Automation · Operations and reporting
Ask on WhatsApp how much you sold yesterday and from which channel with Coupler.io
Ask on WhatsApp how much you sold yesterday and which channel it came from: an AI agent queries your Coupler.io data sets with SQL.
How do I know how much we sold yesterday and which channel it came from without opening the store or the ads?
You write to your Met "how much did we sell yesterday and which channel did it come from?". The Met finds in Coupler.io the data set of the data flow that brings your store and your ads together, reads its columns and the business context already saved, checks when it was last refreshed and runs the SQL query, which runs on Coupler.io's side. It replies with yesterday's sales by channel and the time of the data. If you clarify something, such as the currency, it saves it for next time, and if you ask for a refresh, the Met refreshes the data flow from its source.
What starts it
When someone asks for it
It starts when someone on the team asks the Met about sales for a day or a period. Each query runs on request; this procedure does not leave a scheduled report.
A manual task: someone on the team runs it with a button, or asks the Met for it in chat.
Who runs it
Sales analytics Met with Coupler.io
This is not a named, seeded Met. It is an internal Met with Coupler.io connected: its work ends when it delivers the figures the query returned, or when it tells you which data set it could not see and why.
Channels: WhatsApp
What you need connected
- Coupler.io Research and analyze
6 steps · 7 tools
The procedure, step by step
Each step shows the tool that runs. They belong to the real connector: if one of them stopped existing, this page would not build.
- 1
Find the data set
The Met searches by name or keyword for the data set that brings sales and ads together. If it does not know which one it is, it lists the data sets in your data flows and tells you which ones exist.
- 2
Read the columns
Before querying, the Met reads the data set's columns, their types, their descriptions and the business context already saved, such as the currency or the rows that do not count.
- 3
Check the data is up to date
The Met checks when the data flow last ran, so it can tell you what time the data it is about to reply with is from.
- 4
Query sales by channel
The Met runs the SQL query that adds up yesterday's sales by channel. The query runs in Coupler.io and only the result reaches the Met, which replies to you on WhatsApp.
- 5
Save what it learned
If you clarify something in the conversation, such as that the currency is COP or that test orders do not count, the Met saves it on the data set as business context, if the admin leaves that action on.
- 6
Refresh if you ask
If the data is stale and you ask for a refresh, the Met refreshes the data flow from its source. It does not do it on its own: only when you ask.
Before you start
What you need ready
The Met solves none of these for you. If one is missing, the automation stops there.
-
A Coupler.io data flow that brings store and ads together
The data flow that brings in your orders and your ads is built in Coupler.io, with its sources authorized. The Met queries what that data flow already imported.
-
The MCP destination on that data flow
The Met only sees the data sets of data flows that have the MCP as a destination. If the data set does not show up, add that destination in Coupler.io.
-
Coupler.io connected in Met
In Met, open Connections → Coupler.io → Connect and sign in with your Coupler.io account. The Met that queries is internal, and your team writes to it on WhatsApp.
The limits
What this automation does NOT solve
Better said here than discovered halfway through the rollout.
-
It does not connect your sources on its own. The data flow is built in Coupler.io; this procedure queries what it already imported.
-
It does not see data flows without the MCP destination. If the data set does not show up, that destination has to be added to the data flow in Coupler.io.
-
It does not change data in your store. Queries read what was imported and do not edit, delete or overwrite rows.
-
It does not make up a sale's channel. The channel comes from the data set's columns; if the data set has no channel column, the answer cannot give it.
FAQ
Questions about this automation
According to your data flow's schedule in Coupler.io. The Met tells you when it last ran and, if you ask, refreshes it from the source.
Because the data flow that brings them in does not have the MCP as a destination. Add it in Coupler.io and the data set shows up.
Each query reads one data set at a time. To combine them, Coupler.io can build a new SQL data set from data sets in the same data flow, a step this procedure does not include.
Keep going
Other automations built on the same tools
Operations and reporting
Turn off on WhatsApp the feature flag that breaks the checkout in LaunchDarkly
How do I quickly turn off a feature flag that broke the checkout without opening LaunchDarkly?
- Starts:
- when someone asks for it
- Steps:
- 5, with 7 real tools
- Needs:
- LaunchDarkly
Operations and reporting
Build a department's higher education report without opening SNIES
How do I pull SNIES enrollment and program figures without going into the portal?
- Starts:
- when the customer writes
- Steps:
- 5, with 5 real tools
- Needs:
- SNIES
Operations and reporting
Build your team's org chart in Lucid on WhatsApp and share it
How do I build my business's org chart without sitting down to draw it?
- Starts:
- when someone asks for it
- Steps:
- 6, with 6 real tools
- Needs:
- Lucid
Operations and reporting
Tell customers on your status page that the store is down, asking on WhatsApp with Better Stack
How do I tell my customers my online store is down without opening Better Stack?
- Starts:
- when someone asks for it
- Steps:
- 6, with 6 real tools
- Needs:
- Better Stack
Want this automation running on your own data?
We will show it to you with your accounts connected, not with a canned demo.