Automation · Operations and reporting
Ask on WhatsApp how a Statsig experiment is going and what changed in it
Ask on WhatsApp how a Statsig test is going: an AI agent brings the experiment's results, metrics and change history.
How do I know whether my Statsig test is winning without opening the console?
You write to your Met "how is the new checkout test going?". The Met checks which Statsig project it is connected to, searches the experiment by name, opens its details and brings the overall results between the control and test groups. If you ask about a metric, it opens its definition to explain what it measures, and it checks the audit log in case someone changed the experiment recently. It replies with a summary in the chat. Everything is read-only: the Met does not stop or change the experiment in this procedure.
What starts it
When someone asks for it
It starts when someone on the team asks the Met on WhatsApp about an experiment. Each check runs on request; the Met does not watch the test on its own.
A manual task: someone on the team runs it with a button, or asks the Met for it in chat.
Who runs it
Internal Met that checks your Statsig experiments
This is not a named, seeded Met. It is an internal Met with Statsig connected, for the owner or the agency that measures product tests: its work ends when it sums up the results and what changed in the experiment.
Channels: WhatsApp
What you need connected
- Statsig Automate and collaborate
5 steps · 6 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
Confirm the connected project
The Met asks for the connection context to know which Statsig project it is in and which permissions it has, before searching anything.
- 2
Find the experiment
The Met searches the experiment with the name you gave it and fetches the matching result in full, so it does not confuse it with a similar test.
- 3
Bring the results
The Met opens the experiment's details and asks for its overall results between the control and test groups, with the main metrics.
- 4
Explain the metric
If you ask what a metric means, the Met brings its definition from Statsig and explains what it measures based on that definition.
- 5
Check recent changes and reply
The Met checks the project's audit log to see whether someone changed the experiment recently and replies with the summary of results and changes.
Before you start
What you need ready
The Met solves none of these for you. If one is missing, the automation stops there.
-
Statsig connected in Met
In Met, open Connections → Statsig → Connect and sign in to Statsig. The organization must have Personal Console API Keys enabled for your role.
-
An internal Met on WhatsApp
Assign the connector to a Met that only serves the team, not the one that talks to customers, because the same connection brings actions that change gates and experiments.
-
The experiment names in the instructions
Write in the Met's instructions what your main experiments are called so it always searches for the right one.
The limits
What this automation does NOT solve
Better said here than discovered halfway through the rollout.
-
It does not decide for you whether the test won. The Met shows you the results Statsig computes; launching or stopping is your team's decision.
-
It does not alert you on its own when an experiment changes. The check starts when someone asks the Met.
-
It does not stop or edit the experiment. The update actions are in the listing, but this procedure does not use them.
-
It does not see projects the connected account cannot access. Statsig's permissions decide what the Met can read.
FAQ
Questions about this automation
This procedure does not. The Statsig listing has the experiment update action, which needs write access and a confirmation; if the admin leaves it on, you ask for it in another instruction.
Yes. Every tool this procedure uses is a read tool, and Statsig lets a read-only user use them.
The Met searches by name and opens the matching result. If in doubt, write the experiment's exact name or ID in your question or in its instructions.
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.