Posts tagged "AI"

Your agent can now tell us when something gets in its way.

All you need is to have the Netlify MCP Server installed or set up. If you’re using a Netlify Connector or plugin with your agent, you don’t need extra setup here.

Starting today, the Netlify MCP includes a new feedback tool that lets agents submit feedback or report issues to Netlify on their own when they run into a problem they can’t resolve.

The tool works wherever you use Netlify MCP, including our connectors and plugins. When your agent gets stuck, for example on an unclear error or a missing capability, it can report what happened instead of leaving it as a dead end in the conversation.

We combine this feedback to find where agents struggle on Netlify, then use it to improve the Agent Experience (AX). That means the problems your agent hits today are less likely to slow it down next time.

If your agent is already connected to Netlify MCP, it can use the feedback tool now. To get started, connect to the Netlify MCP server.

You can now check on your deploys right where you’re working. Netlify MCP gives you a visual overview of your project’s deploys in ChatGPT and other clients that support MCP Apps, so you don’t need to switch to the Netlify dashboard to see whether your latest deploy went live or why it failed.

Ask “Show recent deploys for my project” to open a card with up to five recent deploys, or ask about a specific deploy. Each deploy shows its status, branch, creation time, and any error message, with links to visit the deployed site or inspect the deploy in Netlify. Status filters help you find successful, unsuccessful, or queued deploys, and team details give you context for the project.

While any of the deploys on the card are still in progress, the card refreshes automatically, so you can watch a deploy finish without asking again. Automatic refresh stops when they finish or after 15 minutes; select Refresh to check again.

Clients without MCP Apps support receive a text summary instead.

To get started, connect to the Netlify MCP server.

You can now connect Netlify to Grok with the Netlify connector, so your Grok agent can answer questions about your projects, update supported project settings, and deploy to Netlify through conversation.

The connector gives Grok up-to-date context for building and deploying to Netlify, and it works across Grok Bot, Grok CLI, and grok.com.

You don’t need to call the connector by name. Describe what you want, and when the task needs Netlify access, Grok uses the connector for you. For example, you can ask Grok to:

• “Deploy this project to Netlify.”
• “What’s the status of my latest deploy?”
• “Show me my Netlify projects.”
• “Build me a website for my restaurant and deploy it to Netlify.”

To get started, open Connectors in Grok, search for Netlify, then select Add and follow the setup prompts. You’ll need a Grok account with access to connectors and a Netlify account.

Learn more in our guide to setting up Grok for Netlify.

TypeSafe’s Jev 1.14.0 model is now available through Netlify’s AI Gateway with zero configuration required.

Install @typesafe-ai/sdk and use it directly in your Netlify Functions without managing API keys or authentication. AI Gateway handles credentials automatically, and usage is billed to your Netlify credits.

Jev answers typed questions about your application state. Here’s an example using jev-1.14.0 to categorize a support ticket as a bug, feature request, or question:

import { choice, TypeSafeClient } from '@typesafe-ai/sdk';

export default async () => {
    const typesafe = new TypeSafeClient();

    const response = await typesafe.systemOne({
        model: 'jev-1.14.0',
        state: { issue: 'App crashes when I click Save.' },
        questions: {
            label: choice('Categorize this ticket', {
                bug: null,
                feature: null,
                question: null,
            }),
        },
    });

    return Response.json(response);
};

Jev 1.14.0 is also available across Scheduled Functions, Background Functions, and Edge Functions. You get automatic access to Netlify’s caching, rate limiting, and authentication infrastructure.

Learn more in the AI Gateway documentation and the TypeSafe documentation.

Meta’s Muse Spark and Muse Wonder models are now available through Netlify’s AI Gateway with zero configuration required. Choose muse-spark-1.1 for coding, computer use, and multimodal perception; muse-spark-1.2 for coding-optimized agentic workflows; muse-spark-1.3 for long-horizon coding and agentic work with cleaner code and fewer tokens; or muse-wonder-1.0 for complex coding tasks, long-running agents, and advanced computer use.

Use the OpenAI SDK directly in your Netlify Functions without managing API keys or authentication. AI Gateway takes care of the setup automatically. Here’s an example using Muse Wonder with the Responses API:

import OpenAI from 'openai';

export default async () => {
    const meta = new OpenAI();

    const response = await meta.responses.create({
        model: 'muse-wonder-1.0',
        input: 'How can AI improve my coding?'
    });

    return Response.json(response);
};

These Meta models also work in Scheduled Functions, Background Functions, and Edge Functions, with Netlify’s caching, rate limiting, and authentication infrastructure available automatically.

