Reports

A Contextflo report is a prompt with a schedule. You describe what you want to know, pick a cadence, and on schedule an agent queries your connected sources, analyzes the results, and writes a structured report with narrative and charts, delivered to email or Slack.

A report is a prompt, not a saved query

This is the whole model, and the distinction matters. A saved query returns the same rows in a different shape each week. A prompt can notice that a number moved and go looking for why — the part a human would otherwise have to do.

Creating a report

Ask for it in your LLM client. For example:

"Create a weekly report on churn by plan tier with week-over-week comparison."

The agent sets it up and asks you to pick a schedule — daily, weekly, or monthly, at a time you choose, in your timezone.

Writing a prompt worth reading

This is where reports succeed or fail:

• Say what decision it feeds. "Weekly churn report" produces a number. "Weekly churn by plan tier, flagging any tier that moved more than two points, because we're deciding where to focus retention" produces something you can act on.
• Name the comparison. Almost every useful report is a comparison: against last week, the same week last year, or target. A report without one is a number with no opinion about whether it's good.
• Ask it to flag, not just list. "Call out anything unusual and say why you think it moved" turns a summary into an analysis.
• Lean on what you've already defined. The agent uses your saved queries, metrics, and business concepts as context. If active user is defined once in Contextflo, every report means the same thing by it.

Editing and iterating

First drafts are rarely right. Go to the web app to edit the prompt, adjust the schedule, or change delivery. Narrow the scope, add a specific question, or point it at different sources. The next run picks up the change.

You can pause a report or archive it when it's no longer needed.

Delivery: email and Slack

• Email sends the full report body with charts rendered inline — no attachment to download.
• Slack posts to a channel you pick, with tables formatted as native Slack blocks. You can also push any past run to a channel by hand.

Checking its work

Every run includes execution logs: which tools the agent called, what SQL it ran, and how it reached its conclusions. If a number looks wrong, you can trace it to the query that produced it. This is worth doing on the first two or three runs of any new report, then whenever a number surprises you.

Where reports fit

Reports handle recurring questions. Dashboards handle the ones you want to look at on demand. For a full walkthrough, see Creating reports with AI.

Next Steps

• Create live dashboards
• New User Guide (Claude)