Find trends in Ably message history
Ask for a focused review of available message history and get an analysis you can act on.
Trigger
Webhook received
Notis starts this workflow when an external tool or custom backend sends an HTTP request.
Action
Execute Code
Execute python code in a sandbox and return any result, stdout, stderr, and error. use /home/user folder to write/read files. try to not use plt.show() as the code is executed remotely. use files for image/chart output instead.
Why this helps
Reviewing message history by hand takes attention away from the decisions those messages should inform.
- Apply a focused question to available message history.
- Summarize patterns with Python rather than manual scanning.
- Save reusable analysis results in the sandbox.
Setup
Build it in a few focused steps.
- 1Connect Ably and Codeinterpreter once in the Notis portal.
- 2Create an automation in the portal or tell Notis in plain language from any channel.
- 3Describe the channel history source, time period, and trend question in one instruction.
- 4Choose notis_webhook as the trigger and select where run reports should go.
- 5Test with one real request and a representative history sample.
Questions about this workflow
Can this analyze all historical messages in Ably?
Only history that your connected access and instruction make available can be analyzed. Specify the channels and period to include.
Can it infer trends without a baseline?
It can summarize patterns in the supplied data. If you need comparisons against a prior period or baseline, make that data available too.
How do I request a different analysis?
Send another webhook request with the question or period you want, as long as it matches the automation's instructions.
When this happens · Trigger
Do this · Action
Supported Triggers and Actions
Notis builds workflows that link Ably to Codeinterpreter. A trigger fires from one place; an action lands in another.
Ably triggers
Codeinterpreter actions
Recurring trigger
Notis starts this workflow on a schedule, such as daily, weekly, or during business hours.
Create Sandbox
Create a sandbox to execute python code in a jupyter notebook cell. this is useful for agents to communicate, execute code, see output, read files, write files, etc. it's like you own personal computer, but in the cloud. use /home/user folder to write/read files.
Webhook trigger
Notis starts this workflow when an external tool or custom backend sends an HTTP request.
Execute Code
Execute python code in a sandbox and return any result, stdout, stderr, and error. use /home/user folder to write/read files. try to not use plt.show() as the code is executed remotely. use files for image/chart output instead.
Get File
Get a file from the sandbox and returns the file. the files should be read from /home/user folder.
Run Terminal Command
Run a command in the terminal and returns the stdout, stderr, and error code. use /home/user folder to write/read files.
Upload File
Upload a file to the sandbox environment. the files should be uploaded to the /home/user folder.
Connect any two apps with Notis in the middle.
Ably and Codeinterpreter, or any other combination from 1,000+ integrations.
When this happens · Trigger
Do this · Action
Save your first hour today.
7-day trial of any paid plan, with 20$ of usage included.
No card. Works with personal or business Codeinterpreter.