LLM Application Guardrails
Donato Capitalla
Develop robust multi-layered security: Treat AI outputs as potential threats and implement comprehensive system protections
Jan 23, 2026 · 13m 14s BACK TO HOME
TESTING
Explore testing strategies, quality assurance, and validation methods for better products.
Browser-Based Agentic Attack
Donato Capitalla
Adopt robust security guardrails for AI-tools to combat cybersecurity threats in software development workflows
Jan 23, 2026 · 10m 5sThe Non-Deterministic Mindset Shift: From 30 Lines of Code to Orchestrated Natural Language
James LePage
How to operate in a non‑deterministic world: move from unit-level certainty to system-level observability, evals, and human-in-the-loop checks when orchestrating natural‑language driven components.
Sep 29, 2025 · 0m 22sThe Fourth Dimensional Tool Problem
Oji Udezu
Design for non‑determinism: add guardrails, fallbacks, and manual overrides where probabilistic AI cannot be fully trusted.
Sep 29, 2025 · 0m 15sNew KPIs for AI Product Success
Oji Udezu
Measure what matters for AI: track time‑to‑value, output volume, and ‘tweak time’ to ensure automation actually saves effort.
Sep 29, 2025 · 0m 30sThe Breaking Point Architecture: Managing AI's Attention Limits
Chris Rickard
Architect for AI attention limits: know when to switch tools as complexity grows, and add evals plus regression checks to catch breakage.
Sep 29, 2025 · 6m 1sProduction AI Requires Traditional Software Guardrails
Alan Buxton
Harden AI for production: detect out‑of‑distribution inputs, add human‑in‑the‑loop, and monitor outcomes continuously.
Sep 29, 2025 · 0m 26sLanguage Models Are Terrible at Math - And That's Fine
Alan Buxton
Choose the right tool: don’t force LLMs on math; use simpler analytic methods where numbers beat language models.
Sep 29, 2025 · 0m 25s