Get started with AgentStack

AgentStack gives you one place to build an AI agent. You can connect it to reliable knowledge, test its answers, and make it available to customers. You do not need to configure every feature before the agent becomes useful. A strong first version has a narrow job and one trustworthy source. It also has a clear system prompt and a small set of questions that you can grade yourself.

The recommended path

Use this order for a new agent:

1. Create the agent. Give it a name that makes its job obvious.
2. Add one source. Start with a public website page, a file, or a Q&A pair whose contents you know well.
3. Test in Playground. Ask questions with known answers. Then try an unsupported question to see how the agent handles uncertainty.
4. Improve the instructions or knowledge. Change one item at a time so that you know which change helped.
5. Deploy one channel. The website widget is usually the fastest way to reach your first customers.
6. Review real conversations. Use Activity and Analytics to find missing knowledge, confusing prompts, and failed answers.

The first-agent tutorial walks through this loop with the exact dashboard controls.

What makes an agent reliable

An agent's behavior comes from several layers:

• Sources provide the facts the agent can retrieve.
• The system prompt sets the agent's role, boundaries, tone, and response to uncertain questions. AgentStack adds its own retrieval and handoff safeguards on top of this prompt.
• The model affects reasoning quality, speed, and credit cost.
• Channels set where customers can reach the agent.
• Actions let the agent do work, for example call a connected tool. Before the agent can use an action, you must configure it.

Treat these layers separately. If an answer contains the wrong policy, fix or replace the source. If the answer is factually correct but too verbose, improve the system prompt. If the same source and prompt perform inconsistently on difficult questions, compare models.

Before you publish

Before you expose the agent to customers, prepare a small acceptance set. Include at least:

• Three common questions, each with an exact expected answer.
• One ambiguous question that must trigger a clarifying question.
• One question outside the available knowledge.
• One request that the agent must not complete.
• One question written in different words from the source text.

The response-quality guide shows how to run this evaluation in Playground. For practical design rules, see Best practices. If you need to choose between providers or credit tiers, see Choose a model.

Go deeper when you need it

After the first version works, use the detailed guides for the next steps:

• Train the agent
• Install the website widget
• Connect other channels
• Add integrations and actions
• Set up human handoff

When a first setup does not behave as expected, you can return to the FAQ.