Build your agent
Configure an AgentStack agent’s knowledge, retrieval, behavior, appearance, and secure integrations.
You build an AgentStack agent through an iterative loop. You add authoritative knowledge, decide how the agent retrieves it, and test the result. You save only the changes that pass your evaluation. The agent sidebar groups the main building controls under Sources, Playground, and Settings.
Start with knowledge
The Sources → Content screen accepts a website, a single page, files, Notion pages, and explicit Q&A pairs. They are not interchangeable. A website crawl is useful for a public documentation area. A Q&A pair is better for one canonical correction. Before you choose a format, see Sources overview.
Before you grade answers, wait for an asynchronous source to finish. A submitted crawl or upload is not evidence that its material is retrievable. Keep obsolete sources out of the knowledge base so an old policy does not compete with its replacement.
Set retrieval deliberately
Sources → Retrieval controls the confidence guidance and search mode. Standard retrieval is the default. Hybrid, Deep Search, and Auto are useful only when a fixed test set shows they improve the questions your customers ask. The retrieval guide covers the modes and their plan availability.
Test before saving
In Playground, you can change the model and system prompt, use Apply & Test, and compare several configurations without saving each experiment. Test each configuration against representative supported, unsupported, and ambiguous questions. Save only the model and prompt that pass all three types. Read Use Playground for the distinction between test-only changes and saved settings.
Finish the customer experience
Under Settings, configure the agent’s general behavior, conversation opening, widget appearance, public access controls, custom domains, and webhooks. These settings have different permission requirements and save behavior. Use their focused guides:
Use one controlled change at a time. A reliable agent requires that you know why a result changed. It can change because of the source, prompt, model, retrieval mode, or customer surface.