Skip to main content
Agents can be used in a variety of ways:

​
Use agents in Slack

Slack is how most teams use Luno OS agents today. Connect the Luno OS Slack App (luno connect slack --kind luno; catalog slug slackbot — not a Personal Slack Account user token), bind Slack channels to your agent, and teammates can message it like any coworker. The gateway turns each message into an agent session and posts the reply back as the bot. See external channels for the three Slack connection kinds, connecting, binding channels, listen modes, and channel sessions.

​
Use agents in the web app

Every deployed agent has a chat surface on its page in the web app: open Agents in Studio (or the agent in its Space, in the User view), select the agent, and message it directly; the chat dock can talk to it from any page. Each conversation is an agent session — start a new one with New chat, and revisit past sessions from the history rail on the right. Sessions started in the app appear in Runs alongside every other surface. Replies stream live, tool approvals are decided inline, and the composer has mode and model pickers — see Chat with agents. This is where teammates who never touch the CLI use what you build. Chatting with a deployed agent is different from Luno Builder, the built-in builder chat that creates and edits agents rather than running them.

​
Use agents from the CLI

The CLI is the most practical way to run an agent while you build and test it. Deploy your project, then prompt the agent against the deployed project:
The support value is the agent slug from defineAgent(). With --wait, the response includes the completed session and its messages. Without it, the command returns the queued sessionId and runId immediately. --wait is bounded and defaults to 120 seconds for agents. Choose another duration with --timeout <seconds>. A timeout means the session is still active, not failed. Continue waiting with:
When you call an agent from code and need a typed object back, pass an outputSchema and read result.output — see structured output. Continue the same session by passing its ID:
Agent runtime commands run against your deployed cloud project:
luno agents list is platform/org-level and lists agents in the active organization or project. Prompt and session list/get commands run against the resolved project target. Session cancellation is platform-backed today.
List recent sessions for one agent:
Filter while debugging:
Get details — start lean, then expand:
Use --include gateway,messages,events,trace when you need all available session detail. See the CLI reference for the full command list. Cancel a running cloud session by ID:
Cancellation is useful when an agent is stuck in a long-running tool call or no longer needs to finish. This command uses the active platform context today, so use it for deployed/cloud sessions.

​
Use agents in workflow steps

Agents can be called from workflows and actions with .prompt():
When called inside a workflow, the agent prompt is part of the workflow execution and also creates an agent session. Inspect both the workflow run and the agent run when debugging handoff behavior.

​
Run agents from triggers

A trigger attaches an event source (a schedule, a webhook, or a poll) to an agent, so the agent runs on its own when the source fires instead of waiting for someone to prompt it. Triggers live in src/triggers/; a source exposes .attach(), where you pass the agent and the prompt to run.
src/triggers/morning-check.ts
Webhook and poll sources pass their payload to prompt, so the agent can act on the event that fired it:
src/triggers/new-inbox.ts
Each fire starts a new agent session, just like any other surface. Inspect them in Runs (filter Type to Agent) or from the CLI:
See triggers for the full source-and-attach model, payload filters, and transforms. Agents can also schedule their own runs at runtime instead of waiting for a code trigger. See ephemeral triggers.

​
Use agents via API

You can also prompt a deployed agent over HTTP. The route is asynchronous: it enqueues the prompt and returns 202 with a sessionId and runId to inspect later, rather than waiting for the agent to finish.
Continue an existing session by including its sessionId in the body alongside the new message; send only the new message, not the prior turns. Only the session’s owner (who started it) or a project admin (the project Admin role, or an org owner/admin) can continue it, and only if they may use the agent (access lists); anyone else gets 403. Sessions without an owner, such as Slack or Teams channel conversations, are a project admin’s only. Inspect the result later in History or with luno agents sessions get. This is mainly useful for wiring agents into your own services. For most internal tooling, Slack and the CLI cover what you need.

​
Review agent runs

Every surface that runs an agent creates an agent session you can review later. Open Runs (/history) in the web app and filter Type to Agent. The detail panel shows messages, tool calls, metadata, trace data, timing, and errors. The trace has one span per model call (the model that answered, input/output tokens and model time), so you can see where a slow or expensive session spent its time. When a session is waiting on a human approval, the chat shows the pending call with Approve / Deny; from the CLI use luno agents approvals list|approve|deny. From the CLI, use session commands when you want to inspect runs while debugging:
See agent runs for the full run history view.

​
Next steps

Triggers

Run agents on a schedule, webhook, or poll.

External channels

Connect Slack and route channel messages to agents.

Agent runs

Inspect messages, tool calls, errors, and traces.

Deploy a project

Ship agent changes to the platform.