AI Infrastructure, Built to Last
We help engineering teams deploy AI safely and at scale — specialising in Kong AI Gateway, LLM infrastructure, agent platforms, and the cloud-native foundations they run on.
Services
What We Do
Specialist consulting with real production experience — not slides.
Kong AI Gateway
The infrastructure layer your AI needs. We design, deploy, and operate Kong AI Gateway — routing LLM traffic safely across providers with rate limiting, cost controls, compliance, and full observability.
- →LLM proxying (OpenAI, Anthropic, Bedrock, Azure)
- →AI safety: guardrails, PII filtering, content controls
- →MCP server proxying & monetisation
- →Per-consumer rate limiting & usage metering
AI Platform Strategy
We help teams move AI from prototype to production — governed, observable, and built to scale. Real production experience, not slides.
- →AI readiness & architecture assessment
- →Agent platform design (MCP, A2A, tool use)
- →AI governance & compliance frameworks
- →Model selection, cost management & vendor strategy
Platform & Cloud Engineering
Cloud-native foundations on AWS and Kubernetes that support your AI workloads — reliable, observable, and built for the teams that run them.
- →AWS architecture & implementation
- →Kubernetes for AI workloads
- →API management & Kong Gateway (non-AI)
- →Infrastructure as Code (Terraform, Helm)
Latest Tutorials
From Hashnode
Kong AI Gateway on Kubernetes: Apply Compliance and Safety Policies with AWS Guardrails
One-line summary By the end of this tutorial, you'll have AWS Bedrock Guardrails wired into your Kong AI Gateway — blocking harmful content, prompt injection attacks, PII leakage, and off-limits topi
Kong AI Gateway on Kubernetes: Proxy OpenAI via Konnect
One-line summary By the end of this tutorial, you'll have Kong Gateway 3.14 running as a data plane on a local Kubernetes cluster, connected to a Konnect control plane, with the AI Proxy plugin routi
Latest Articles
From dev.to
Nvidia wants enterprises to run agents safely. NemoClaw is how.
Getting enterprises to adopt autonomous agents isn't a model problem — it's a governance problem....
'"An LLM and a harness": Nvidia''s simple thesis on what agents actually are'
Nvidia's Nader Khalil — Director of Developer Technologies and co-founder of Brev.dev, acquired by...
Fable disappeared overnight. That's the best ad for open-weight AI anyone could have run.
Fable 5 launched. Developers loved it. Three days later, a US government export-control directive...
Video
Latest from YouTube
Konnect Tutorial: Deploying a self hosted Konnect Kong Gateway using IaC
Konnect Tutorial: Deploying a self hosted Konnect Kong Gateway Manually
Create, Explore, Manage: Improving Developer Experience with Konnect Developer Portal
Recognition
Recognised in the Industry
API Summit AI Hackathon
2023 Winner · 2024 Winner · 2025 3rd Place
Three years competing and placing at Kong's API Summit AI Hackathon — from building AI-powered API tooling to the Kong Auto Rollback AI Agent in 2025.
🎤Kong Champion & Conference Speaker
Community Expert · Platform Engineering & AI
Recognised by Kong as a community Champion, and a regular speaker at conferences and meetups on AI infrastructure, Kong AI Gateway, and platform engineering.
Andrew Kew
Founder, Keogh Innovation
About
Built on Real Experience
Keogh Innovation was founded by Andrew Kew — an AI platform engineer helping teams deploy LLMs safely, govern agents at scale, and build the infrastructure that makes it all work in production.
A two-time AI Hackathon winner at API Summit and deep expert in Kong AI Gateway. Under the brand The Gateway Guy, Andrew publishes hands-on AI infrastructure tutorials and analysis followed by engineers worldwide.
Ready to modernise your platform?
Most engagements start with a conversation. Tell us what you're building.
Get in Touch