What are Agent Automations?
In this article
In this article group
Use Enterpret Agent automations for recurring reporting and follow-up work. Automations can produce a daily report, weekly digest, scheduled summary, or account-health update. Use scheduled Agent automations for reporting setup and connectors for external context and supported actions.
Agent Automations run configured jobs in the background. Depending on the available automation type, a run can start on a schedule or a supported signal. Configure the objective, data scope, permitted tools, and delivery destinations. Reports can be delivered to configured Slack or email destinations; supported connector actions require the relevant connection and permissions.
The same agent, a different mode
In a Session, you work interactively with the Enterpret Agent. An Agent Automation runs a saved job after its configured trigger. Available runtime, tools, Skills, and approval settings can differ, so test the automation itself before enabling it.
An automation can research available feedback and produce a report or use permitted connector actions. Its prompt and selected Skills guide the output. Request source links for counts and quotes, then review the report's evidence, coverage, filters, and period before sharing it.
This is why a good automation often begins life as a Session. Once a question becomes one you ask every week, "what changed in my product area?", it is a candidate to hand off. Prove the prompt works in a Session, then set it to run on its own.
What an automation does with the result
An automation can do two kinds of work with what it finds.
Deliver a report. Configure the available Slack or email destination and request the structure your team needs, such as a summary, comparisons, and representative quotes. Open source links to check the evidence and review the delivered format; citations and coverage can be incomplete. For how to read one end to end, see Reading automation reports.
Act in a connected tool. An automation can use supported tools enabled for its connected account and saved permissions. For example, an available issue-tracker connector may support creating a ticket. Interactive approval-dependent actions need suitable unattended permissions; adding a connector alone does not enable every action.
Example automations
These are example objectives, not a guarantee that every template or action is available. Adapt the scope and check the configured connector permissions, Skills, and delivery settings before enabling a recurring job.
Automation | What it does | Who it's for |
Product Area VoC | A recurring feedback digest for one product area. Leads with what changed, classifies themes as emerging, trending, or persistent, and carries representative quotes and a driver hypothesis for each. | The PM who owns the area |
Account Health Monitoring | A health digest across a configured account roster, whether top accounts, a CSM book, or a segment. Surfaces which accounts are getting louder or quieter, the risks worth escalating, and the wins worth amplifying. | CS and post-sales leadership |
Org-Wide VoC Report | A whole-company readout of what got worse, what got better, and what is new across the full feedback corpus, built for a five-minute read before the recurring review. | Product, support, and CX leadership |
Ticket triage | On each run, finds the new high-priority issues in your feedback and files or tags them in your connected tracker, such as Linear or Jira, so the queue is triaged before the day starts. | Support and triage owners |
CRM account flags | Flags accounts whose feedback signals rising risk and updates the account record in your connected CRM, so the owner sees it in the tool they already use. | CSMs and account owners |
For the full catalog and how to start from a pattern, see Automation templates.
How to get started
Decide what to automate. A good first automation is a question you already ask on a cadence and that the agent has the context to answer on its own, such as a weekly product-area readout or a recurring account-health check.
Create the automation. Set the prompt, the schedule, where the result goes, and the connectors and skills it should use. See Create a scheduled automation for the full walkthrough.
Let it run, then tune it. Read the first few deliveries, adjust the prompt or cadence, and pause or edit it any time from Manage your automations.
To start from a known-good pattern instead of a blank prompt, browse Automation templates for ready-made jobs like the ones above.
What to expect
A trigger starts or queues a run; it is not a delivery deadline. The result is delivered after successful execution and delivery. Completion time varies with the job, dependencies, and service availability. Review run history if a result is missing.
Automation connectors use the configured user connection and saved tool permissions. Source-system access still applies. Check the automation's own configuration rather than assuming it inherits a Session's model, Skills, or approval settings.
Frequently asked questions
Is an Agent Automation a different product from the Enterpret Agent?
Sessions support interactive work; Automations run saved jobs on configured triggers. They can share Agent capabilities, but the available automation type, tools, Skills, permissions, and output settings determine what a particular automation can do.
Where does an automation's output go?
Reports can be sent to the available Slack or email destinations configured on the automation. Supported connector actions can write to a connected tool when the saved permissions allow it. Check the run result and delivery status.
Are the reports cited?
Reports can include links to source evidence and verbatim quotes. Open the links and check the counts, filters, period, quote text, and available attribution before relying on a finding. Missing or incomplete evidence needs review.
Can I see what an automation found without leaving Slack?
With Slack delivery configured, you can read the delivered report in the selected channel or DM. Follow its source links for full context and check the automation's run history when investigating missing output.
How is this different from Enrichment workflows?
Agent Automations are standing jobs the Enterpret Agent runs to research feedback and deliver reports. Enrichment workflows are a separate Enterpret feature.
Have a question about Agent Automations, or an automation you would love to run? Reach out at support@enterpret.com and we will jump in.