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

AI Governance in Healthcare

LLM Tool Calling in Production

Perplexity as an Enterprise Answer Engine

AI Governance in Financial Services

Llama 3.1 405B and Open Weights

Agent Orchestration Patterns

Consultant, Integrator, or Operator

AI in Medical Imaging

AI Chatbots in Banking

Why AI Agents Fail in Production

Gamma for Deck Generation at Scale

GPT-4o in Production

Tell us the number you need to move