docs / getting started
getting started
what you're working with
runshift gives you a three-panel control tower for your AI agents.
on the left is the roster — every agent in your current workflow, their model, status, and what they've cost so far.
in the center is the deck — your operational view. outcome cards summarize what's happened: total runs, interrupts, changes made, total cost. below that is the execution view for the active workflow.
on the right is relay — your orchestration agent. this is where you direct agents in plain language, see live output as agents run, and handle trust gates when they fire.
adding your first agent
there are two ways to add an agent to your roster.
build an agent
use the wizard to create a native agent inside runshift. you define the identity, task, model, gate policy, skills, and schedule. runshift hosts and runs it. click the plus button in the roster to start.
connect via AMP
register an external agent using the Agent Message Protocol. your agent runs wherever you want. it signals runshift on every run using a per-agent API key. runshift tracks status, cost, and gates without touching your infrastructure.
relay commands
type commands into the relay chat panel to control agents. relay understands plain language, but these patterns work reliably:
run [agent-name]
triggers an agent with default behavior.
run [agent-name]: [input]
triggers an agent with a specific input.
stop [agent-name]
interrupts a running agent and marks the run as stopped.
examples:
run growth
run outreach: Jane Smith, Acme Corp
stop rover
trust gates
when an agent is about to take a consequential action, runshift interrupts execution and fires a gate.
you'll see an amber banner in the deck panel with the agent name, the proposed action, and a summary of what it's about to do. you can approve or deny.
gates also fire to Slack — you'll get a message in your configured channel with the draft content visible and approve/deny buttons that link back to the dashboard. you don't have to be at your desk to stay in the loop.
every gate decision is written to the audit trail. approvals, denials, and the content at the time of the decision — all immutable, all queryable.
cost tracking
every agent run tracks tokens in, tokens out, and cost in USD. cost is calculated at the model's live rate and written to the database on gate approval.
you'll see per-agent cost on each agent card in the roster. total cost across the workflow appears in the outcome cards on the deck.
costs are displayed to four decimal places — $0.0012, not $0.00. you're running infrastructure. precision matters.
next