> For the complete documentation index, see [llms.txt](https://docs.beefree.io/beefree-sdk/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.beefree.io/beefree-sdk/ai-and-mcp/ai-co-pilot-closed-beta/beefree-ai-faqs.md). # Beefree AI FAQs #### **What is Beefree SDK's AI Co-Pilot ?** The AI Co-Pilot is a ready-made promt-to-design agent available in the email builder. It is installed as a Partner AddOn in Developer Console. Once installed, it surfaces a conversational AI panel directly inside the builder within your application, letting end users generate, iterate on, and apply content across their email design, all without leaving the editor. #### **How is this different from the AI Writing Assistant?** The AI Writing Assistant targets individual content blocks. The AI Co-Pilot goes further, surfacing a full conversational agent panel that allows users to work across their entire design in a guided chat experience. #### **How do I get access?** The AI Co-Pilot is in closed beta. Once you get accepted into the beta, log in to the Beefree SDK Developer Console, navigate to your application, and open the AddOns section. From there, click Browse AddOns, select the Beefree AI AddOn, and click Install. Once installed, select your provider and model, enter your API key, toggle Enable, and save. Make sure you have an API key from your chosen AI provider before starting. #### **Do I need my own AI provider API key?** Yes. You supply an API key from a supported provider during setup in the Developer Console. Beefree does not provide API keys. #### **Which AI providers and models are supported?** Three providers are currently supported: Anthropic, OpenAI, and Gemini (Gemini support is currently in preview). Each provider offers multiple models. Recommended starting points, chosen for their balance of cost, speed, and output quality, are Claude Haiku 4.5, GPT-5.4 Mini, and Gemini 2.5 Flash. Higher-tier models are available if your use case demands stronger output, but come with higher cost and latency. #### **Can I customize how the AI behaves for my users?** Yes. The `systemPrompt` setting lets you inject role, tone, or brand voice instructions that are forwarded with every chat request. You can also use [Brand Rules](/beefree-sdk/ai-and-mcp/brand-rules-for-ai.md) to ensure the Co-Pilot follows specific brand guidelines. #### **Can I control costs?** Yes. The `maxIterations` setting caps the agent's auto-continue loop, with a default of 10. Lowering it is recommended in cost-sensitive environments, especially when using larger models. #### **Can I persist chat history across sessions?** Yes, though persistence is the responsibility of the host application. The SDK broadcasts the full conversation through the `onInfo` callback after each turn. You store it, then pass it back as `initialMessages` on the next session. #### **Can I disable the Co-Pilot for specific users?** Yes. Set `enabled: false` on the AI Co-Pilot entry in `beeConfig` for any user you want to exclude. #### **Is this available in production?** Not yet. The AI Co-Pilot is currently in closed beta for selected partners. The interface, configuration options, supported models, and underlying behavior are all subject to change. Do not use it in production. Share feedback directly with your Beefree customer success manager. #### **What is the applicable use policy?** During the beta, you may use the MCP Server and its tools for development, prototyping, and evaluation. Access is subject to Beefree SDK's standard Terms of Service. Abuse or production-scale misuse will result in suspension of access. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.beefree.io/beefree-sdk/ai-and-mcp/ai-co-pilot-closed-beta/beefree-ai-faqs.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.