Scheduled Agent Automations

Automate reporting with Enterpret Agent. Use scheduled automations for a daily report, weekly report, monthly summary, recurring digest, voice-of-customer report, or account-health update sent to Slack or email. Connectors add external context and supported actions.

How do I set up a daily report for my team?

Use Enterpret Agent and Automations to create a daily report, recurring summary, scheduled digest, or weekly team update delivered to Slack or email.

1. Open Automations and create a scheduled automation, starting from a template when useful.
2. Describe the report: product area or accounts, sources, customer segment, reporting window, comparison period, and desired format.
3. Choose Daily, set the run time, and confirm the timezone. Use a weekly or monthly schedule for less frequent reporting.
4. Choose the Slack or email delivery destination. Attach available connectors and Skills if the job needs context or supported actions in another tool, and review the saved permissions.
5. Run a test, check the evidence and destination, then save and confirm the automation is active. Review run history to check execution and delivery.

Example brief: “Prepare a daily report on [product area] for [team]. Cover the last 24 hours, compare with the previous 24 hours, and highlight new complaints, feature requests, and significant changes. Include supporting feedback links and representative quotes. Deliver the report to [Slack channel or email recipients].” Configure the schedule and destination in the automation settings; a prompt alone does not activate recurring delivery.

See scheduled Agent automations for the full setup and connectors for supported external tools and access. A scheduled time starts or queues work; report arrival depends on successful execution and delivery.

A scheduled automation hands the Enterpret Agent a standing job and a cadence. Write what to analyze, set how often it runs, choose what it does with the result, and the agent does the work in the background and delivers on its own. The result is either a report sent where your team works, in Slack or email, or an action taken in a connected tool, like a filed ticket or an updated record.

This article covers the full lifecycle: creating an automation, starting from a ready-made template, reading what it delivers, managing it after it is live, and troubleshooting when something looks wrong.

Available automation capabilities depend on its type, enabled tools and Skills, connected accounts, and saved permissions. An interactive action that needs a person's approval may not run unattended.

Create a scheduled automation

Building an automation is six steps. The first four are setup, the test run shows the output before you commit, and saving activates the schedule.

Describe the job → Set the schedule → Choose what it does → Attach tools → Test → Save

Worked example. A product manager owns the mobile onboarding area and wants a weekly digest of what customers are saying: what changed, which themes are emerging or persistent, representative quotes, delivered to the team's Slack channel every Monday morning.

1. Describe what to analyze

Open the automation builder and write a prompt describing the job, the same way you would brief the agent in a Session. State the scope, the window, what to compare against, and the shape of the output you want.

Example prompt:

Generate a weekly Voice of Customer digest for the mobile onboarding product area. Cover the past 7 days against the prior 7 days, and check the past 4 weeks for persistent themes. For each significant theme, give the volume count and week-over-week delta, classify it as emerging, trending, or persistent, and include two or three verbatim quotes with source links. Lead with what changed, not what exists. Prefer tables over prose.

A sharper prompt produces a sharper report. If the prompt is rough, use the refine action to sharpen it. The agent rewrites the draft into a fuller brief, tightening the scope, naming the comparison window, and structuring the output. Keep or adjust the result before moving on.

The agent can research the available feedback in your Context Graph. State the sources, filters, period, and evidence you need; review the resulting counts, quotes, and source links rather than assuming every claim is cited.

2. Set the schedule

Choose how often the automation runs and when. A schedule has a frequency, a day, a time, and a timezone.

For the worked example: weekly, Monday, 8:00 AM, set to the team's working timezone.

The schedule determines when a run is eligible to start, not when its report must arrive. Execution and delivery take additional time and can fail or be delayed. Set the schedule with time for review, and use run history to check progress; there is no fixed completion time for every job.

3. Choose what it does with the result

A scheduled automation either delivers a report or takes an action in a connected tool.

• Deliver a report to a Slack channel, a Slack DM, or email. Pick the destination that puts the report in front of the people who need it.

• Take an action in a connected tool. Choose supported actions available to the automation's connected account. Ticket creation, record updates, or messages require the relevant tools and saved permissions; a connected provider does not grant every action.

For the worked example: the team's Slack channel, so the Monday digest is waiting when the team logs on. The recurring question nobody wanted to keep asking now answers itself.

4. Attach connectors and skills (optional)

By default the automation works over your Context Graph and the Enterpret Agent's built-in analytical skills. You can extend it.

• Connectors let the automation read from and act in your other tools, such as Slack, Notion, Linear, and PostHog. Attach a connector when the job needs context from another system, or should write a result back into one.

• Skills are reusable instructions for an analysis method. Where supported, select an available Skill and test whether the result follows the method and scope you need.

Select the connection and tool permissions for the automation. User-connected actions use the configured account's access and must be authorized for unattended execution; interactive Session approval does not automatically grant background permission.

5. Run a test

Before you save, run a test to preview the output. The agent executes the job once, on demand, and shows what a real run produces.

Read the test output as the result's first reader. Check the scope, evidence, quote text, source links, and format. Adjust the configuration and test again. On supported saved automations, the creator can also use Run now to check a change without waiting for the next scheduled run.

6. Save to activate

Save the automation and confirm its status, cadence, connections, permissions, and delivery destination. An enabled schedule can start future runs; successful execution and delivery still depend on access and service availability.

Start from a template

Rather than writing a prompt from scratch, start from a ready-made pattern. A template loads its prompt into the automation builder, already shaped for the job: scope, comparison window, output structure. Adapt the scope to yours, set the schedule and what it does with the result, test, and save.

