Netlify Changelog - Agent-runners

Rich link previews for Agent Runners sites

Tue, 29 Sep 2026 00:00:00 GMT

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.

GPT-6.1 Sol now available in AI Gateway and Agent Runners

Tue, 29 Sep 2026 00:00:00 GMT

OpenAI’s GPT-6.1 Sol model is now available through Netlify’s AI Gateway and Agent Runners with zero configuration required. Use the OpenAI SDK directly in your Netlify Functions without managing API keys or authentication. AI Gateway handles everything automatically. Here’s an example using GPT-6.1 Sol with the Responses API: import OpenAI from 'openai'; export default async () => { const openai = new OpenAI(); const response = await openai.responses.create({ model: 'gpt-6.1-sol', input: 'Give a concise explanation of how AI works.', }); return Response.json(response); }; GPT-6.1 Sol 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 Agent Runners documentation.

Prompt and preview in one view with Agent Runners

Mon, 28 Sep 2026 00:00:00 GMT

Agent Runners now shows you a preview right next to your prompt. Previously, you’d get a link to the Deploy Preview and have to open it in a separate tab to see what the agent changed. Now the preview appears inline, so you can review the result and write your next prompt without switching back and forth. Plus, you can still access the Deploy Preview link if you need it. This makes iterating with an agent feel more like a conversation. See what changed, spot what’s off, and follow up with the next instruction, all in one view. Example flow For example, say you’re building a strategic task organizer and prompt your agent to add a button that generates a quarterly impact report. Now you can watch your agent’s updates in the side preview next to your prompt. Agent Runners side-by-side view showing a chat prompt to add a quarterly report button next to the live Deploy Preview of the resulting task organizer app In this example, your agent on Netlify will also let you know if your project cannot save your tasks across browser sessions yet, and you can approve adding a database in the same view. This is just one example of how Netlify gives you professional-grade capabilities, such as a real working database, with your agent of choice when you prompt with Agent Runners. Try it out See it in action when you start a new agent run or learn more about working with agents on Netlify.

Claude Sonnet 5.5 now available in AI Gateway and Agent Runners

Mon, 28 Sep 2026 00:00:00 GMT

Anthropic’s Claude Sonnet 5.5 model is now available through Netlify’s AI Gateway and Agent Runners with zero configuration required. Use the Anthropic SDK directly in your Netlify Functions without managing API keys or authentication. AI Gateway handles everything automatically. Here’s an example using Claude Sonnet 5.5: import Anthropic from '@anthropic-ai/sdk'; export default async () => { const anthropic = new Anthropic(); const response = await anthropic.messages.create({ model: 'claude-sonnet-5-5', max_tokens: 4096, messages: [ { role: 'user', content: 'How can AI improve my coding?' } ] }); return Response.json(response); }; Claude Sonnet 5.5 is also available across Background Functions, Scheduled 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 Agent Runners documentation.

New project activity feed

Thu, 24 Sep 2026 00:00:00 GMT

As part of our ongoing work to simplify the Netlify dashboard, we’ve added an activity feed to the project overview page. It’s available on all plans and adapts to how your project is set up. Now when you open a project, the activity feed gives you a snapshot of your project's latest updates, with quick access to:

Production versions of your project, including the version last published
Preview versions of your project
Agent runs, so you can see what agents are working on and what you and your teammates have prompted

Project activity feed in the Netlify dashboard listing recent activity newest first, with filters for All, Production, Previews, and Agent runs. Entries include an in-progress agent run, a published production deploy, and two branch deploys with Preview links. This means that instead of tracking down Production deploy links, Deploy Preview links, branch deploy links, and your agent runs list separately, you can now see where your project stands at a glance in one single spot. The feed also suggests next steps to help you get started. It's one of several dashboard improvements we're gradually rolling out to simplify the Netlify experience, so you may have spotted a few already, with more to come.

Claude Opus 5.5 now available in AI Gateway and Agent Runners

Tue, 22 Sep 2026 00:00:00 GMT

Anthropic’s Claude Opus 5.5 model is now available through Netlify’s AI Gateway and Agent Runners with zero configuration required. Use the Anthropic SDK directly in your Netlify Functions without managing API keys or authentication. AI Gateway handles everything automatically. Here’s an example using Claude Opus 5.5: import Anthropic from '@anthropic-ai/sdk'; export default async () => { const anthropic = new Anthropic(); const response = await anthropic.messages.create({ model: 'claude-opus-5-5', max_tokens: 4096, output_config: { effort: 'medium' }, messages: [ { role: 'user', content: 'How can AI improve my coding?', }, ], }); return new Response(JSON.stringify(response), { headers: { 'Content-Type': 'application/json' }, }); }; Claude Opus 5.5 is also available across Background Functions, Scheduled 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 Agent Runners documentation.

GPT-6 Sol and GPT-6 Luna now available in AI Gateway and Agent Runners

Tue, 22 Sep 2026 00:00:00 GMT

OpenAI’s GPT-6 Sol and GPT-6 Luna models are now available through Netlify’s AI Gateway and Agent Runners with zero configuration required. Use the OpenAI SDK directly in your Netlify Functions without managing API keys or authentication. AI Gateway handles everything automatically. Here’s an example using GPT-6 Sol with the Responses API: import OpenAI from 'openai'; export default async () => { const openai = new OpenAI(); const response = await openai.responses.create({ model: 'gpt-6-sol', input: 'Give a concise explanation of how AI works.', }); return Response.json(response); }; GPT-6 Sol and GPT-6 Luna are 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 Agent Runners documentation.

