Weekly Reporting Automation Numbers pulled, variances found, the narrative drafted, sent on Monday
Monday's report writes itself from the metric catalogue — numbers, context, narrative — and waits for one approval.
- Installed for you · one-time$249
- Run for you$197/month
- Custom build · this process$2,000–4,000 one-time
- Starts whenSchedule Trigger (Monday 6am)
Per report with up to 30 metrics from up to five sources. Board decks with custom charts or multi-team roll-ups are a custom build. Custom builds start at $2,000 site-wide; this band is for this process and its integrations.
Weekly Reporting Automation is an automation Agentmelt installs in Google Docs + Slack. The free template is a file you import yourself; the kit ($49) adds the setup guide and prompts. Installed for you costs $249 one-time and is live within two working days of access, with a recorded walkthrough and 30 days of fixes. Run for you costs $197/month, with setup and maintenance included. A custom build of this process is $2,000–4,000 one-time; custom builds start at $2,000 site-wide. No call is needed for any option. Written by Max Zeshut; last revised 2026-09-21.
Reference stack: Claude + n8n. Node names are on each step; the file is under the template.
Founder at Agentmelt
Reviews every build before it goes live; the workflow escalates to a person, never past one.
What is weekly reporting?
Weekly reporting automation assembles the report someone builds every Monday from the same queries and the same template: every metric runs from a catalogue with an owner and a target, the table of this week, last week, last year and target is computed with deltas and flags, the week’s events — releases, campaigns, incidents, holidays — are pulled for context, an AI agent drafts the narrative (the three biggest moves, likely causes tied to named events, what to watch) from the numbers and last week’s approved report, and the owner approves or edits in Slack before it goes out. Every number in the narrative must appear in the table; the agent explains figures, it never introduces them.
- The weekly report is Friday afternoon, every Friday, by hand.
- Two dashboards show two different revenue numbers and both are ‘right’.
- The narrative says what moved and never why.
- A metric’s query broke in March and nobody noticed until June.
- Adding a metric means asking the one person who knows where the queries live.
If two of these are yours, this is the process to look at first. Free audit — or read on.
What it looks like once it runs.
Every team produces a weekly report from the same queries and the same template, and someone spends Monday morning assembling it. The workflow runs the queries, computes the week-over-week and target deltas, has an AI agent draft the narrative — what moved, why, what to watch — from the numbers and last week's report, and posts it for a one-click approval. The person who used to assemble it now edits three sentences.
- Monday 6:00 Every metric in the catalogue is queried: this week, last week, last year, target.
- 6:10 Releases, campaigns and incidents from the week are pulled for context.
- 6:20 The narrative is drafted: the three biggest moves and why, in last week's approved tone.
- 7:00 The owner reviews in Slack and approves; the report goes to the leadership channel and the list.
Reports are late, inconsistent between weeks, and built by copying numbers between tabs. The narrative is either missing or written under time pressure. Nobody compares this week to the target because the target lives somewhere else.
The report arrives at 7am Monday in the same format every week, with every number sourced, deltas against last week and target, and a narrative that names the three things that changed. The owner approves or edits, and it goes out. Leadership reads a consistent document; the team gets Monday morning back.
Trigger, then 8 steps.
Seven of the eight steps run without anyone. Step 06 waits for a person.
Schedule Trigger (Monday 6am)
Run the metric queries
Each metric defined once in a query catalogue (SQL, API call or sheet range) with owner and target; the run executes all of them for the period and the comparison periods.
Assemble the metrics table
Current, previous week, same week last year and target per metric; deltas and flags for metrics outside their tolerance band.
Pull context
Notable events from the week — releases, campaigns, incidents, holidays — from the calendar, changelog and incident tracker, so the narrative can explain moves.
Draft the narrative
From the table, the context and last week's approved report, the agent writes the summary: the three biggest moves with likely causes from the context, metrics off target, and what to watch. Every claim references a number in the table.
Render the report
Template filled with the table, charts generated from the numbers, and the narrative; also a Slack-ready short version.
Approve
Owner reviews in Slack — approve, or edit the doc and approve; edits are kept for next week's prompt context.
Distribute
Posted to the leadership channel and emailed to the list; the doc archived by week.
Maintain the catalogue
Metric definitions, owners and targets live in a sheet; adding a metric is a row, and broken queries alert their owner rather than silently dropping out.
The report arrives at 7am Monday in the same format every week, with every number sourced, deltas against last week and target, and a narrative that names the three things that changed
The report arrives at 7am Monday in the same format every week, with every number sourced, deltas against last week and target, and a narrative that names the three things that changed.