Ticket triage and CRM account flags are action-in-connector patterns: instead of delivering a report, they write a result back into Linear, Jira, or your CRM. They need the relevant connector attached and authorized.

Use the available catalog as a starting point and adapt the objective to your data and supported tools. Confirm the saved configuration and test the result before relying on a recurring job.

What an automation delivers

An automation produces one of two things when its run completes: a report, or an action in a connected tool.

A report

A report's structure depends on the prompt, selected Skills, and output settings. You can request an executive snapshot, deeper research, comparisons, and linked quotes. Review the actual report and its evidence; every run is not guaranteed to include every section or citation.

The executive snapshot sits at the top and answers one question: what changed since last time. It carries a headline stating the most important movement in the window, the key changes with volume counts and the delta against the prior period, and representative quotes for the findings that matter. It leads with movement, not inventory, classifying themes as emerging, trending, or persistent so a theme that has been loud for months reads differently from one that spiked this week.

The deep dive can include supporting feedback, hypotheses about a change, and the evidence for those hypotheses. Treat causal explanations and confidence assessments as analysis to investigate, rather than proof that feedback alone establishes the cause.

Citations let you inspect supporting evidence. Open available count and quote links and check the underlying records, filters, time window, quote text, and attribution. Evidence or quote coverage can be incomplete; verify unsupported claims before using the report.

Where supported, request a PDF report. Open the exported file and check its contents and source links before sharing. Access to the file and to the linked Enterpret records may differ.

An action in a connected tool

When the automation's job is to act rather than report, the result lands in the connected tool instead. It files or tags a ticket in your tracker, updates a record in your CRM, or posts into the tool where that work already lives. The action runs under the connector's access, the same as in a Session, and is attributable to the person who created the automation.

Manage your automations

Every automation you create lives in one place: the Automations list. From there you find an automation by its name and owner, edit it, pause or resume it, delete it, and review its run history.

The list groups automations by state:

• Active — enabled for its configured triggers. Check run history and delivery status to confirm a particular run completed.

• Paused — not enabled for new scheduled runs. Its saved configuration remains. Resume it to enable future runs on the configured cadence; do not assume missed runs are replayed.

Each row shows the automation's name and its owner, the person who created it. In a workspace where several people run automations, the list holds everyone's; filter to your own to see just the ones you created.

Edit an automation you are permitted to edit to adjust its prompt, cadence, delivery, connectors, or Skills. Changes apply to future runs. Where available, use Run now to inspect a saved change.

Pause an automation to disable future scheduled runs while retaining its configuration. Delete stops future runs and removes it from the active list; this is not a promise that all historical run data is permanently erased.

Review run history to see, per automation, when it ran, whether the run completed, and the result it produced. Run history is the first place to look when a delivery looks wrong: a run that started but did not deliver shows up here, before you re-check the prompt or the destination.

Who can do what

For the scheduled automation settings described here, editing is reserved for its creator. Owners and Admins can manage pause, resume, and deletion subject to the available item controls. Roles do not override creator-only connector settings or guarantee access to every Session.

Troubleshooting

Most automation problems trace back to one of four things: a run that errored, a result that never reached its destination, a connector that lost access, or a prompt that asked for more than one run could carry.

Two checks resolve a large share of issues first:

1. The automation is Active. A paused automation does not run and produces nothing. Confirm the one in question shows as Active rather than Paused.

2. Check run history after the scheduled time. A queued or running job may need more time; a failed run or delivery needs investigation. The schedule is not a fixed report-arrival deadline.

A run failed or errored. Open its run history and inspect the recorded error. Check the configured connections, permissions, scope, and destination. Correct the identified issue and test again; do not assume every failure is transient or caused by prompt size. Contact support if the cause is unclear or failures continue.

A report did not arrive. The automation ran, but no report showed up where you expected. Confirm the delivery destination on the automation is the channel or person you expect, since a report sent to the wrong place looks like one that never arrived. For delivery to a Slack channel, confirm the Enterpret Slack app is present in that channel, because delivery to a channel the app has not been added to will not land. Add the app, then test.

A connector lost access or authorization. An automation that reads from or writes to a connected tool depends on that connector staying authorized. OAuth sessions can lapse, an admin in the connected tool can revoke access, or your own access in the tool can narrow. Open the Connectors panel, check the status of the connector the automation uses, reconnect or re-authorize it by signing in again with your own account, and confirm your account still has the access the automation needs, for example membership in the target Slack channel or visibility into the Linear project. Then test.

A prompt was too large or the output was truncated. A run can complete but return less than expected: a report that stops partway, a table that cuts off, an analysis covering a narrower slice than the prompt asked for. This usually means the job asked for more than a single run could carry. Narrow the scope to one product area, one account roster, or a single window rather than the whole corpus at once, and bound the output by asking for representative quotes rather than all of them. If wide coverage is needed, split it into several automations, each scoped to a slice. Tune at the test stage until a single run returns the complete report.

How to escalate. Most cases above resolve yourself. Contact support when the problem outlasts those fixes: runs that keep failing after a narrowed prompt and confirmed connector access, a report that still truncates despite a focused prompt, or anything you cannot diagnose from the run history. Email support@enterpret.com with the automation name, what you expected versus what happened, the run time in question, and the delivery destination or connector involved. The more precisely you can point at the failing run, the faster the team can trace it.

---

Have a question about scheduled automations, or one you would love to run? Reach out at support@enterpret.com and we will jump in.