Agent Runners: Get a working result when low on credits

Mon, 14 Sep 2026 00:00:00 GMT

Agent Runners are now better at completing their work when a run has less credits remaining than the task requires. If you are close to running our of credits during a run, the agent will start focusing on delivering the most useful result it can with the credits it has left. It finishes work already in progress, leaves the project in a working state, and provides a clear summary of what it completed. Previously, an ambitious task could end abruptly before the agent wrapped up, leaving partial changes and little explanation. Now, you’re more likely to get a working result you can use right away, or a solid, clearly documented starting point for your next run. This improvement applies automatically to every agent and model available in Agent Runners. There’s nothing to enable or configure. Learn more in Make changes with Agent Runners and how credits work.

ChatGPT Images 2.5 now available in AI Gateway and Agent Runners

Wed, 09 Sep 2026 00:00:00 GMT

OpenAI’s ChatGPT Images 2.5 models are now available through Netlify’s AI Gateway and Agent Runners with zero configuration required. Use gpt-image-2.5-flare or gpt-image-2.5-sunburst to generate images for your applications. Use the OpenAI SDK directly in your Netlify Functions without managing API keys or authentication. AI Gateway handles everything automatically. Here’s an example using the gpt-image-2.5-flare model: import OpenAI from 'openai'; const ai = new OpenAI(); export default async (req, context) => { const response = await ai.images.generate({ model: 'gpt-image-2.5-flare', prompt: 'A golden retriever working at a laptop in a sunny startup office', size: '1024x1024', quality: 'low', output_format: 'jpeg', output_compression: 80 }); const imageBuffer = Buffer.from(response.data[0].b64_json, 'base64'); return new Response(imageBuffer, { status: 200, headers: { 'content-type': 'image/jpeg', 'cache-control': 'no-store' } }); }; Both ChatGPT Images 2.5 models are available across standard Functions, Background Functions, Scheduled Functions, Edge Functions, and Agent Runners. You get automatic access to Netlify’s caching, rate limiting, and authentication infrastructure. Learn more in the AI Gateway documentation and Agent Runners documentation.

Agent Runners now use smarter scoping for new projects

Fri, 04 Sep 2026 00:00:00 GMT

Agent Runners can now scope ambitious prompts for new projects to create a partial working project and provide next steps within the available credit budget. Previously, a brand new project could use up its credit budget before the agent finished for ambitious prompts, leaving the run marked Cancelled partway through. Now, your agent scopes the work more intelligently. It builds out part of the project and shares a plan for next steps, so you can preview a working version within your new project credit budget instead of the run stalling out. Learn more in Make changes with Agent Runners.

GPT-6 Astra now available in AI Gateway and Agent Runners

Fri, 04 Sep 2026 00:00:00 GMT

OpenAI’s GPT-6 Astra model is now available through Netlify’s AI Gateway and Agent Runners with zero configuration required. Use the OpenAI SDK directly in your Netlify Functions without managing API keys or authentication. AI Gateway handles everything automatically. Here’s an example using GPT-6 Astra with the Responses API: import OpenAI from 'openai'; export default async () => { const openai = new OpenAI(); const response = await openai.responses.create({ model: 'gpt-6-astra', input: 'Give a concise explanation of how AI works.', }); return Response.json(response); }; GPT-6 Astra is also available across Background Functions, Scheduled 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 Agent Runners documentation.

Google Gemini 3.8 Flash now available in AI Gateway and Agent Runners

Wed, 02 Sep 2026 00:00:00 GMT

Google’s Gemini 3.8 Flash model is now available through Netlify’s AI Gateway and Agent Runners with zero configuration required. Use the Google GenAI SDK directly in your Netlify Functions without managing API keys or authentication. The AI Gateway handles everything automatically. Here’s an example using the Gemini 3.8 Flash model: import { GoogleGenAI } from '@google/genai'; export default async () => { const ai = new GoogleGenAI({}); const response = await ai.models.generateContent({ model: 'gemini-3.8-flash', contents: 'How can AI improve my coding?' }); return Response.json(response); }; Gemini 3.8 Flash is available for all Function types and Agent Runners. You get automatic access to Netlify’s caching, rate limiting, and authentication infrastructure. Learn more in the AI Gateway documentation and Agent Runners documentation.

Claude Fable 5.1 now available in AI Gateway and Agent Runners

Tue, 01 Sep 2026 00:00:00 GMT

Anthropic’s Claude Fable 5.1 model is now available through Netlify’s AI Gateway and Agent Runners with zero configuration required. Use the Anthropic SDK directly in your Netlify Functions without managing API keys or authentication. The AI Gateway handles everything automatically. Here’s an example using the Claude Fable 5.1 model: import Anthropic from '@anthropic-ai/sdk'; export default async () => { const anthropic = new Anthropic(); const response = await anthropic.messages.create({ model: 'claude-fable-5-1', max_tokens: 4096, messages: [ { role: 'user', content: 'How can AI improve my coding?' } ] }); return new Response(JSON.stringify(response), { headers: { 'Content-Type': 'application/json' } }); }; Claude Fable 5.1 is available for all Function types and Agent Runners. You get automatic access to Netlify’s caching, rate limiting, and authentication infrastructure. Learn more in the AI Gateway documentation and Agent Runners documentation.

Agent Runners can now ask clarifying questions

Wed, 19 Aug 2026 00:00:00 GMT

Agent Runners can now ask you clarifying questions before they start building. When a few details could significantly improve the result, the agent pauses and asks instead of guessing. The clarifying questions UI in an Agent Runners session, asking: What should the tracker dashboard keep track of? How clarifying questions work Say you start with something broad, like “Build a tracker dashboard.” Previously the agent had to make every call for you: what the dashboard should track, whether entries should be editable and saved to a database or live in the code as a read-only placeholder, whether the look should be dark and high-contrast or light, clean, and editorial. Now it can ask, and you can answer directly where the agent run works. Answer, skip, or add your own context Answering questions is always optional so you can answer the ones you have opinions about and skip the rest. Or you can skip all questions and let the agent decide. Finally, you can always add context in your own words alongside your answers. In our testing, even a few quick answers make the first build noticeably sharper and saves credits you’d otherwise spend on course corrections. Once you answer, the run continues as usual: the agent writes the code, works with Netlify’s platform features, and creates a Deploy Preview you can review and iterate on. Learn more Clarifying questions work with every agent and model available in Agent Runners. Try it out and see how to use Agent Runners in our docs.

