Building reliable systems

Most agent failures I see in production are not bad prompts. They are missing boundaries, missing observability, and a planning loop nobody can inspect.

Field notes from the 2025 Privacy, Security and Trust Industry Summit: AI as a threat amplifier, cyber attribution, and agentic-AI risk frameworks from TD Bank, Mastercard, and the CIC.

A walkthrough for enforcing role-based page access in a multi-role Next.js App Router app: JWT decoding in middleware, whitelists per role, and redirect logic with the full code.

Building a content-based recommendation API with Django, Django REST Framework, TF-IDF vectorization, and cosine similarity, with the trained model cached via pickle on app startup.