Notes from building trustworthy AI.

Free to read. No signup.

The archive

Everything we've published.

Showing all 16 blogs

Nov 13, 2026 · 4 min read

AI Governance Tools: A Buyer’s Guide for Teams With Agents

AI governance tools fall into five groups. See what each one covers, where agents slip through, and the eight questions to ask a vendor before you buy.

Human Oversight

Nov 13, 2026 · 4 min read

Human in the Loop: What It Means for AI Agents

Human in the loop means a person reviews or approves an AI decision. Learn the three oversight models and how to pick the right one for each agent action.

Nov 13, 2026 · 4 min read

AI Audit Trail: What It Is and What Auditors Ask For

An AI audit trail records what an AI system decided, why, and under which rules. See the six parts of a record that holds up with an auditor.

Guardrails

Nov 13, 2026 · 5 min read

6 Examples of AI Hallucination and How to Prevent Them

Six real examples of AI hallucination, from Air Canada to a federal court, with what happened and the controls that stop it in customer-facing agents.

Nov 13, 2026 · 4 min read

What Is an AI BOM? The AI Bill of Materials Explained

An AI BOM lists every model, dataset, prompt, tool and policy behind an AI system. Learn what goes in one, who asks for it, and how to produce it.

Human Oversight

Oct 26, 2026 · 3 min read

Human-in-the-Loop AI Agents: Why Approval Isn’t Oversight

Human-in-the-loop AI often means a person approving outputs all day. That erodes judgment. Here’s how to design oversight that makes agents and people better.

Oct 26, 2026 · 3 min read

Agentic Governance Glossary: 16 Terms Every Team Should Know

Plain-English definitions of 16 agentic governance terms, from RML and AIBOM to earned autonomy and cognitive surrender, with links to go deeper.

Oct 15, 2026 · 3 min read

Agentic Governance Platform: How to Choose One for AI Agents

Choosing an agentic governance platform? Compare the three types of tools, the eight capabilities that matter, and the questions to ask vendors.

Oct 15, 2026 · 4 min read

Agentic Governance Framework: A Practical Template

A practical agentic governance framework for AI agents: owners, autonomy levels, controls and evidence, mapped to the EU AI Act, NIST AI RMF and ISO 42001.

Explainability

Oct 15, 2026 · 3 min read

Explainable AI Agents: Explaining Decisions, Not Just Models

Classic explainable AI explains model features. AI agents need more: what they claimed, what evidence backed it, and which rules they were checked on.

Oct 9, 2026 · 4 min read

Agentic Governance: How to Get Agents Into Production

Agentic governance is what gets agents past risk and compliance. Learn the five controls risk teams ask for, and how to prove agents belong in production.

Guardrails

Oct 9, 2026 · 3 min read

AI Agent Guardrails: What They Catch and What They Miss

AI agent guardrails block bad inputs and outputs, but miss unbacked claims and broken business rules. Here’s what a complete guardrail stack needs.

Observability

Oct 9, 2026 · 3 min read

Agent Observability: Why Traces Are Not Enough

Agent observability shows what your AI agent did. It can’t show what the agent believed or whether your data backed it. Here’s how to close that gap.

Engineering

Mar 4, 2026 · 3 min read

Creating an AI knowledge layer on top of your project repository

What if your codebase could explain itself? Here's how to build an AI-powered knowledge layer that turns your repository into a living, queryable resource for your entire team.

Zahwah Jameel

Developer Experience

Feb 18, 2026 · 3 min read

Learn new developer tools faster by turning official docs into an AI mentor

Official documentation is comprehensive but overwhelming. Here's how to transform any tool's docs into a personalized AI mentor that teaches you at your own pace.

Zahwah Jameel

Research

Feb 3, 2026 · 4 min read

How explainable AI reduces hallucinations in domain-specific systems

Hallucinations aren't just a model problem — they're a transparency problem. Here's how explainability techniques can dramatically reduce false outputs in specialized AI systems.

Zahwah Jameel