Pre-launch toolbar and the Powered by Netlify badge

Wed, 19 Aug 2026 00:00:00 GMT

Private projects on Netlify will now show a pre-launch toolbar so you can share your project for review and run audits using AI checks before you make your project public. Private projects and agent runs require a Credit pricing plan. If you're on a Legacy pricing plan, you will not have access to the pre-launch toolbar. Audits consume credits like any other agent run. For public projects, new projects created on a Free plan on or after August 19, 2026 show a Powered by Netlify badge to all visitors. The badge is configurable for each project through your project configuration settings. To turn the Netlify badge on or off for all visitors of your site:

Go to Project configuration > General > Powered by Netlify badge and turn it on or off.

Additionally, any visitor can hide the badge for themselves, and that choice is stored locally on their browser and never reaches Netlify. All projects created before August 19, 2026 have the badge off by default. Users on a Credit-based Personal and Pro plans can also turn the badge on or off per-project. For these plans, the badge is always off by default. Release timeline We’re rolling both overlays out gradually over the next few weeks, so a project that qualifies may not have them yet. Learn more about the pre-launch toolbar and the Powered by Netlify badge in the Netlify documentation.

Google Gemini 3.7 Flash now available in AI Gateway and Agent Runners

Thu, 13 Aug 2026 00:00:00 GMT

Google’s Gemini 3.7 Flash model is now available through Netlify’s AI Gateway and Agent Runners with zero configuration required. Use the Google GenAI SDK directly in your Netlify Functions without managing API keys or authentication. The AI Gateway handles everything automatically. Here’s an example using the Gemini 3.7 Flash model: import { GoogleGenAI } from '@google/genai'; export default async () => { const ai = new GoogleGenAI({}); const response = await ai.models.generateContent({ model: 'gemini-3.7-flash', contents: 'How can AI improve my coding?' }); return Response.json(response); }; Gemini 3.7 Flash is available for all Function types and Agent Runners. You get automatic access to Netlify’s caching, rate limiting, and authentication infrastructure. Learn more in the AI Gateway documentation and Agent Runners documentation.

Agent Runners adds OpenCode and AI model controls

Thu, 06 Aug 2026 00:00:00 GMT

Through a new partnership with OpenRouter, you can now choose OpenCode as an AI agent with Agent Runners. OpenCode allows you to choose many different AI models, including Kimi, DeepSeek, and GLM. Learn more about our OpenRouter partnership through the Netlify blog on open models. Previously, you could only choose Claude, Gemini, or Codex as your AI agent, but now you can choose the OpenCode agent, which offers even more models from different AI providers. Requests made through OpenCode are only routed to model providers with a Zero Data Retention (ZDR) policy, so your prompts and outputs are never stored. AI model selection As part of this release, you can now also specify which model any agent uses with Agent Runners. Previously, Claude, Gemini, and Codex agents all automatically chose a model for the task you prompted with Agent Runners. Agents can still auto-select a model for you, but now you can also choose different models for your agents, with these preferences saved just for you on your device. This means you can experiment with which AI models best fit your needs. To open your AI model options for Agent Runners, select agent near your prompt box. Choosing the best AI model for your needs To help you choose the best AI model for your needs, within Agent Runners you can browse details about each model, including a link to learn more, a visual way to compare cost across all supported models with a 1-5 dot scale, and the option to set an effort level for that model. To get the most out of your credits, consider the following strategies:

Use a more expensive, capable model to help you plan your project updates and design a clear prompt with Agent Runners’ ask mode , then switch to a cheaper model to implement the changes.
Experiment with using different AI models for different tasks.
Be explicit about the functionality you want when using models that are cheaper or set to a lower effort level. These models may fill in placeholder functionality. For example, a model might render a contact page without fully setting up working Netlify Forms, so the page looks complete but doesn’t actually work as expected.

Learn more To learn more, check out our docs:

Agent Runners overview
Make changes with Agent Runners

Ask mode for Agent Runners

Thu, 30 Jul 2026 00:00:00 GMT

Netlify Agent Runners now have a mode selector. Pick Ask and the agent reads, investigates, and answers questions about your project. Build is still the default and works exactly as before. Ask mode is strictly read-only. The agent can’t edit files, run commands, deploy, or change settings. With no build or Deploy Preview, Ask runs are often faster and use fewer credits. It answers with real context: your repository, your project context, and your project’s Netlify Database. Your data is often the fastest way to answer a question about your app, and Ask mode can query it with no risk of a write. A few prompts to steal:

“How many users are in the database?”
“Walk me through how authentication is implemented in this project. Which files handle it, and where is the token stored?”
“Our Largest Contentful Paint is bad on mobile. Read the code and tell me what's most likely responsible.”
“Plan out how we can migrate to the latest version of Astro.”

Because it’s a mode on the same run, you can switch to Build the moment an answer turns into a task — same run, same context, no re-explaining. Ask mode is available on all agents, Claude Code, Google Gemini, and OpenAI Codex, in Agent Runners today. See the docs on Ask and Build modes.

