Adding capabilities to an AI agent during a conversation requires code to manage which tools are available. Fred Schott’s answer borrows directly from how React solved a similar problem for web interfaces years ago.

Schott, the creator of the Astro web framework, launched version 2 of his AI agent framework Flue on July 31, 2026. In the launch post, he explains why the earlier, simpler design stopped working:

“The static agent approach worked well for simple use-cases, but started to break down for more complex, non-trivial agents and multi-step workflows.”

His fix reaches for a comparison from web development:

“The same problem that React Hooks was invented to solve applies to agents as well: How do you compose functionality at the lowest, most fundamental level?”

Who he is

Schott created Astro, a JavaScript web framework used by companies including Unilever, Visa, and NBC News. Cloudflare acquired Astro’s parent company in January 2026, and Schott has continued building in that space, most recently with Flue, a TypeScript framework for building AI agents.

What he gets right, and where it’s incomplete

An AI agent can call tools, remember task state, and choose its next step. Flue’s earlier design set a prompt and tool list upfront. A support bot might need account-change tools only after verifying a customer’s identity. Managing every step separately can make that workflow difficult to maintain. Flue’s hooks, such as useSkill() and useTool(), let a developer attach or drop a capability at the exact moment it becomes relevant, instead of loading everything up front.

The React comparison is useful but not exact. React Hooks let developers combine reusable behavior in interface components. Agent hooks apply a similar pattern to tools and task state. An agent hook can attach a tool that takes real-world action, like sending a payment or deleting a record. Check which tools the agent can call at each step, and enforce permission checks inside tools that change data.

Why it’s notable

Agent framework design is still unsettled. Vercel’s eve and Schott’s Flue both launched this year as competing templates for how to structure agent code, and Bret Taylor, the chairman of OpenAI and CEO of Sierra, has separately compared the current state of agent tooling to the early, less structured “jQuery era” of web development, before frameworks like React standardized how developers built interfaces. Schott is applying the hooks pattern to agents. Whether it becomes a common framework pattern remains open.

What it means for builders

For a multi-step agent, ask how it gains or loses capabilities without rewriting the whole workflow. In your current setup, does adding a tool change one reusable component or require rewriting the prompt and task logic?

End of article