Learn more in the AI Gateway documentation and explore the models on Meta’s developer site.

You can now subscribe to Netlify events from ChatGPT and set up automations that respond to what’s happening on your sites.

Instead of checking the Netlify dashboard or waiting on an email, you can have ChatGPT act as soon as something happens. Events you can subscribe to include:

• A deploy succeeded
• A build failed
• A form submission came in

For more events to subscribe to, check out our deploy events.

Combine events with Netlify plugin and MCP server

Events get more useful when you pair them with everything else you can already do through the Netlify ChatGPT plugin and Netlify MCP server. For example, you could set up an automation that:

• Reviews new form submissions and flags the ones that need a follow-up
• Summarizes what changed when a production deploy succeeds

Because these automations live in ChatGPT, you can describe what you want in plain language and adjust it as your workflow changes.

Get started

Connect Netlify in ChatGPT, then ask it to subscribe to the events you care about for your project. Learn more in our guide to using Netlify with ChatGPT.

OpenAI’s Decisions API is now available through Netlify’s AI Gateway with zero configuration required.

Use the OpenAI SDK directly in your Netlify Functions to classify, route, and score inputs without managing API keys. Instead of generating prose, the Decisions API answers questions you define about an input, and choice answers are always one of the options you declared. That means there’s no output to parse and nothing unexpected to handle before you branch on the result. The Decisions API is in beta and currently runs on gpt-6-luna.

Here’s a Function for an online store that sorts incoming return requests by reason:

import type { Config } from "@netlify/functions";
import OpenAI from "openai";

export default async (req: Request) => {
  const openai = new OpenAI();

  const { answers } = await openai.decisions.create({
    model: "gpt-6-luna",
    input: await req.text(),
    questions: [
      {
        type: "choice",
        name: "reason",
        instructions: "Why is the customer returning this item?",
        choices: [
          { value: "wrong_size" },
          { value: "defective" },
          { value: "not_as_described" },
          { value: "changed_mind" },
        ],
      },
    ],
  });

  return Response.json(answers[0]);
};

export const config: Config = { path: "/api/returns", method: "POST" };

Send it “The jacket fits well, but the zipper came off the second time I wore it” and you get back:

{
  "type": "choice",
  "name": "reason",
  "choice": "defective",
  "probabilities": [
    { "value": "wrong_size", "probability": 0.01 },
    { "value": "defective", "probability": 0.95 },
    { "value": "not_as_described", "probability": 0.03 },
    { "value": "changed_mind", "probability": 0.01 }
  ],
  "confidence": 0.93
}

choice is safe to branch on directly, so you can send a prepaid label for defective items or offer an exchange for the wrong size, and use confidence to pass unclear requests to your support team.

Learn more in the AI Gateway documentation and the OpenAI API reference.

You can now add comments to individual lines in the diff on the Code tab of Agent Runners, so you can give your agent precise feedback on the code it generated.

Previously, asking for a fix meant describing where the problem was in your prompt, such as naming the file, quoting the code, or explaining which function you meant.

Now you can pinpoint exactly where you want changes. Open the Code tab for an agent run, select the + next to a line in the diff, and leave a comment about what you want changed. Your comments are sent along with your next prompt, so the agent knows exactly which code lines you’re referring to.

This makes follow-up prompts more useful when you want to:

• Correct a specific bug or edge case without rewriting the whole request
• Ask for a different approach in one part of a change while keeping the rest
• Flag naming, styling, or structure issues right where they appear
• Leave feedback on several spots across multiple files in a single follow-up run

Try it on your next agent run, or learn more about making changes with Agent Runners.

Every site created with Agent Runners now includes Open Graph tags. When you share a link to your site, it shows up as a proper preview instead of a bare URL.

Social media sites and messaging apps read Open Graph tags to build link previews. Now, when you or your visitors share a site you created with Agent Runners, the preview includes a screenshot of the site, its title, and a description. That makes your site easier to recognize, more inviting to click, and look better than ever from the moment you share it.

This is available on all public sites created with Agent Runners. You don’t need to do anything to turn it on.

Learn more about Agent Runners in the Agent Runners docs.