25

Skyfire partners with F5 to bring verified AI agent identity inside the world’s largest bot defense platform

Agentic commerce has a trust problem, and it’s not the one most people expect. The challenge isn’t that merchants don’t want to transact with AI agents. It’s that the infrastructure they’ve spent decades building to protect their platforms was specifically designed to stop automated traffic. Bot defense systems, web application firewalls, and fraud detection layers […]
Read more
Engineering Blog

From Discovery to Execution: How AI Agents Can Dynamically Install Tools

General-purpose agents often rely on tools served by Model Context Protocol (MCP) servers to accomplish things for humans. MCP has quickly become the go-to protocol for enabling AI agents to access a wide range of tools. At a high level, a large language model (LLM) acts as the agent’s “brain,” while tools give it the […]
Read more
Engineering Blog

Converting OpenAPI Specs to Agent Tools

Before we dive in, let’s clarify what we mean by “agent tools”. Agent tools are local functions whose descriptions and parameters are exposed to an agent. The agent can then supply all the parameters to perform a “tool call”. Then, the agent framework (CrewAI, AWS Strands, Langchain, etc.) orchestrates running the tool function with those […]
Read more
Engineering Blog

The Importance of Context Placement in AI Agents

When building AI agents, it’s tempting to feed the model every bit of context you have – all the tools, all the data, all the instructions – in hopes that “more context == better results.” In theory, a larger context window and more tools should make an agent more capable. In practice, we’ve learned the […]
Read more
Engineering Blog

Your Agent Has Amnesia: Why Short-Term Memory Matters More Than You Think

How agent frameworks like Vercel AI and Autogen approach memory and why forgetting can break reasoning. This isn’t about vector databases — it’s about the kind of memory agents need to think between runs. Short-Term Memory Keeps LLMs Thinking Straight Try solving a problem without being able to remember the last step you took. You’d […]
Read more

Fireside Chat: Mr. 403 Meets the Agent Economy

Fireside Chat: Mr. 403 Meets the Agent Economy   If you’ve ever tried to run an AI agent at scale across the open web, you’ve likely hit a wall of “403 Forbidden.” Behind many of those blocks is Akamai, the world’s largest edge security and bot management platform. At the Agentic Commerce event, Skyfire sat […]
Read more

Auth0 x Skyfire: Agentic Commerce

Inside the Auth0 + Skyfire Demo: How Agents Can Act on Your Behalf Without Exposing Identity or Payment Credentials For years, Auth0 has been at the forefront of identity and access management, powering login, authentication, and API protection for thousands of applications and platforms. But at the Skyfire Agentic Commerce event, they showed something different: […]
Read more
AI merchant service

Agent Tool Calling Chaos when MCP Server Tools have Optional or Nullable Parameters

When building MCP servers, you quickly realize something: the devil really is in the details. One issue we’ve encountered is how differently LLMs and agent frameworks handle optional and nullable parameters in MCP server tools. At first glance, this might sound like a subtle implementation detail. But as we learned—through multiple iterations across OpenAI, Anthropic, […]
Read more

Agentic Commerce: The Rise of Tokenized Payments and Identity

The internet is changing again. After evolving from static web pages to dynamic applications and APIs, a new shift is underway. This time, it’s not just about users. It’s about agents. Software agents—powered by large language models, task automation frameworks, and decision engines—are beginning to act on behalf of people and organizations. They book meetings, […]
Read more
1 3