Monthly thinking room
How much control do agents need so that companies can hand work over to them, and how does real impact show? This edition shows how pioneers build review, limits and measurement and what leaders can adopt from them.
For working with your own AI assistant. How it works
We handpicked 119 podcast episodes released in July 2026 and distilled 357 insights from them. These ten patterns bring together recurring experiences of setting limits for agents, ensuring reliable results and making their value to the company measurable.
Patrick McQuaid, Group Head of Data, AI and Analytics at NGM Group, presents his AI risk framework to the company's own model and has it look specifically for weaknesses and gaps.
Lawyer Dennis Engbrink (ZIRNGIBL) has the same set of facts assessed one after another from a legal perspective and from the perspective of the producer, organizer or intermediary, and treats the outputs like advice from consultants.
Because AI assistants tend to agree by default, Anna Ott, Vice President People at HV Capital, built a Claude skill that responds in the style of a Berlin bus driver and thereby deliberately generates pushback.
Status: confirmed, 1 new supporting episode. Christoph Werner, Chairman of the Management Board of dm-drogerie markt, writes emails and columns himself and at most asks AI whether a text contains logical gaps, contradictions or potential resistance.
Supported by these conversations
A Statista customer burned through a quarter of a million credits in the first three days with an agent that had gotten out of control; Statista works with stop-loss limits beyond which usage is stopped.
Ben Hoskins (CTO, NewStore) blocks his coding agent's bash actions and instead has refactorings carried out through IntelliJ functions connected via MCP.
Manu Narayan (CIO, GitLab) anchors guardrails and governance on the repo side, because no reliable control can be enforced on developers' machines, whether they use Claude Code, Codex or open models.
Status: unchanged
Supported by these conversations
321 MED has agents that know nothing of each other check one another, so that a second AI stops an incorrect output to patients before it goes out.
The CPTO of felmo embeds quality rules as hooks that enforce a security check and an architecture check before the push to GitHub, because skills get forgotten in the model's context.
Parloa has every pull request reviewed by several specialized agents; an LLM judge evaluates their consensus and sends risky pull requests to a person for review.
Status: unchanged
Supported by these conversations
With a subscription
With a subscription you read all 10 with their sources and download them as a text file.
The complete collection
119 conversations, ordered from newest to oldest.
Organization before technology
AI transformation is 70 percent organizational and people work. Anyone who treats AI as a highly gifted new team member rather than as a tool has to redesign roles, maturity levels and development conversations, not just buy licenses.
With a subscription
With a subscription you open all 119 conversations of this room with their insights, search the catalogue and download the files.
1 conversation added · none removed
1 confirmed · 9 unchanged
With a subscription you see which conversations, findings and recommendations changed.
Compared with V2 · 14 Sept 2026.