Claude Opus 5 Now Available in AI Gateway and Agent Runners

Fri, 24 Jul 2026 00:00:00 GMT

Anthropic’s Claude Opus 5 model is now available through Netlify’s AI Gateway and Agent Runners with zero configuration required. Use the Anthropic SDK directly in your Netlify Functions without managing API keys or authentication. The AI Gateway handles everything automatically. Here’s an example using the Claude Opus 5 model: import Anthropic from '@anthropic-ai/sdk'; export default async () => { const anthropic = new Anthropic(); const response = await anthropic.messages.create({ model: 'claude-opus-5', max_tokens: 4096, output_config: { effort: 'medium' }, messages: [ { role: 'user', content: 'How can AI improve my coding?' } ] }); return new Response(JSON.stringify(response), { headers: { 'Content-Type': 'application/json' } }); }; Claude Opus 5 is available for all Function types and Agent Runners. You get automatic access to Netlify’s caching, rate limiting, and authentication infrastructure. Learn more in the AI Gateway documentation and Agent Runners documentation.

Google Gemini 3.6 Flash and Gemini 3.5 Flash-Lite Now Available in AI Gateway and Agent Runners

Tue, 21 Jul 2026 00:00:00 GMT

Google’s Gemini 3.6 Flash and Gemini 3.5 Flash-Lite models are now available through Netlify’s AI Gateway and Agent Runners with zero configuration required. Use the Google GenAI SDK directly in your Netlify Functions without managing API keys or authentication. The AI Gateway handles everything automatically. Here’s an example using the Gemini 3.6 Flash model: import { GoogleGenAI } from '@google/genai'; export default async () => { const ai = new GoogleGenAI({}); const response = await ai.models.generateContent({ model: 'gemini-3.6-flash', contents: 'How can AI improve my coding?', }); return Response.json(response); }; Gemini 3.6 Flash and Gemini 3.5 Flash-Lite are available for all Function types and Agent Runners. You get automatic access to Netlify’s caching, rate limiting, and authentication infrastructure. Learn more in the AI Gateway documentation and Agent Runners documentation.

Set AI usage limits for individual team members

Wed, 15 Jul 2026 00:00:00 GMT

Team Owners on Pro plans can now limit Agent Runners spend for individual members in your team, giving you finer control over how AI credits are used across your team. Set a single credit limit that applies to every member, then customize it with overrides for specific people who need more (or less) room to work. This makes it easy to give power users a higher ceiling while keeping predictable, budget-friendly defaults for everyone else. You’ll find these controls in Team Settings under General > AI Enablement. This builds on our existing team-wide AI usage limits, so you can now manage AI spend both for an entire team and down to each individual member. We’ve also updated how AI inference credit usage is displayed in your dashboard, making it easier to monitor AI usage and manage your AI spend. Learn more about AI inference usage and how credits work.

OpenAI GPT-5.6 Sol, Luna, and Terra Now Available in AI Gateway and Agent Runners

Thu, 09 Jul 2026 00:00:00 GMT

OpenAI’s GPT-5.6 Sol, Luna, and Terra models are now available through Netlify’s AI Gateway and Agent Runners with zero configuration required. Use the OpenAI SDK directly in your Netlify Functions without managing API keys or authentication. The AI Gateway handles everything automatically. Here’s an example using the GPT-5.6 Sol model: import OpenAI from 'openai'; export default async () => { const openai = new OpenAI(); const response = await openai.responses.create({ model: 'gpt-5.6-sol', input: 'Give a concise explanation of how AI works.', }); return Response.json(response); }; GPT-5.6 Sol, Luna, and Terra are available for all Function types and Agent Runners. You get automatic access to Netlify’s caching, rate limiting, and authentication infrastructure. Learn more in the AI Gateway documentation and Agent Runners documentation.

Claude Sonnet 5 now available in AI Gateway and Agent Runners

Tue, 30 Jun 2026 00:00:00 GMT

Anthropic’s Claude Sonnet 5 model is now available through Netlify’s AI Gateway and Agent Runners with zero configuration required. Use the Anthropic SDK directly in your Netlify Functions without managing API keys or authentication. The AI Gateway handles everything automatically. Here’s an example using the Claude Sonnet 5 model: import Anthropic from '@anthropic-ai/sdk'; export default async () => { const anthropic = new Anthropic(); const response = await anthropic.messages.create({ model: 'claude-sonnet-5', max_tokens: 4096, messages: [ { role: 'user', content: 'How can AI improve my coding?' } ] }); return Response.json(response); }; Claude Sonnet 5 is available for all Function types and Agent Runners. You get automatic access to Netlify’s caching, rate limiting, and authentication infrastructure. Learn more in the AI Gateway documentation and Agent Runners documentation.

Functions redesigned for agents

Thu, 25 Jun 2026 00:00:00 GMT

We have redesigned Netlify functions for an improved agent experience. With these updates, functions are more discoverable, easier to autocomplete, update, and manage for people and agents alike. They move function configuration into code, making it type-safe and immediately visible to editors, tools, and agents, with no platform-specific naming conventions to memorize or get wrong. None of these changes are breaking, so you can adopt them on your own timeline. Netlify Functions are serverless functions that run on-demand in response to HTTP requests or platform events. They handle server-side logic without any infrastructure to manage, and live in your repository at netlify/functions/. To learn more about these updates in depth, check out our blog on redesigning Netlify functions for agent experience. See the table below for a summary. Feature: Event handlers What changed: Export typed event handlers from the default export object What it means for agents: Typed handlers are discoverable like any API, with no magic filenames to guess or get wrong. What you need to do: Nothing required. Adopt the new syntax for new event handlers for better agent discoverability and updates. Feature: Background functions What changed: Declare with background: true in config instead of the -background filename suffix What it means for agents: Type-safe and config-driven, not name-driven. Agents can set it in code without guessing platform naming conventions, and get an error if the value is wrong. What you need to do: Nothing required. The -background suffix still works. Feature: Region selection What changed: Set per-function via the region config property, replacing the global UI setting What it means for agents: Agents can set region as a type-safe config property, catching invalid values before deploy rather than at runtime. Use deploy previews to test before going live. What you need to do: Nothing required. Optionally move region out of the UI into config for per-function control. Feature: Memory and vCPU What changed: Set via memory or vcpu config properties; both values scale together automatically What it means for agents: Agents provisioning compute-heavy workloads (inference, large payloads) can do so in code. What you need to do: Nothing. Defaults unchanged. Set only if your workload needs more than 1 GB / 0.5 vCPU. Requires a credit-based Pro plan. Feature: getContext() What changed: Named import from @netlify/functions, replacing the Netlify.context global What it means for agents: Named imports surface in autocomplete and carry type information. Globals are invisible to agents; named imports are not. What you need to do: Nothing required. Netlify.context still works. Switch to getContext() for better discoverability. Learn more in the Netlify Functions documentation, which has also been recently revamped.

