Organizational learning
Individual AI use becomes team capability only when the organization changes with it: incentives, ownership of risk and trust. Without that, pilots succeed technically and still stall, and usage grows while the company learns nothing.
Written by
-
Benedikt Stemmildt Founder & Co-CEO
Updated:
Getting Started 2
Our position. We treat adoption as an organizational topic, because agents change the organization around the code more than the code itself (opens in a new tab).
The tools speed up individuals and make collaboration harder. One team that studied its own adoption had to add synchronization on purpose: more co-working sessions, shared experiment artifacts and purpose-built internal tooling (Rotational Labs - What We’ve Learned From 3 Months Living with AI Coding Tools (opens in a new tab)).
Usage counts hide whether anything was learned. The useful question shifts from “are people using AI?” to “what changed because we spent those tokens?” (When everyone has AI and the company still learns nothing (opens in a new tab)). Any raw metric of AI usage invites gaming, so separate deep use from shallow theatre (video essay on the AI-native talent market (opens in a new tab)).
The bottleneck is rarely model capability and usually institutional readiness. A pilot that succeeds technically in a week can stall for months over who owns risk acceptance for AI-generated output (A Country Full of Geniuses (opens in a new tab)). The underdiagnosed resistance concerns positioning rather than job loss: whether one’s expertise will still matter. It surfaces as vague objections about tooling or quality, and leaders have to name it directly before it hardens into active resistance (The Drag Problem in AI Adoption (opens in a new tab)).
Start here
- Adoption gaps and resistance: Why technically successful AI pilots stall when institutions, incentives, and trust do not change with them.
Related
- Getting Started and Learning: how individual practice starts before it becomes team capability.
- What moves adoption: the practices with the strongest measured effect on sustained use.
- Leadership: the environment in which teams decide well on their own.
- The State of AI-Native Engineering report: how few leaders changed review, roles or onboarding alongside the tools.
- Moving away from Agile: why company-level gains need a changed operating model.
Resources
Articles
- A Country Full of Geniuses (opens in a new tab) - LinkedIn article arguing the AI bottleneck is institutional readiness, so technically successful pilots stall over who owns risk acceptance.
- The Drag Problem in AI Adoption (opens in a new tab) - LinkedIn article on organizational drag in AI adoption and the underdiagnosed fear about one’s positioning rather than job loss.
- What We’ve Learned From 3 Months Living with AI Coding Tools (opens in a new tab) - Rotational Labs internal study finding that coding tools speed individuals but make collaboration harder, requiring deliberate synchronization.
- When everyone has AI and the company still learns nothing (opens in a new tab) - Blog essay shifting the adoption question from whether people use AI to what changed because the tokens were spent.
Posts
- Agents change the organization around the code more than the code itself (opens in a new tab) - LinkedIn post treating AI adoption as an organizational topic, because agents reshape the organization more than the code.
Talks and videos
- The Red Queen Trap: Who Survives 2026 (opens in a new tab) - Video essay on the AI-native talent market, warning that raw AI-usage metrics invite gaming and hide shallow theatre.
In this section
- Adoption gaps and resistance
AI pilots stall when the organization does not change with the tool. Usage spreads unevenly and shallowly, nobody owns the risk of AI-generated output, and engineers fear for their expertise more than their jobs, so adoption needs structural and cultural work alongside the rollout.