Agents

The grid lists every agent in your account. Each card carries the agent name, model badge, last-updated timestamp, and a quick-action menu (Test, Edit, Duplicate, Delete).

• Create Agent (header)The Create Agent button in the top-right of the header opens the four-step wizard — Template → Identity → LLM → Done — from any page.
• FilterNarrows the grid by model, provider, or template. Filters stack — picking OpenAI + gpt-4o shows only agents that match both.
• SortReorders the grid by name, model, last updated, or last used. The default is most-recently-updated first.
• SearchLive filter against agent name and description. Combines with the filter chips above.
• Agent cardEach tile shows name, description, model + provider badge, last-updated time, and a menu with Test, Edit, Duplicate, Move to Folder, and Delete.

1. 1

   Pick a template

   Templates ship with a battle-tested system prompt and tone. Pick Website Chatbot to ground an agent on your site content, Order Status for an MCP-backed lookup, or Custom for a blank slate.
2. 2

   Set identity

   The name + description pre-fill from the template. Click Prompt Library to swap the system prompt for one of the curated presets. The description is what teammates see in the dashboard and what members see in the portal agent picker.
3. 3

   Connect a model

   Pick a provider, then choose a model from the Model dropdown — it's prefilled with that provider's current catalogue, so there's no need to type a model ID by hand. Paste a key (or choose a saved one from Use saved key — see LLM Keys), set the temperature, and expand the Advanced panel if you need to tune max tokens or token costs.
4. 4

   Save and review

   The wizard finishes on a confirmation screen. Click Go to agent and you land on the new agent's Agent Settings. To try it out, open the Playground from the left menu — it runs against the globally-selected agent.

There is no in-page tab bar. The agent's four views are entries in the left menu's Agent group — Agent Settings, Conversations, Token Cost, and Versions. They all act on the agent chosen in the global agent dropdown, so switching view keeps your selection. On the Agent Settings view the page header carries the agent's Live / Draft pill (click to start or stop it), a click-to-copy Agent Id, and a ⋮ overflow menu (Start / Stop, Delete).

• Agent SettingsIdentity, model + provider, the API key, and the system prompt — plus the header chrome (Live/Draft pill, the Agent Id you'll send as X-Agent-Id, and the ⋮ actions). The Model field is a dropdown of the provider's current models. Edits save when you click Update Agent.
• ConversationsRecent conversations handled by this agent — open one to inspect the full message trail.
• Token CostPer-million-token rates the platform uses to attribute spend to this agent. Keep these accurate so Analytics and Tracing match your provider bill.
• VersionsEvery publish creates a snapshot. Diff, roll back, or pin a member-portal agent to a specific version.
• Documents · Knowledge · Web Sources · MCPGrounding and tools live in the dedicated Knowledge and MCP workspaces. Select this agent in the header dropdown, then open Knowledge or MCP from the left menu to manage its documents, snippets, Q&A, crawled pages, and tools in one place.

• Temperature0.0 – 2.0. Lower = more deterministic; higher = more creative. Templates ship with the right default for their use case.
• Max tokensHard ceiling for the response length. The default fits the agent's template; raise it for long-form assistants.
• Output typetext, markdown, json, or code. JSON output is validated server-side; invalid replies are auto-retried (up to 2) before erroring.
• StreamingOn by default for Pro+. Disable to receive a single response body — useful for batch jobs that don't need progressive UI.
• Max tool roundsCaps how many MCP tool round-trips the agent can take before the platform returns the final reply. Default 8 — enough for most multi-step lookups, low enough to bound cost.