Claude Opus 4.8 now available in AI Gateway and Agent Runners

Thu, 28 May 2026 00:00:00 GMT

Anthropic’s Claude Opus 4.8 model is now available through Netlify’s AI Gateway and Agent Runners with zero configuration required. Use the Anthropic SDK directly in your Netlify Functions without managing API keys or authentication. The AI Gateway handles everything automatically. Here’s an example using the Claude Opus 4.8 model: import Anthropic from '@anthropic-ai/sdk'; export default async () => { const anthropic = new Anthropic(); const response = await anthropic.messages.create({ model: 'claude-opus-4-8', max_tokens: 4096, messages: [ { role: 'user', content: 'How can AI improve my coding?' } ] }); return new Response(JSON.stringify(response), { headers: { 'Content-Type': 'application/json' } }); }; Claude Opus 4.8 is available for all Function types and Agent Runners. You get automatic access to Netlify’s caching, rate limiting, and authentication infrastructure. Learn more in the AI Gateway documentation and Agent Runners documentation.

Gemini 3.5 Flash now available in Agent Runners

Wed, 20 May 2026 00:00:00 GMT

Google's Gemini 3.5 Flash model is now available through Netlify's Agent Runners with zero configuration required. Learn more in the Agent Runners documentation.

Agent Runners workflow improvements

Wed, 13 May 2026 00:00:00 GMT

We're making it easier to use Agent Runners in the existing workflows you have. Now you can do the following in a more seamless way:

Prompt new changes using Agent Runners more quickly from a GitHub pull request link
Copy output from Agent Runners faster so you can get back to what you're doing
Track pull request ownership so you can understand who is doing what at-a-glance

Start prompting updates from GitHub PR comment link GitHub-linked sites already receive a comment on each pull request with links to build logs, failure diagnostics, and more. That comment now also includes a Make changes link that opens Agent Runner for the site, with the pull request‘s branch pre-selected in the dropdown. This makes it faster to act on review feedback or investigate a failing build. Learn more about Agent Runners. Copy to clipboard in single click You can now copy Agent Runner output with a single click. Previously, grabbing output text — especially long responses or anything on mobile — meant manually selecting it all. A new copy-to-clipboard button now appears alongside Agent Runner output, making it easy to drop results into a doc, a message, or wherever you need them. Pull requests auto-assign people for clearer ownership Agent Runner–created pull requests now automatically assign the person who opened them, provided their GitHub account is linked with Netlify. Before this change, pull requests opened by an agent runner had no assignee, making it harder for teams to track ownership at a glance. Now, when Netlify can match the user to a GitHub account, the pull request is assigned to them automatically. To take advantage of this, make sure your GitHub account is connected under your Netlify account settings.

OpenAI GPT-5.5 and GPT-5.5 Pro now available in AI Gateway and Agent Runners

Fri, 24 Apr 2026 00:00:00 GMT

OpenAI’s GPT-5.5 and GPT-5.5 Pro models are now available through Netlify’s AI Gateway and Agent Runners with zero configuration required. Use the OpenAI SDK directly in your Netlify Functions without managing API keys or authentication. The AI Gateway handles everything automatically. Here’s an example using the GPT-5.5 model: import OpenAI from 'openai'; export default async () => { const openai = new OpenAI(); const response = await openai.responses.create({ model: 'gpt-5.5', input: 'Give a concise explanation of how AI works.', }); return Response.json(response); }; GPT-5.5 and GPT-5.5 Pro are available for all Function types and Agent Runners. You get automatic access to Netlify’s caching, rate limiting, and authentication infrastructure. Learn more in the AI Gateway documentation and Agent Runners documentation.

Rename an agent run

Thu, 23 Apr 2026 00:00:00 GMT

You can now rename an agent run to more easily identify it in your list of runs and share it with teammates. Previously, agent runs were automatically titled based on your prompt, which made longer lists harder to scan once you had several runs going. Editing the title lets you give each agent run a short, meaningful name, such as the feature you’re building or the bug you’re chasing, so you can find it again quickly and send it to a teammate without needing to explain which run is which. Try it out Open any agent run, select the title, and type a new name. The updated title appears in your list of runs and anywhere the run is shared. Learn more about Agent Runners.

New frontend-design skill for Agent Runners

Fri, 17 Apr 2026 00:00:00 GMT

Agent Runners now include a frontend-design skill that guides AI agents toward creating distinctive, production-grade frontend interfaces with high design quality. When building web components, pages, or applications, AI agents often default to generic, cookie-cutter aesthetics. The frontend-design skill steers agents toward creative, polished output that avoids that "AI slop" look and instead produces UIs with real visual identity and craft. Here's what a generated calculator component looks like without the skill: Calculator without frontend-design skill And here's the same prompt with the frontend-design skill enabled: Calculator with frontend-design skill The skill is automatically available in Agent Runners and activates when the agent is asked to build web components, pages, or applications. No configuration required—just prompt your agent to build a UI and the skill handles the rest. Learn more about Agent Runners and available skills in the Netlify docs.

