Skip to main content
Agents automate recurring workflows (account health digests, renewal-risk follow-up, onboarding check-ins) so your team can spend time on the work that needs a person. For the short definitions of agent, agent run, task, and skill, see Core Concepts. This page is how agents work.

​
What Agents Can Do

You describe the workflow in chat, and Cora builds it. Once you turn the agent on, it runs from the trigger you set: on a schedule, when a signal fires, or when you start it yourself. Agents can do things like:
  • Query your data and send a summary to Slack or email
  • Draft customer outreach when a risk signal is detected
  • Post a weekly digest of renewal activity to your team
  • Send personalized alerts to each account owner about their portfolio
Every agent is created paused by default. It will not run or take any action until you review it and explicitly turn it on.

​
Three Trigger Types

Every agent needs a trigger: the condition that tells it when to run. There are three types: Manual: You start the agent yourself, on demand. Good for workflows you want to run ad hoc, like generating a briefing before a specific meeting. Scheduled: The agent runs automatically on a recurring schedule. For example, every Monday at 9am, or daily at 6pm. You set the frequency, time, and timezone. Event-driven (Signal): The agent runs automatically when Cora detects a specific lifecycle event, like a renewal risk, a stakeholder change, or a competitor mention. These events come from your connected integrations (Salesforce, Gong, Gmail, Slack, and others). See Setting Up Signals for more on how lifecycle event detection works.

​
Autonomy Levels

When you build an agent, you choose how much independence it has. Cora uses three levels: Crawl: The agent surfaces information internally only. It might post a Slack alert or an internal summary, but it never contacts your customers directly. This is the safest starting point. Walk: The agent drafts customer-facing messages (like emails) but sends them through a human approval step first. You or a designated approver review and approve each message before it goes out. This is the recommended level for customer outreach. See How Approval Notifications Work for how approvers are notified. Run: The agent acts fully autonomously, including sending customer-facing messages without approval. Use this for workflows where you are confident in the output and comfortable with no human review. You can always change the autonomy level later by refining the agent through chat with Cora.

​
Where Agents Fit in Cora

Agents sit next to the rest of Cora. Use this as a map; the definitions live on Core Concepts.
  • Core Concepts: short definitions for agent, run, task, skill, signal, and artifact
  • Chat: where you ask one-off questions, and where you build and refine agents
  • Signals: lifecycle events that can start an event-driven agent. Setup is in Setting Up Signals
  • Artifacts: saved outputs agents and chat create (documents, dashboards, surveys, and more)
  • Skills: reusable instructions an agent can run on a schedule
  • Accounts: the customers an agent can run against, one account or the whole portfolio
  • Integrations: the tools agents read from and write to (Salesforce, Slack, Gmail, Gong, and others)

​
The Agents Page

All your agents live on the Agents page. From here you can:
  • See a list of all agents and their current status (Live or Off)
  • Search for agents by name
  • Open an agent to review its configuration, tasks, and recent runs
  • Activate or pause agents
The Agents page is your home base for managing automated workflows. You can also build and refine agents from chat. The two work together.