Hello Everyone,
Today I am going to share my thoughts on the use of the code interpreter on customer-uploaded files in agent conversations in copilot studio.
Let’s get started.
Your chatbot (agent) can take a user upload during a chat and automatically analyze it using code, then return results within the same conversation.
What actually happens behind the scenes
1. User uploads a file
Examples:
Excel (.xlsx)
CSV (.csv)
Sometimes JSON or text files.
2. The agent receives the file
The file is passed into the conversation as:
System.Activity.Attachments
3. Code Interpreter kicks in
Copilot Studio:
Generate Python code automatically
Runs it in a secure environment
Uses it to:
Read the file
Analyse data
Create outputs
4. The agent responds with results
The bot sends back:
Charts
Tablets
Insights
Summaries
Example flow:
Real example
User says:
“Analyze this sales spreadsheet”
What the agent does:
Reads the Excel file
Groups sales by month
Calculates totals
Generates a chart
Response:
“Revenue increased 18% in Q3. Here’s a breakdown…” + chart
Why this feature is useful
No manual coding needed
Works in real-time conversations
Turns your agent into a data analyst
Great for:
Customer uploads
Business reports
Data exploration
In one sentence
It lets your Copilot Studio agent act like a Python-powered data analyst that can read and analyze files users upload during chat.
Important notes
Best with structured data (Excel, CSV)
Requires:
File upload enabled
Code Interpreter enabled
Has file size and type limits
That’s it for today.
I hope this helps.
Malla Reddy Gurram aka @UK365GUY