Claude Opus 4.7 now available in AI Gateway and Agent Runners

Thu, 16 Apr 2026 00:00:00 GMT

Anthropic's Claude Opus 4.7 model is now available through Netlify's AI Gateway and Agent Runners with zero configuration required. Use the Anthropic SDK directly in your Netlify Functions without managing API keys or authentication. The AI Gateway handles everything automatically. Here's an example using the Claude Opus 4.7 model: import Anthropic from '@anthropic-ai/sdk'; export default async () => { const anthropic = new Anthropic(); const response = await anthropic.messages.create({ model: 'claude-opus-4-7', max_tokens: 4096, messages: [ { role: 'user', content: 'How can AI improve my coding?' } ] }); return new Response(JSON.stringify(response), { headers: { 'Content-Type': 'application/json' } }); }; Claude Opus 4.7 is available for all Function types and Agent Runners. You get automatic access to Netlify's caching, rate limiting, and authentication infrastructure. Learn more in the AI Gateway documentation and Agent Runners documentation.

Netlify CLI adds prompt-based creation and anonymous deploys

Tue, 31 Mar 2026 00:00:00 GMT

We've improved the Netlify CLI's Agent Experience to make it the fastest way for both developers and AI agents to go from idea to deployed site. Here's what's new. Create a new project from a prompt The netlify create command now builds you a new site from scratch, triggering Agent Runners: netlify create "a landing page for a SaaS product with a waitlist signup" This single command will:

Create a new Netlify project for you
Deploy it to a live URL
Pull down the code so you can start iterating locally

Prefer to build with GitHub? The Netlify CLI can also create a new GitHub repo and automatically hook it up to your new Netlify project, no manual setup required. Deploy without an account Need to spin up something quick without creating an account first or signing in? The new --allow-anonymous flag lets you deploy without a Netlify account: netlify deploy --allow-anonymous This will create the project, deploy it to a live URL, and let you claim the project within an hour. This is especially useful for AI agents that need to create temporary projects without requiring Netlify credentials upfront. Better agent experience throughout We've resolved the major issues agents commonly hit with the CLI. The CLI is now a more predictable integration point whether you're building with an AI coding assistant or orchestrating your own agents. Install or update the Netlify CLI to try it out: npm install -g netlify-cli@latest

Deploy from Codex with the Netlify Plugin

Fri, 27 Mar 2026 00:00:00 GMT

You can now deploy sites to Netlify directly from OpenAI Codex using the Netlify plugin in the Codex plugin directory. Netlify plugin in Codex Codex plugins extend Codex with apps, skills, and MCP servers, to access external tools, data, and workflows directly from your coding environment. With the Netlify plugin, Codex can create projects, configure settings, and deploy without leaving the coding workflow. What you can do Deploy directly from Codex

Deploy projects using the Netlify CLI workflow
Generate preview URLs automatically
Deploy to production when ready
Validate build configuration before deployment

Manage your projects

Create new projects
Install extensions
Manage environment variables
Configure visitor access controls
Manage forms
Update project settings

Review and fix deployments

Inspect deploy status
Retrieve build logs
Identify configuration issues
Iterate on fixes within Codex

Codex is also available through Agent Runners, where you can prompt AI agents against your live project and deploy changes directly from the Netlify Dashboard. The Netlify plugin for Codex is available now in the Codex plugin directory.

Introducing Prompt Templates

Wed, 18 Mar 2026 00:00:00 GMT

To help you and your agents build more effectively, we're introducing reusable Prompt Templates available directly from within Netlify. Browse a curated collection of reusable prompts for common Netlify workflows: accessibility audits, A/B testing with Edge Functions, and more. Each template uses variable placeholders so you can adapt it to your project without starting from scratch. Prompt Templates live directly in your project's agent runs dashboard. From there you can:

Browse public prompt templates
Customize and save your own versions of any template for your team
Submit templates back to the community to share what is working for you

Learn more about managing Prompt Templates for your team.

Limit AI usage on your team

Fri, 06 Mar 2026 00:00:00 GMT

Team Owners can now set a credit limit on AI inference usage to keep Agent Runners and AI Gateway costs within budget. When your team’s usage hits the credit cap you define, active agent runs stop, new agent runs are blocked, and continued AI Gateway usage is paused to help you keep more of your credit balance. This is especially useful for teams actively using AI features who want predictable monthly costs without manually watching the meter. Set it once, and Netlify enforces it automatically across your entire team. Learn more in our docs on limiting AI features. Agent run credits tracking You can also track how much each agent run task costs on your agent runs page, shown next to how long the agent took to run the task. Learn more about AI inference usage and how credits work.

OpenAI GPT-5.4 and GPT-5.4 Pro Now Available in AI Gateway and Agent Runners

Thu, 05 Mar 2026 00:00:00 GMT

OpenAI’s GPT-5.4 and GPT-5.4 Pro models are now available through Netlify’s AI Gateway and Agent Runners with zero configuration required. Use the OpenAI SDK directly in your Netlify Functions without managing API keys or authentication. The AI Gateway handles everything automatically. Here’s an example using the GPT-5.4 model: import OpenAI from 'openai'; export default async () => { const openai = new OpenAI(); const response = await openai.responses.create({ model: 'gpt-5.4', input: 'Give a concise explanation of how AI works.', }); return Response.json(response); }; GPT-5.4 and GPT-5.4 Pro are available for all Function types and Agent Runners. You get automatic access to Netlify’s caching, rate limiting, and authentication infrastructure. Learn more in the AI Gateway documentation and Agent Runners documentation.

