Talk tech with tips and tutorials from builders at Kong and the Kong Community.
When an application calls a model provider directly, the service needs the provider's API key, and any control over that traffic has to be built into the service itself. For one service calling one model, that is the right amount of machinery. It holds up less well as the application grows. Every…
Let’s say someone logs in with a real account and a valid token, and your system treats them like any other customer. Then they start changing the invoice number in their requests and reading invoices that belong to other people. That’s a classic case of security breach, but nothing in that story…
KSAI stands for Kong Skills for Agentic Intelligence. It brings AI-assisted code review and implementation into GitHub, where our engineering work is actually done. The AI agents run in CI, so closing a laptop doesn't stop the work. By leveraging KSAI, we establish agentic engineering best…
Kong and Straiker are partnering to help enterprises secure AI agents across the traffic, tools, and systems they already manage through Kong AI Gateway . The integration brings Straiker into the Kong ecosystem, giving customers a way to add deeper security visibility, testing, LLM runtime…
You've mapped the architecture. Your agents retrieve context from external tools, coordinate with other agents, and propagate mutations through your systems. The model logic is solid. An agent gateway is the control layer for traffic between agents, models, tools, APIs, and data sources. It applies…
Most teams building multi-agent systems hit the same wall at roughly the same point. The prototype works. Agents chain together, tasks complete, the demo impresses the room. Then someone asks: "What happens when this runs a thousand times a day? What happens when an agent calls an external API…
Every team running production LLMs has had the same idea: not every request needs the frontier model. Intelligent model routing (or LLM routing)— choosing a model per request on criteria such as task complexity, cost, latency, or quality — enables more efficient model usage. The idea is easy.…
You would never expose a REST API without an API gateway in front of it. Authentication, rate limiting, observability, access control — these aren't optional extras. They're mandatory, and we've spent the last decade building the API gateway pattern to solve exactly this problem. So here's the…
The new Konnect Dev Portal Toolkit extension for Visual Studio Code gives you a live, portal-accurate preview of your content right beside the file you are editing. You watch a page take shape exactly as it will appear to your developers, as you type, without ever leaving your local editor. Konnect…
As APIs grow across teams, keeping them consistent becomes difficult. Some APIs follow naming conventions and include clear descriptions, while others don’t. Over time, these differences make APIs harder to understand, review, and maintain. That is where API linting helps. Kong Insomnia has already…
Running Apache Kafka on Amazon Managed Streaming for Apache Kafka (MSK) gives you a managed broker with no ZooKeeper to operate, automated patching, and multi-AZ replication handled by the service. What it doesn't give you is a safe, governed way to expose Kafka access beyond your VPC boundary.…
Our launch announcement made the business case for prepaid credits: collect fiat-specific payment before consumption, protect your margins from token-cost spikes and collections risk, and give customers a flexible wallet with different overage options. This post is the technical follow-up, written…
Enterprise AI adoption is accelerating. In PwC's April 2025 survey of 308 US business executives, 88% said they plan to increase AI-related budgets in the next 12 months [1]. But scaling AI from pilot to production exposes a structural problem most teams discover too late: direct LLM API…
This is the second post in a series. For the first part, see Why We Need to Stop Prompt Hacking . Generative AI systems do not fail because models are weak. They fail because architectures are incomplete. Once organizations accept that prompts cannot guarantee reliability, a new challenge emerges:…
Generative AI has completely changed the landscape of enterprise automation, knowledge work and operational efficiency. In 2026, the question is no longer whether these models can perform complex tasks, but whether they can do so reliably enough for mission-critical systems. Despite the…
As API ecosystems grow, developers and platform teams often work in separate environments. Platform teams manage APIs, gateways, and governance centrally, while developers recreate those configurations locally for testing and debugging. Over time, this can lead to configuration drift, inconsistent…