Agent Mode
Agent mode enables conversational development inside Appfarm Create. Describe the desired app or functionality and follow along as the agent goes through the implementation tasks. The agent is currently limited to certain parts of the platform, see Current Limitations.
Getting Started
When you have no apps in your solution, the Apps empty state will prompt you to describe the app for the agent to build, as shown in the image below.
The agent will then create a plan for building the app based on your prompt, breaking the implementation down into specific tasks. You can refine and iterate on this plan by asking the agent to remove, add or revise tasks. Once you're satisfied with the plan, click "Build app". You will then be taken to the Apps page, the AI panel will open with your initial prompt and the list of implementation tasks, and the agent will automatically start working on the first task.
Working with the agent
Tasks and Changes
Changes made by the agent to your solution are not automatically saved to the database. As it works, all modifications remain local to your client and appear in a list of unsaved changes at the bottom of the AI panel, as shown below. You can click any item in the list to jump to its location in Create. Once the agent completes a task, you can review the changes and choose to save or revert them. Note that changes can't be reverted or saved while the agent is working.
When you save changes made by the agent, Create will create only one transaction in the change history for undo/redo. The transaction can include multiple changes and it will be stated how many items were changed.
Important
Any changes you make while there are unsaved changes in your solution will not be automatically saved to the database. Instead, they'll be added to the list of unsaved changes. Once you've saved or reverted these changes, Create will resume automatically saving your work.
When starting from an app-building plan or handling a complex request, the agent creates tasks to track its work. The task list appears at the bottom of the AI panel, as shown below. As each task is completed, its status updates in the list, and you can click "Save & Continue" to save the changes and move on to the next task.
Once the agent begins a task, you can enable auto-run. This allows the agent to work through all subsequent tasks autonomously, without requiring user input. Please be aware that progress is not saved while auto-run is active, so unsaved changes will accumulate. To prevent it from running indefinitely, the agent will automatically pause after a set period and prompt you to continue.
Error handling
Like any AI, the agent can make mistakes. These mistakes may result in bugs in your app, such as faulty logic in an action or suboptimal UI. You can resolve these issues by prompting the agent—check out our Prompting guide for effective techniques—or by fixing them manually.
The agent may also make changes to your models that aren't technically valid in Create. When the agent completes an operation, all changes go through a validation layer. If issues are detected, the error messages are automatically sent back to the agent, which will then attempt to fix them. If the agent can't resolve the errors after several attempts, it will pause and ask whether you'd like it to continue.
Please help us avoid errors and improve the agent by providing feedback when you encounter issues. This can be done by clicking the or after the response provided by the agent.
Threads
A thread is a conversation with the agent that may include a list of tasks. When you message the agent, the entire thread is used as context along with the status of all associated tasks.
Start new thread: Click the icon in the top right corner of the AI panel.
Show thread history: Click the icon in the top right corner of the AI panel to view your ten most recent threads in the current solution. Select any thread to continue the conversation and complete unfinished tasks.
By default, Create starts a new thread when you refresh or reload your solution. To resume your previous context, open the thread history and select your most recent thread.
Prompting guide
Prompting refers to how you formulate the textual instructions to Appfarm AI. When using Appfarm AI in Agent mode, the way you formulate and structure your prompt directly influences the end result. A good prompt is specific and provides necessary context. Also, when building Apps, you should start small and work iteratively.
Be specific
When building new apps: Instead of "Build an inventory management app", be specific about what you want to build: "Build an inventory management app for a mobile device, with a dashboard, UI and logic for managing tools, checkout tools and checkin tools". You may also use bullets for the list of functionalities.
When extending functionality: Instead of "Build a dashboard", be more specific: "Build a professional-looking dashboard for managers to get an overview of current tools status, with Tiles for tracking current status and a line chart showing checkouts last week".
When improving or debugging functionality: Instead of "Make this look better", be more specific: "Improve the UI of this dashboard to be modern with cards, KPIs and charts". Instead of "My app is not working, can you help?" try "When clicking this Submit button, nothing happens. Can you identify and fix the error?".
Provide context
Being specific is great. But in many cases, the AI will benefit from your context: What is the industry you are building that inventory management for? Who are the users? Can you provide some known examples (other SaaSes) with the functionality you are looking for?
When building new apps: "Build a field operations app" has little context. The AI would benefit from knowing where, when, or by whom this field operations app should be used. Try instead "Build a mobile field operations app for construction workers to register deviations (with categorisation and image upload), and register reception of material on the construction site".
When extending functionality: Instead of "Create functionality for generating an order confirmation", try to add some context (and be more specific): "Extend this action: Add functionality for generating an order confirmation for customers submitting wedding cake orders from our website, and send the confirmation as an email attachment to the customer".
When improving or debugging functionality: When improving a UI, some more context could be beneficial in many cases. For example, from "Improve this action" to "Improve this action: Add error handling and user feedback for non-technical users". Or when debugging, add as much context as possible, and be precise: "This action is not working" could be "This action works for me in Develop environment, but not for end-users in production. Security setup looks correct. Can you help me identify potential issues, and then suggest some fixes?".
Start small - work iteratively
Appfarm AI allows you to build Apps from scratch, with a planning process as the starting point, resulting in an agreed scope containing a set of tasks. The built-in instruction for the AI is to always use an MVP approach when building full apps, but you will still benefit from trying to keep the scope down ("start small") in your prompt. Appfarm AI is great at extending functionality for the app later.
A reasonable initial scope is an app containing < 15 tasks in the planning process. However, note that some tasks could be small, and others large. For example, the AI could generate a task "Create all views", which could be huge if the initial scope is to create a complete CRM system with 50 different entities (object classes), and they should all be accessible as tables in the app.
A good rule of thumb is to try to limit the number of entities requested to < 10 at once. For example, instead of "Create a full CMR system with all core functionality as the state-of-the-art best CRM SaaSes", try "Build a simple and modern CRM for the sales department of our B2B Office Equipment company <Company Name>. The app should have functionality and UI for tracking, adding and editing Companies, Contacts, Leads and Sales Activities, and a Dashboard with Sales KPIs". This prompt is specific, has context, and starts small (with a given set of 4 main entities). And the app can easily be extended once created.
How the agent works
When you give the agent a task or prompt, it receives your application model description as context. Based on its system instructions, it identifies available tools and determines which ones to use. Through these tools, the agent learns how building blocks work in Appfarm Create. It then issues commands to insert, update, or delete parts of the application model. These commands function identically to actions performed by a human user, so the same guardrails and rules apply.
Read more about our approach to AI on our website.
Current Limitations
The agent is currently able to implement the following concepts in Create:
The agent is currently limited to working on smaller apps and will return an error if asked to modify large, complex applications. We currently recommend using it primarily for building new apps from scratch.
Last updated
Was this helpful?