One decision, at step 06. Seven steps ran without you.
Each pattern page explains it in plain words and lists every automation that uses it.
The template is built on n8n (how the n8n AI Agent node works); the same steps run on Make, Zapier or plain code. The tool is chosen to fit your accounts, you own the result, and the template comes in all three formats.
Data it touches
- Data warehouse / databases (BigQuery, Snowflake, Postgres)
- SaaS APIs (HubSpot, Stripe, GA4, Zendesk, Jira)
- Metric catalogue with targets (sheet)
- Calendar, changelog, incident tracker (context)
Guardrails
- Every number in the narrative must appear in the metrics table; the agent cannot introduce figures.
- Causal claims are phrased as likely and tied to a context event; where no event exists the narrative says the cause is unknown.
- The report is approved by its owner before distribution.
- Broken or missing metrics are flagged in the report, never silently omitted.
The catalogue is what makes it reliable
Automated reports break when a query changes or a metric is redefined by someone who forgot to tell the report. Keeping every metric as a row in a catalogue — definition, query, owner, target — makes the report a rendering of the catalogue. A broken query alerts its owner; a new metric is a new row. The narrative is the visible part, but the catalogue is what keeps it correct.
Narrative that respects the numbers
The agent is given the table, the context events and last week's approved narrative, and told that every claim must reference a number and every causal statement must point at an event. That constraint is what makes the draft trustworthy: it cannot say revenue rose because of the campaign unless the campaign is in the context and revenue is in the table. Owners edit tone, not facts.
What it connects to.
| Tool | Role in this workflow |
|---|---|
| n8n | Queries, assembly, rendering, approval, distribution |
| Claude | Narrative drafting |
| BigQuery / Snowflake / Postgres | Metric sources |
| Google Docs + Slack | Report and delivery |
Want this running without building it?
$197/month
We set it up in your tools, run it on our servershost it on our n8n cloud (or deploy it to your own n8n, Make or Zapier), watch it, and fix it when something changes. Setup included, cancel monthly; the automation stays yours if you leave.
$2,000–4,000 one-time
Your systems, your rules, your edge cases. A one-off build delivered into your accounts to keepon Claude and n8n, delivered into your accounts to keep, with documentation and a recorded walkthrough.
Per report with up to 30 metrics from up to five sources. Board decks with custom charts or multi-team roll-ups are a custom build.
Also sold one-time, installed in your own accounts, as part of the executive assistants package and the founders package and the product managers package and the operations managers package and the data analysts package and the financial analysts package and the project managers package — do it yourself $49 · installed for you $249 · done for you $490.
When this becomes a custom build.
The subscription covers the standard version — $197/month, setup and maintenance included. Three things move it to a custom build ($2,000–4,000 one-time), delivered into your accounts to keep. If one of them is you, say so on the audit and the plan prices both.
A board deck with custom charts and commentary rather than a text-and-table report.
Roll-ups across several teams, each with its own sources and targets.
More than 30 metrics or five sources, or a data warehouse that needs new models first.
Running the standard version first is the usual path: the exceptions it logs in the first month are the scope of the custom build, with your own numbers. How custom builds work.
Frequently asked questions.
Can it produce charts?
Yes — standard line and bar charts from the metrics table, rendered into the doc. Custom visualisations are a custom addition.
What if a data source is late?
The report notes which metrics are provisional and re-runs when the source updates, replacing the doc and notifying the owner.
Monthly and quarterly reports?
Same workflow with a different period and template; the narrative compares against the prior period and the plan.
Can weekly reporting automation produce charts?
Yes — charts are generated from the metrics table into the template, plus a Slack-length version with the headline numbers. Board decks with custom charts and commentary are a custom build; the standard report is text, table and standard charts.
What if a data source is late or a query fails?
The metric is flagged in the table with the reason, its owner is alerted rather than the report failing silently, and the narrative says the figure is missing instead of guessing. A metric that fails twice becomes a catalogue task.
Does it handle monthly and quarterly reports too?
The same catalogue runs on any cadence with the comparison periods changed — month over month, quarter over quarter, year to date. Roll-ups across several teams with their own sources and targets are a custom build.
What this blueprint is built on.
Vendor documentation the steps rely on, and the rules the guardrails are written against.
- Google Cloud — BigQuery documentation cloud.google.com/bigquery/docs
- Google — Docs API overview developers.google.com/workspace/docs/api
- Slack — API documentation api.slack.com/docs