The Secure AI Starter Kit: Download the Code and Field Guide
Part 17 and the finale of the KIS AI Security Series: download a runnable offline security lab, the setup and operations guide, and a one-page map of all 17 parts.
Monitoring AI Applications: Traces, Alerts and Troubleshooting
Part 16 of the KIS AI Security Series: trace retrieval, model and tool outcomes while keeping sensitive prompts out of routine logs.
Building AI Agents with Safe Tool Permissions
Part 15 of the KIS AI Security Series: build a deterministic tool gateway with scoped permissions, validated actions and one-time human approval.
Evaluating RAG Answers: Evidence, Citations and Abstention
Part 14 of the KIS AI Security Series: evaluate RAG evidence, citation support and abstention with a tested Python example and a clear release gate.
Build a Secure RAG Pipeline: Tenant Isolation, Citations and Retrieval Tests
Build a secure RAG pipeline with permission-aware retrieval, tenant isolation, citation validation and practical Python tests for the evidence boundary.
How LLMs Process Text: Tokens, Embeddings, Attention and Context Windows
Part 12 of the KIS AI Security Series: understand how tokens, embeddings, attention and context windows shape model behaviour and what security teams should test.
Build an LLM Application from First Principles
AI SECURITY · BLOG 16 A technical walkthrough of a small AI service that accepts a support ticket, calls a language model, validates the result and records evidence without turning the model into an uncontrolled decision-maker. AI Security Series · Part 1112 min readFor developers, security engineers & architects REFERENCE REQUEST PATHInput → inference → […]
The AI Security Operating Model: A 90-Day Roadmap
AI SECURITY · BLOG 15 The AI Security Operating Model: A 90-Day Roadmap The capstone of the KIS AI Security Series: how to turn principles, controls and testing into an operating model that improves every quarter. AI Security Series · Part 109 min readFor executives, risk owners & security teams AI SECURITY OPERATING MODELGovern it. […]
Testing AI Security: From Prompt Injection to Evidence
AI SECURITY · BLOG 14 Testing AI Security: From Prompt Injection to Evidence A practical testing programme for finding prompt injection, unsafe tool behaviour and weak controls before they become incidents. AI Security Series · Part 98 min readFor risk, product & security leaders AI SECURITY TESTING LOOPAttack the path. Capture the evidence. 01ModelMap assets, […]
Securing AI Agents: Permission-Aware Tools and Safe Actions
AI SECURITY · BLOG 13 Securing AI Agents: Permission-Aware Tools and Safe Actions A practical guide to giving AI agents useful tools without giving them unlimited authority over data, systems or business decisions. AI Security Series · Part 88 min readFor product, security & engineering teams AGENT SECURITY STARTERBound the action. Prove the result. 01IdentifyList […]