How Agents Work
What an agent is, and the order you build one in.
An AI agent is a software-based digital worker that understands goals, makes decisions, and takes actions to complete tasks. Unlike a chatbot, which mainly generates responses, an agent reasons through problems, reads knowledge you give it, uses tools and integrations, and interacts with external systems — databases, APIs, enterprise applications — with minimal human intervention, while still allowing human oversight where you want it.
This page walks through building one, in the order you actually do it. Each step links to the concept behind it and the screen that configures it.
1. Describe what you want the agent to do
Start with a plain-language description of the task. Be specific about what the agent should accomplish — the more context you give, the less manual configuration you'll do afterwards. You don't need to know which settings to use yet.
2. Confirm how the agent identifies and responds
Review the suggested name and description, and choose the Agent Output Format that matches who — or what — receives the responses: Markdown for humans reading in a UI, Json when your application parses the output.
3. Choose the runtime version
New agents are pinned to the latest executor version your tenant supports. Existing agents stay on the version they were created with unless you change it deliberately — the platform won't force an upgrade. Move to a newer version when you want a capability it introduces.
4. Set how the agent thinks
Three levers, all on one screen, all with sensible defaults:
Agent Capability (
Auto,Intelligent Planner,Next Best Step, orFast; defaultAuto) — how deeply the agent thinks about each request.Autolets the platform decide per request.Fastleaves out persona memory, FAQ memory, and learning cases for lower latency.Response Mode (
Advanced,Balanced, orFlash; defaultAdvanced) — the speed-versus-quality trade-off.Execution Model and Planning Model — which model runs the agent, and which one plans its work. They can differ. Both are chosen in
Advancedmode, from the models AI Gateway serves for your organization.
5. Decide what the agent remembers
Both memory settings are under Agent Config → Reinforcement Learning, and both are off on a new agent.
User persona memory (Enable User Persona) lets the agent remember what an individual user has asked about, preferred, or corrected, across conversations.
FAQ memory (Enable FAQ) lets the agent reuse a stored answer when a question matches a known FAQ.
6. Remove capabilities the agent doesn't need
The platform attaches a set of skills to every agent by default. Read that list and disable anything your agent won't use — keeping unused skills active widens the range of things the agent can do wrong.
7. Connect the tools and data the agent needs
For each external system the agent must reach, attach the right kind of skill: an API call for REST endpoints and an MCP server for tool platforms. For document search, attach a knowledge base. Configure endpoints, authentication, and schemas for each.
8. Decide which guardrails the agent runs
Open Agent Config → Guardrails and choose the per-agent controls:
Sensitive Data Masking replaces detected PII with tokens before it reaches a model.
Tool Execution Approval pauses the agent before selected skills run, so the user can allow or deny each call.
9. Test whether it behaves as intended
Use Try Agent to run sample inputs that represent real usage. Open the execution trace to see how the agent interpreted your instructions, which skills it called, and how long each step took. If something's off — wrong skill, unexpected output — adjust and re-test before moving on.
→ Test · Regression Evals
10. Go live, and keep it improving
Once the agent performs on your test cases, deploy it. Then review what it actually does in production: approve corrections that represent genuine improvements, reject anything incorrect or exploitable, and iterate as edge cases emerge.
→ Deploy · Monitor · Human-in-the-Loop
The loop closes: what you learn in step 10 becomes a change in steps 4 through 7. For the ideas behind each step, see Agent Foundations.
Last updated
Was this helpful?

