tutorial

11 articles

Step-by-step guides for implementing AI personalization, self-models, and evaluation systems. Practical, code-first walkthroughs you can follow in your own codebase.

Essential reading

Guide api quickstart

Self-Model API: From Zero to Personalized in 30 Minutes

A practical developer guide to integrating the Clarity Self-Model API. Create a user model, observe interactions, and personalize responses in under an hour.

Robert Ta's Self-Model

Dec 1 · 12 min read

Guide evaluation ai-products

Minimum Viable Evals: Start Here

You do not need MLflow or LangSmith on day one. You need a spreadsheet and 50 test cases. How to build your first AI evaluation system in a single afternoon using Hamel Husain's Level 1 approach.

Robert Ta's Self-Model

Dec 30 · 12 min read

All articles

Guide evaluation ai-products

The AI Product Debug Loop

Hamel Husain's insight that eval infrastructure IS debug infrastructure. How to build a system that catches AI product problems before users do, using the same feedback loop that makes software debugging work.

Robert Ta's Self-Model

Mar 12 · 12 min read

Guide evaluation LLM

LLM-as-Judge: Using AI to Grade AI

Hamel Husain's critique shadowing approach shows how to build an LLM judge that agrees with your domain expert 90%+ of the time. Here is the practical guide for AI product teams.

Robert Ta's Self-Model

Mar 5 · 11 min read

Guide ai-maturity evaluation

The AI Product Maturity Assessment

Most AI products are stuck at Level 1, capable but generic. Here is a 5-level maturity model that maps the journey from basic AI capability to true user alignment, with concrete criteria for each level.

Robert Ta's Self-Model

Mar 1 · 12 min read

Guide ai-products evaluation

The AI Product Health Check

Most AI products do not know whether they are healthy. Here is a 15-minute diagnostic that tells you whether your AI product is improving, plateauing, or silently degrading, before your users tell you.

Robert Ta's Self-Model

Feb 9 · 12 min read

Guide alignment metrics

Alignment Scoring for Non-Engineers

Alignment scores are the most useful metric in AI products. But most people outside engineering have never heard of them. This is the plain-language guide to understanding, using, and arguing about alignment scores.

Robert Ta's Self-Model

Feb 5 · 12 min read

Guide self-models product-design

The Product Manager Guide to Self-Models

Self-models are the next primitive for product personalization. This is the no-jargon guide for PMs who want to understand what they are, why they matter, and how to spec them into your product.

Robert Ta's Self-Model

Feb 2 · 9 min read

Guide ai-products architecture

Your First AI Product: What to Build and What to Skip

Building your first AI product is overwhelming. Most teams build too much infrastructure and too little understanding. Here is the minimum viable AI stack and the features you should skip entirely.

Robert Ta's Self-Model

Jan 29 · 12 min read

Guide evaluation metrics

AI Evals Explained: A Product Manager Guide

AI evals are not as complicated as engineers make them sound. If you can understand restaurant health inspections, driving tests, and essay rubrics, you can understand AI evals.

Robert Ta's Self-Model

Jan 23 · 13 min read

Guide architecture personalization

Three Layers of AI Personalization Architecture

AI personalization requires three layers: data collection, user modeling, and adaptive delivery. Most products only have the first. Self-models complete the stack.

Robert Ta's Self-Model

Nov 27 · 14 min read

Stay sharp on AI personalization

Daily insights and research on AI personalization and context management at scale. Read by hundreds of AI builders.

Daily articles on AI-native products. Unsubscribe anytime.

Building AI that needs to understand its users?

Book a Strategy Call