Deploy Preview screenshots in agent runs

Tue, 03 Mar 2026 23:59:59 GMT

Starting today, all completed agent runs show a screenshot of your Deploy Preview. This makes it easier to quickly see the result of an agent run and keep track of agent run sessions without opening the full preview. Screenshot of the agent runs dashboard showing a completed run with a Deploy Preview screenshot Test it out today:

Go to your Netlify project dashboard.
On the left, select Agent runs, then choose an existing agent run or start a new one by entering a prompt and selecting Run task.
At the bottom of your agent run sessions, you'll find a screenshot of your Deploy Preview. The screenshot is taken from the main page of your project.

Note: If you've set up private deploys or password protection, the screenshot will show a sign-in page instead. Learn more about Password protection. Learn more about getting started with Agent Runners.

Use Netlify Agent Runners from Linear

Fri, 27 Feb 2026 23:59:59 GMT

Linear users can now launch Netlify Agent Runners directly from any Linear issue, allowing you to seamlessly share context with your AI agent of choice. If you have your Linear issue synced with related Slack messages, this context will also be included in your agent run prompt. Before starting your agent run, you can review and edit your prompt. Next, you can choose which AI agent to use — Claude Code, Google Gemini, or OpenAI Codex. Netlify Agent Runners doesn’t lock you into using a single AI agent so you can pick the agent that fits the task best. To start an agent run from Linear:

Go to a Linear issue where you want to trigger an agent run.
In the top right corner, select Configure coding tools.... Linear issue view showing the Configure coding tools option in the top right corner
Toggle Netlify Agent Runners on.
Go back to the issue and in the top right corner, select Open in Netlify Agent Runners. Linear issue view showing the Open in Netlify Agent Runners option in the top right corner
Review the prompt and choose your AI agent.
To start the agent run, select Run task.

Once you’ve enabled this integration from your personal Linear preference settings, any Linear issue you open in your workspace will give you the option to open with Netlify Agent Runners. Now your entire team can save time and seamlessly share context between Linear and Netlify Agent Runners while keeping this work clearly tracked across Linear and Netlify. Learn more about Agent Runners.

Claude Sonnet 4.6 now available in AI Gateway and Agent Runners

Tue, 17 Feb 2026 00:00:00 GMT

Anthropic's Claude Sonnet 4.6 model is now available through Netlify's AI Gateway and Agent Runners with zero configuration required. Use the Anthropic SDK directly in your Netlify Functions without managing API keys or authentication. The AI Gateway handles everything automatically. Here's an example using the Claude Sonnet 4.6 model: import Anthropic from '@anthropic-ai/sdk'; export default async () => { const anthropic = new Anthropic(); const response = await anthropic.messages.create({ model: 'claude-sonnet-4-6', max_tokens: 4096, messages: [ { role: 'user', content: 'How can AI improve my coding?' } ] }); return Response.json(response); }; Claude Sonnet 4.6 is available for all Function types and Agent Runners. You get automatic access to Netlify's caching, rate limiting, and authentication infrastructure. Learn more in the AI Gateway documentation and Agent Runners documentation.

Sync changes with Agent Runners

Fri, 13 Feb 2026 00:00:00 GMT

You can now sync changes from different agent runs in the Netlify dashboard. This is especially helpful if you use Netlify Drop to publish or update your project and don't use Git workflows to sychronize versions of your project. Syncing changes helps you and your whole team build and publish faster. How it works For example, let's say you used Netlify Drop to publish your project without setting up a Git workflow. Next, you decide to use Agent Runners to add a new landing page. You also start an agent run to update your project's footer and publish the new footer. Your agent run for the new landing page doesn't include the footer changes yet. To get these updates, start a sync run from the Agent Runners dashboard. This will apply all new updates from the live production version of your project. Now when you publish your landing page updates, you’ll get the updated footer as well. Syncing changes with Agent Runners enables smoother shipping with several agent runs and with multiple team members working on the same project.

Claude Opus 4.6 now available in AI Gateway and Agent Runners

Thu, 05 Feb 2026 00:00:00 GMT

Anthropic's Claude Opus 4.6 model is now available through Netlify's AI Gateway and Agent Runners with zero configuration required. Use the Anthropic SDK directly in your Netlify Functions without managing API keys or authentication. The AI Gateway handles everything automatically. Here's an example using the Claude Opus 4.6 model: import Anthropic from '@anthropic-ai/sdk'; export default async () => { const anthropic = new Anthropic(); const response = await anthropic.messages.create({ model: 'claude-opus-4-6', max_tokens: 4096, messages: [ { role: 'user', content: 'How can AI improve my coding?' } ] }); return new Response(JSON.stringify(response), { headers: { 'Content-Type': 'application/json' } }); }; Claude Opus 4.6 is available for all Function types and Agent Runners. You get automatic access to Netlify's caching, rate limiting, and authentication infrastructure. Learn more in the AI Gateway documentation and Agent Runners documentation.

Agent Runners improvements

Thu, 29 Jan 2026 00:00:00 GMT

Here are some Agent Runners improvements that all people with Credit-based pricing plans can enjoy: Shareable agent run links You can now link directly to an agent run to share it with your team or bookmark for later review. Screenshot showing the copy link button in the Agent Runners interface Agent Runners available no matter how you deploy Agent Runners now supports static projects without build steps. Previously, projects without a build step couldn't use Agent Runners. Improved diff view performance By default, the diff view now loads only the first 50 changed files with an option to load more. This improves performance for large projects. Feedback welcome Keep sharing your product feedback about Agent Runners in the feedback form at the bottom of our Agent Runners docs page. And don't forget that while you can run multiple agent runs and do other work while they run, you can also play a Netlify game while you wait for the agent to finish.

