
Vice President @Capgemini. | Building at the intersection of AI, data, and business transformation | Views my own
Chicago, IL
Joined February 2009
- Tweets9.2K
- Following772
- Followers1.7K
- Likes1.1K
Spoke at Microsoft Ignite today with Caroline Matthews, at the Anthropic booth. The subject: Claude agents working through a 40,000-deduction backlog in CPG, investigating each dispute and resolving it, and the process learning to fix itself as they went.
1
15
Full post: linkedin.com/posts/tinholt_m…
13
Exception-based oversight beat universal human approval by $21 to $29 per transaction across 9,000 agent decisions. Accuracy was 98 to 100% on complete records.
1
10
The Dog That Didn't Bark: when one decisive record was silently missing, accuracy fell to 30 to 38%. Agents approved 72 to 95% of defect cases without a flag when the missing record would have ruled out fraud. Full write-up: medium.com/@tinholt/the-dog-…
8
9,000 real agent decisions, three Claude models, five back-office workflows, four oversight regimes. Pre-registered. Full human approval never came out on top.
2
1
31
Exception-based review caught 62% of mistakes at $3,000 per 100 errors. Full approval caught 69% at $30,000. Where you place oversight matters more than how much you buy. dinand.com/research/the-auto…
1
13
What happens when you send more agent work to review but keep the review team the same size? I ran 90,568 simulated configurations to find out.
1
25
Fixed team: the delegation margin falls, slope −0.593. Grow the team in step with the load: it rises, +1.148. Same routing decision, opposite sign.
1
18
Past 0.8 sustained utilisation the margin itself turns negative. Full walk-through: medium.com/@tinholt/oversigh…
19
90,880 configurations of agent organisations. Delegation depth weighed more against quality than anything else in the model. The first version had one flaw: its reviewers never got tired.
1
22
Let them tire and the lever drops from +1.46 to +0.93, turning negative past 80% sustained utilisation. Scaling staff with the escalations scored +1.15. Fixed headcount scored -0.59.
1
11
Meta's numbers from that period: major incidents up 40%, firefighting up 70%. Headcount plans need one more line: hours of human review per unit of agent output. linkedin.com/posts/tinholt_a…
5
Ran my 3D Chicago walkthrough test on Fable 5.2. One sentence in, it rebuilt downtown on the city's open data: 2,850 buildings on their true lots, the river bending where it bends. Full test here: linkedin.com/posts/tinholt_f…
22
I rebuilt the game that got me into computers, with a model under my desk and a day of agents. A small 3-bit open-weights model rebuilt a 1988 engine from a spec: 503 tests, 78 hours, 26 kWh.
1
2
44
Then a blind gauntlet against a commercial bar built Mercy County in a day. Spec and tests first, cheap local build second. A ratio that applies far beyond games.
1
18
A fine-tuned encoder first reached its workflow ceiling at 1,000 labelled cases: 0.825 vs 0.822 on challenge cases. The from-scratch classifier never got there, even at 3,000. And the shipped eight-vote mode bought nothing. Claim withdrawn. medium.com/@tinholt/how-many…
2
62
At $11.65 in video-generation charges, a creative idea becomes something you can afford to explore. Chicago in Five Breaths: 51 seconds of watercolor Chicago, Belmont Harbor to Navy Pier after dark. dinand.com/side-projects/chi…
1
52
An architecture diagram starts a debate about the architecture. My second Maison Agent experiment presents the AI control plane like a fragrance ad: one gold ring gathering black ribbons, one sentence beneath it.
1
1
36
"One place to direct AI agents, set their boundaries, and see what they do." Direct. Govern. Observe. The only promise on the page: autonomy, with you in control. dinand.com/publications/powe…
1
24