Blog

AI agents, RAG, and integrations — notes from production.

Build vs Buy for AI: A Framework That Works Across Fraud, Search, and Support

Build vs buy for AI is three options: buy a product, build from scratch, or a custom build on managed components. The signals that move you between them.

How Much Does a Custom AI Feature Cost to Run Per Month?

AI feature run cost has three parts in every domain: model inference at your volume, supporting infrastructure, and the human review that never goes to zero.

How to Run an AI Pilot That Produces a Real Go/No-Go Number

How to run an AI pilot: one narrow slice, a go/no-go metric and threshold set before you start, a control to measure against, and the run cost too.

Picking a Confidence Threshold: When Should AI Escalate to a Human?

An AI confidence threshold decides when the system acts alone and when it hands off: two cutoffs not one, calibrate the score first, and start conservative.

Shadow Mode: Testing an AI Component Against Production Without Touching Decisions

Shadow mode runs a new AI component on live traffic with its outputs changing nothing - logged beside the real decision so you learn if it agrees with reality.

How to Write an Evaluation Set for an AI Feature Before You Build It

An AI evaluation set is your definition of "working": real inputs from your own data, expected outputs, and the hard cases. Write it before the build.

Store Photos and Privacy: Handling Staff and Customers in Shelf Images

Retail computer vision privacy: shelf photos catch people incidentally. Process on-device, keep only the result, retain no images, add no face recognition.

What Does It Cost to Deploy Shelf-Monitoring Computer Vision Per Store?

Computer vision cost per store: a one-time build, a per-store rollout for hardware and install, and ongoing retraining, fleet management, and review staffing.

How to Measure ROI on Computer Vision for Shelf Availability

Computer vision retail ROI: recovered sales from faster gap closure, audit hours saved, and a store holdout to measure it net of substitution.

Common Mistakes When Rolling Out Store Computer Vision Across a Chain

Retail computer vision rollout mistakes: designing for connectivity stores lack, a single confidence threshold, stale training data, and a flagship-only pilot.