AI Models

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

AI Models

Human-in-the-Loop Data Capture

Claude Opus 4.5 and the Price Cut

Gemini 3 Pro for Multimodal and Agentic Workloads

Adaptive Reasoning Arrives

Selecting a Model for Enterprise RAG

Claude Haiku 4.5 and Small-Model Economics

Choosing Models for Clinical Assistants

Claude Sonnet 4.5 and Long-Horizon Agents

The Best Models for AI Agents

Claude Opus 4.1 for Enterprise Coding

Are Frontier Models Becoming Commodities?

GPT-5 in Production

Function Calling and Tool Use, Compared

Tell us the number you need to move