AI Security
RAG Pipeline Security Controls in 2026
Retrieval-augmented generation pipelines have become a primary breach vector for LLM products. The controls that contain the risk without breaking the use case.
Feb 26, 20266 min read
Resources
Supply Chain Security, in plain English.
Deep dives, practical guides, and incident analyses from engineers who build Safeguard. No fluff, no vendor FUD — just what you need to ship secure software.
Filter
Articles
RSS feedAI Security
Griffin AI vs Claude Batch API for Scanning
Claude's Batch API gives you 50% off for async workloads. Griffin AI uses it internally. The question is whether your team should use the Batch API directly or consume it through Griffin.
Feb 26, 20262 min read
AI Security
LLM-As-Judge Pitfalls In Security Evals
Using an LLM to score another LLM's output is expedient and dangerous. The judge has its own biases — ones that affect security evaluations specifically.
Feb 26, 20262 min read
AI Security
Windsurf vs Sourcegraph Cody: Security Comparison
A side-by-side security comparison of Windsurf and Sourcegraph Cody: data handling, agent scope, deployment models, and enterprise controls.
Feb 25, 20265 min read
AI Security
Task-Routed LLM Architectures For Security
One model for every task wastes budget on trivial work. Task-routed architectures match model capability to task requirements — the right lever for security at scale.
Feb 25, 20262 min read
AI Security
Why Engine-Plus-LLM Beats Pure-LLM: Griffin vs Mythos
The structural case for engine-plus-LLM security reasoning — and why pure-LLM products in the Mythos class hit a ceiling that no parameter count can raise.
Feb 25, 20266 min read
AI Security
Griffin AI vs GPT-5: Enterprise Controls
Frontier models offer impressive enterprise features. Security programs need deeper controls than chat can provide—controls that live in the engine around the model.
Feb 25, 20267 min read
AI Security
AI-Managed Security Services: What You're Actually Buying
AI managed security is sold as autonomous defense, but the honest version of the pitch is faster triage and drafted fixes with a human still signing off — worth knowing before you buy the marketing version.
Feb 25, 20266 min read
AI Security
MCP Definition: What the Model Context Protocol Actually Is
The MCP definition in one line: an open standard that lets AI assistants connect to your tools and data through a single, consistent interface instead of a tangle of one-off integrations.
Feb 24, 20266 min read
Stay informed
Weekly insights on software supply chain security, delivered to your inbox.
Self-healing security runs on Safeguard.
Your first fix PR is minutes away.
No sales call required, even your agent can complete the purchase over MCP.