29%; use cases pursued and with positive returns. Gartner newsroom
2. McKinsey — The State of AI in 2026: On the road to ROI (n=1,719, 97 countries; fieldwork May 4–Jun 8, 2026). Aug 25, 2026Nearly 9 in 10 use AI regularly in at least one function; 44% scaling (38% in 2025); 54% of $1B+ companies vs. about one-third of smaller ones; 37% attribute EBIT impact; ~6% high performers; ~3/4 of high performers redesigned workflows vs. ~1/4 of others; agents scaling at 40% of large vs. 22% of smaller organizations. McKinsey
3. RSM — Middle Market AI Survey 2026: U.S. and Canada (n=1,030, companies with $30M–$10B revenue; fieldwork Mar 5–16, 2026). Jul 21, 202686% integrated; 97% moderate or high pilot success; 54% exceeded ROI expectations; 84% expect spend to rise; 85% say executives are more enthusiastic than employees; inhibitors: data quality 34%, security/privacy 30%, legacy integration 28%, skills 28%; 45% clear value today vs. 17% enterprise-wide. Manufacturing cut: data quality 51%, integration 43%. RSM newsroom · Manufacturing insights
4. KPMG — Global AI Pulse, Q3 2026 (n=2,131 senior leaders, 20 countries). Sep 24, 202612% consistently assess AI value against cost (48% among organizations with established ROI); 61% review AI costs at approval; formal AI harness layer 55% (86% among established ROI). KPMG
5. BCG — AI at Work 2026 (n=11,749 workers, 14 markets). Jun 3, 202647% spend more time managing and directing AI than doing the work; 41% increased cognitive load; 42% of regular frontline users save a full workday a week, 66% of them with limited or no guidance on using it; workflow redesign +24 pts; strategy +25 pts vs. ~5 pts from tools alone. BCG press release
6. PagerDuty / Wakefield Research — Shadow AI survey (n=1,250 non-IT office professionals at $500M+ companies, US, UK, Australia, Japan; fieldwork Apr 9–20, 2026). Jun 202666% used AI they believed was not allowed (72% at 1,500+ employees); 44% to work around approved tools; 34% entered customer data into public AI tools; 81% believe leadership follows different rules. PagerDuty
7. IBM Institute for Business Value — CIO/CTO study (n=2,000 technology executives, 33 geographies; fieldwork Jan–Apr 2026). Jun 8, 202670% say teams deploy technology faster than IT can track; 77% say adoption outpaces governance; 85% lack full visibility into real-time AI spend; average of 54 agent incidents last year; 11% fully ready; embedded control: 25% fewer incidents, 16x more agents, 18% higher operating margins. IBM newsroom
8. 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; 47% say their organization has integrated AI tools (41% in Q1). Gallup
9. Microsoft — 2026 Work Trend Index (n=20,000 AI-using knowledge workers, 10 countries, plus Microsoft 365 telemetry). May 5, 2026Active agents in Microsoft 365 up 15x year over year; 26% of AI users say leadership is clearly and consistently aligned on AI. Microsoft WorkLab
10. Zylo — 2026 SaaS Management Index ($75B+ in spend, 40M+ licenses). Jan 29, 2026AI-native app spend +108% year over year; 78% of IT leaders reported unexpected charges tied to AI features or consumption-based pricing. Zylo
11. EY — US AI Pulse (n=534 US SVP+ leaders; fieldwork Apr 24–May 17, 2026). Jul 28, 202682% of those investing in AI are concerned about token costs. EY newsroom
12. The Adaptavist Group — The Human Cost of AI Transformation (n=2,500 knowledge workers, US, UK, Canada, Germany, Spain; fieldwork Mar 2026)42% spend more time verifying AI output than it saves; 52% regularly correct colleagues' AI-generated work. Vendor research. Report (PDF)
13. IBM Institute for Business Value — 2026 CEO Study (n=2,000 CEOs; fieldwork Feb–Apr 2026). May 4, 2026CEOs estimate 25% of the workforce uses AI regularly; 86% believe employees have the skills. IBM newsroom
14. Gallup — AI and workplace productivity. Jul 27, 2026 (updated Sep 30, 2026)78% frequent AI use with active manager support vs. 44% without; 36% strongly agree their manager actively supports AI use. Gallup
15. Microsoft — Microsoft 365 pricing and packaging updates, effective July 1, 2026Microsoft 365 E3 $36 → $39; Microsoft 365 E5 $57 → $60; Office 365 E3 $23 → $26; Business Standard $12.50 → $14 (USD, per user per month); Business Premium unchanged. Microsoft Licensing Resources
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