Resources
Content & Tutorials
Tutorials, market analysis, conference talks, and video content published regularly under the brand The Gateway Guy.
Featured Video
YouTube — The Gateway Guy
Latest Videos

Konnect Tutorial: Deploying a self hosted Konnect Kong Gateway Manually

Create, Explore, Manage: Improving Developer Experience with Konnect Developer Portal

Kong Hackathon 2025 Winner - Kong Auto Rollback AI Agent

How do you protect your upstream services while limiting your consumers?

Building Effective API Strategies for Engineers and Architects
Speaking
Watch Andrew's conference talks →
Step-by-step guides
Hashnode Tutorials

Kong AI Gateway on Kubernetes: Apply Compliance and Safety Policies with AWS Guardrails
Add AWS Bedrock Guardrails to your Kong AI Gateway — block harmful content, prompt injection attacks, PII leakage, and off-limits topics at the gateway…

Kong AI Gateway on Kubernetes: Proxy OpenAI via Konnect
Deploy Kong Gateway 3.14 as a Konnect-connected data plane on kind, configure the AI Proxy plugin with decK, and proxy OpenAI in under 30 minutes.
Market awareness & analysis
dev.to Articles

Protect Your Users: PII Redaction in AI Requests with Kong AI Gateway 2.0
One-line summary: By the end of this tutorial, you'll have Kong AI Gateway 2.0 automatically...

OpenAI's first custom chip just benchmarked past NVIDIA. Jalapeño changes the inference equation.
OpenAI just published benchmark results for Jalapeño — its first custom AI inference chip — and the...

MCP just went stateless. Here's what the new roadmap builds next.
The Model Context Protocol team published an updated roadmap this week, and it's worth reading beyond...

Small Models Are Coming for the Cloud — And the Data Is Damning
A Stanford research team just published a paper that should make every hyperscaler investor...

The Local LLM Stack in 2026: What Actually Works
Running a language model locally used to be a hobbyist experiment. In 2026, it's a viable engineering...

Who's really winning open models in 2026? It's not who you think
HuggingFace just published their biannual State of Open Models report covering January to August...

The real LLMOps risk isn't the model. It's shadow AI.
Large language models broke the clean "train it, test it, ship it" model of production ML. The thing...

DeepSeek's Flash outpaced its own flagship. The upgrade was post-training, not parameters.
DeepSeek shipped V4-Flash-0731 last week — same 284B parameter architecture as the preview, same 13B...

Cedar could stop one bad tool call. Dogwood stops bad sequences.
AWS launched Dogwood this week — an open-source policy language (Apache 2.0) for AI agent runtime...