AI agent hardening service for existing Kubernetes platforms

A consulting/service offering that adds layered defenses around AI agents already running in a company's cluster: Kubernetes network policy (L4/L7), Kyverno admission rules restricting image sources and deployment requirements, agent identity via Spiffe/Spire, runtime security, and an LLM Guard proxy in front of the agent providing input and output sanitization plus MCP/tool checking. The pitch: excessive agency is an infrastructure and process problem, not an AI problem — don't let agents have direct access, stick to known flows, and extend the CI/CD and SDLC controls you already have.

online B2B Deep Tech / Infrastructure

From AI Engineer — Build a Platform and Watch It Burn — Michael Forrester, Accenture & Whitney Lee, Datadog at 13:28

Problem: Teams give agents oversized scopes without knowing elevated credentials sit in the environment; relying on the model to refuse is unreliable since refusals are probabilistic and attackers can often bypass them within 20–30 prompts.

For: Enterprises running or about to run AI agents inside Kubernetes — the three use cases named: AI-assisted software development, AI added to an existing application, and AI-managed systems (the riskiest).

Products from this video

Amazon Elastic Kubernetes Service (Amazon EKS) AWS Bedrock Backstage BurritoBot Datadog Falco Falco Talon Grafana Jaeger kagent KubeArmor Kyverno LLM Guard OpenTelemetry SPIFFE/SPIRE Tetragon Watch It Burn - Claim Your Cluster Zipkin

Examples

🔒 Full analysis locked

Unlock more videos and the full analysis

A credit unlocks one video's full analysis for good — the build steps, the tools and how each was used, the methods behind every use case. Pro opens the whole library instead, and raises how many videos you can analyse a day.

Unlock full analysis — free

Other takes on AI security infrastructure

All AI security infrastructure ideas →