--- title: "Agent-runners | Netlify Changelog" description: "Get the latest updates on Netlify products and features to meet your developer needs." source: "https://www.netlify.com/changelog/tag/agent-runners/" last_updated: "2026-07-14T01:27:39.000Z" --- # Posts tagged "Agent-runners" All Tags Agent-runners AI Ai-gateway Angular Astro AX Build CLI Database Design Devtools Domains E-commerce Extensions Forms Framework Functions Logs Next.js Nuxt.js Remix SDK Security Updates Workflow [Subscribe to feed](https://www.netlify.com/changelog/tag/agent-runners/feed.xml) - [ ## OpenAI GPT-5.6 Sol, Luna, and Terra Now Available in AI Gateway and Agent Runners ](/changelog/gpt-5-6-sol-luna-terra-ai-gateway-agent-runners/) July 9, 2026 - [ai gateway](/changelog/tag/ai-gateway/) - [agent runners](/changelog/tag/agent-runners/) 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](https://docs.netlify.com/build/ai-gateway/overview/) and [Agent Runners documentation](https://docs.netlify.com/build/build-with-ai/agent-runners/overview/). [Permalink to OpenAI GPT-5.6 Sol, Luna, and Terra Now Available in AI Gateway and Agent Runners Permalink](/changelog/gpt-5-6-sol-luna-terra-ai-gateway-agent-runners/) - [ ## Claude Sonnet 5 now available in AI Gateway and Agent Runners ](/changelog/claude-sonnet-5-ai-gateway-agent-runners/) June 30, 2026 - [ai gateway](/changelog/tag/ai-gateway/) - [agent runners](/changelog/tag/agent-runners/) 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](https://docs.netlify.com/build/ai-gateway/overview/) and [Agent Runners documentation](https://docs.netlify.com/build/build-with-ai/agent-runners/overview/). [Permalink to Claude Sonnet 5 now available in AI Gateway and Agent Runners Permalink](/changelog/claude-sonnet-5-ai-gateway-agent-runners/) - [ ## Functions redesigned for agents ](/changelog/2026-06-25-functions-redesigned-for-agents/) June 25, 2026 - [functions](/changelog/tag/functions/) - [agent runners](/changelog/tag/agent-runners/) - [ai](/changelog/tag/ai/) 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](https://www.netlify.com/blog/netlify-functions-designed-for-agent-experience). See the table below for a summary. Feature What changed What it means for agents What you need to do [Event handlers](https://docs.netlify.com/build/functions/overview/#platform-events) Export typed event handlers from the default export object Typed handlers are discoverable like any API, with no magic filenames to guess or get wrong. Nothing required. Adopt the new syntax for new event handlers for better agent discoverability and updates. [Background functions](https://docs.netlify.com/build/functions/background-functions/) Declare with `background: true` in config instead of the `-background` filename suffix 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. Nothing required. The `-background` suffix still works. [Region selection](https://docs.netlify.com/build/functions/configuration/#region) Set per-function via the `region` config property, replacing the global UI setting 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. Nothing required. Optionally move region out of the UI into config for per-function control. [Memory and vCPU](https://docs.netlify.com/build/functions/configuration/#memory-or-vcpu) Set via `memory` or `vcpu` config properties; both values scale together automatically Agents provisioning compute-heavy workloads (inference, large payloads) can do so in code. Nothing. Defaults unchanged. Set only if your workload needs more than 1 GB / 0.5 vCPU. Requires a credit-based Pro plan. [`getContext()`](https://docs.netlify.com/build/functions/api/#getcontext) Named import from `@netlify/functions`, replacing the `Netlify.context` global Named imports surface in autocomplete and carry type information. Globals are invisible to agents; named imports are not. Nothing required. `Netlify.context` still works. Switch to `getContext()` for better discoverability. Learn more in the [Netlify Functions documentation](https://docs.netlify.com/build/functions/overview/), which has also been recently revamped. [Permalink to Functions redesigned for agents Permalink](/changelog/2026-06-25-functions-redesigned-for-agents/) - [ ## Claude Opus 4.8 now available in AI Gateway and Agent Runners ](/changelog/claude-opus-4-8-ai-gateway-agent-runners/) May 28, 2026 - [ai gateway](/changelog/tag/ai-gateway/) - [agent runners](/changelog/tag/agent-runners/) 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](https://docs.netlify.com/build/ai-gateway/overview/) and [Agent Runners documentation](https://docs.netlify.com/build/build-with-ai/agent-runners/overview/). [Permalink to Claude Opus 4.8 now available in AI Gateway and Agent Runners Permalink](/changelog/claude-opus-4-8-ai-gateway-agent-runners/) - [ ## Gemini 3.5 Flash now available in Agent Runners ](/changelog/gemini-3-5-flash-agent-runners/) May 20, 2026 - [agent runners](/changelog/tag/agent-runners/) 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](https://docs.netlify.com/build/build-with-ai/agent-runners/overview/). [Permalink to Gemini 3.5 Flash now available in Agent Runners Permalink](/changelog/gemini-3-5-flash-agent-runners/) - [ ## Agent Runners workflow improvements ](/changelog/2026-05-13-agent-runners-workflow-improvements/) May 13, 2026 - [agent runners](/changelog/tag/agent-runners/) 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](https://docs.netlify.com/build/build-with-ai/agent-runners/overview/). ## 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](https://docs.netlify.com/manage/accounts-and-billing/user-settings/). [Permalink to Agent Runners workflow improvements Permalink](/changelog/2026-05-13-agent-runners-workflow-improvements/) - [ ## OpenAI GPT-5.5 and GPT-5.5 Pro now available in AI Gateway and Agent Runners ](/changelog/gpt-5-5-ai-gateway-agent-runners/) April 24, 2026 - [ai gateway](/changelog/tag/ai-gateway/) - [agent runners](/changelog/tag/agent-runners/) 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](https://docs.netlify.com/build/ai-gateway/overview/) and [Agent Runners documentation](https://docs.netlify.com/build/build-with-ai/agent-runners/overview/). [Permalink to OpenAI GPT-5.5 and GPT-5.5 Pro now available in AI Gateway and Agent Runners Permalink](/changelog/gpt-5-5-ai-gateway-agent-runners/) - [ ## Rename an agent run ](/changelog/2026-04-23-rename-agent-run/) April 23, 2026 - [agent runners](/changelog/tag/agent-runners/) 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](https://docs.netlify.com/build/build-with-ai/agent-runners/overview/). [Permalink to Rename an agent run Permalink](/changelog/2026-04-23-rename-agent-run/) - [ ## New frontend-design skill for Agent Runners ](/changelog/2026-04-17-frontend-design-skill-for-agent-runners/) April 17, 2026 - [agent runners](/changelog/tag/agent-runners/) - [design](/changelog/tag/design/) - [ai](/changelog/tag/ai/) 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](/images/changelog/frontend-design-skill-without.png) And here’s the same prompt with the `frontend-design` skill enabled: ![Calculator with frontend-design skill](/images/changelog/frontend-design-skill-with.png) 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](https://docs.netlify.com/build/build-with-ai/agent-runners/overview/) and available skills in the Netlify docs. [Permalink to New frontend-design skill for Agent Runners Permalink](/changelog/2026-04-17-frontend-design-skill-for-agent-runners/) [Next page](/changelog/tag/agent-runners/page/2)