GPT-5.2-Codex Now Available in AI Gateway and Agent Runners

Wed, 14 Jan 2026 00:00:00 GMT

OpenAI's GPT-5.2-Codex model is now available through Netlify's AI Gateway and Agent Runners with zero configuration required. Use the OpenAI SDK directly in your Netlify Functions without managing API keys or authentication. The AI Gateway handles everything automatically. Here's an example using the GPT-5.2-Codex model: import OpenAI from 'openai'; export default async () => { const openai = new OpenAI(); const response = await openai.responses.create({ model: 'gpt-5.2-codex', input: 'How does AI work?' }); return new Response(JSON.stringify(response), { headers: { 'Content-Type': 'application/json' } }); }; GPT-5.2-Codex is available across Background Functions, Scheduled Functions, and Agent Runners. You get automatic access to Netlify's caching, rate limiting, and authentication infrastructure. Learn more in the AI Gateway documentation and Agent Runners documentation.

Play Games While Agent Runners Do the Work

Thu, 08 Jan 2026 00:00:00 GMT

While Agent Runners take care of tasks on your site, you can now play games right in the UI. We've brought the same beloved build-time games to the Agent Runner page, so you can flip tiles, plan snake, install other games, or even create your own while your agent runs in the background. A little delight, now everywhere you wait. Play a game while you wait modal showing a Match the Pairs game on the Agent Runner page Learn more about the Netlify Entertainment System.

GPT-5.2 and GPT-5.2-Pro now available in AI Gateway and Agent Runners

Thu, 11 Dec 2025 00:00:00 GMT

OpenAI's GPT-5.2 and GPT-5.2-Pro are now available through AI Gateway and Agent Runners. You can call these models from Netlify Functions without configuring API keys; the AI Gateway provides the connection to OpenAI for you. Example usage in a Function: import { OpenAI } from "openai"; export default async () => { const openai = new OpenAI(); const response = await openai.chat.completions.create({ model: "gpt-5.2", messages: [ { role: "user", content: "What are the key improvements in GPT-5.2?" } ] }); return new Response(JSON.stringify(response), { headers: { "Content-Type": "application/json" } }); }; These models work across any function type and are compatible with other Netlify primitives such as caching and rate limiting, giving you control over request behavior across your site. See the AI Gateway documentation for details. Agent Runners support the same models, enabling AI to complete long-running coding tasks. You can learn more in the Agent Runners documentation.

GPT-5.1-Codex-Max now available in AI Gateway and Agent Runners

Thu, 04 Dec 2025 00:00:00 GMT

OpenAI's GPT-5.1-Codex-Max model is now available through Netlify's AI Gateway and Agent Runners with zero configuration required. Use the OpenAI SDK directly in your Netlify Functions without managing API keys or authentication. The AI Gateway handles everything automatically. Here's an example using the GPT-5.1-Codex-Max model: import OpenAI from 'openai'; export default async () => { const openai = new OpenAI(); const response = await openai.responses.create({ model: 'gpt-5.1-codex-max', input: 'What improvements are in GPT‑5.1-Codex-Max?' }); return new Response(JSON.stringify(response), { headers: { 'Content-Type': 'application/json' } }); }; GPT-5.1-Codex-Max is available across Background Functions, Scheduled Functions, and Edge Functions. You get automatic access to Netlify's caching, rate limiting, and authentication infrastructure. Learn more in the AI Gateway documentation. You can also leverage GPT-5.1-Codex-Max with Agent Runners to build powerful AI-powered workflows, including expanded tool use and support for long-running agent tasks. Learn more in the Agent Runners documentation.

Claude Opus 4.5 now live in AI Gateway, plus latest Claude Code via Agent Runners

Mon, 24 Nov 2025 00:00:00 GMT

Anthropic's Claude Opus 4.5 model is now available through Netlify's AI Gateway with zero configuration required. Use the Anthropic SDK directly in your Netlify Functions without managing API keys or authentication. The AI Gateway handles everything automatically. Here's an example using the Claude Opus 4.5 model: import Anthropic from "@anthropic-ai/sdk"; export default async () => { const anthropic = new Anthropic(); const response = await anthropic.messages.create({ model: "claude-opus-4-5-20251101", max_tokens: 4096, messages: [ { role: "user", content: "Give me pros and cons of using claude-opus-4-5-20251120 over other models." }, ], }); return new Response(JSON.stringify(response), { headers: { "Content-Type": "application/json" } }); } Claude Opus 4.5 is available across Background Functions, Scheduled Functions, and Edge Functions. You get automatic access to Netlify's caching, rate limiting, and authentication infrastructure. Learn more in the AI Gateway documentation. You can also access the newest Claude Code capabilities via Agent Runners, including expanded tool use and support for long-running agent workflows. Learn more in the Agent runner documentation.

Gemini 3 now available in AI Gateway and Agent Runners

Tue, 18 Nov 2025 00:00:00 GMT

Google's Gemini 3 Pro Preview model is now available through Netlify's AI Gateway and Agent Runners with zero configuration required. Use the Google GenAI SDK directly in your Netlify Functions without managing API keys or authentication. The AI Gateway handles everything automatically. Here's an example using the Gemini 3 Pro Preview model: import { GoogleGenAI } from "@google/genai"; export default async (request: Request, context: Context) => { const ai = new GoogleGenAI({}); const response = await ai.models.generateContent({ model: "gemini-3-pro-preview", contents: "Explain why gemini 3 is better than other models", }); return new Response(JSON.stringify({ answer: response.text }), { headers: { "Content-Type": "application/json" } }); }; Gemini 3 is available across Background Functions, Scheduled Functions, and Agent Runners. You get automatic access to Netlify's caching, rate limiting, and authentication infrastructure. Learn more in the AI Gateway documentation and Agent Runners documentation.