What we learn operating AI

Every post draws on a system we engineered and still answer for in production, written by the engineers and leaders accountable for it, so each lesson has already been tested against real users and real auditors.

Define an Outcome

Agentic AI27 July 2026

Human-in-the-Loop Data Capture

Most capture pipelines put the reviewer at the end of the line, where a finished extraction looks settled and gets waved through. Oversight earns its keep at the point the agent is unsure, which makes this a placement decision before it is a staffing one.

Shardul SinghCTORead the blog

Tell us the number you need to move

Define an Outcome

What we learn operating AI

Human-in-the-Loop Data Capture

Agreeing the Number Before You Start

Credit Model Monitoring Through the Cycle

Small Language Models in Agentic Systems

AI Voice Agents in Healthcare Call Centres

Terminal and Async Coding Agents Compared

Choosing Models for Clinical Assistants

Structured Outputs in Production

LLMs for Earnings Calls and Filings

The CFO Test for Enterprise AI

AI in Surgical Planning and Intraoperative Support

AI Act Obligations in Practice

AI in the Tools You Already Use

Tell us the number you need to move