Conduit Docs
  • Getting Started
    • Importing Data
    • Connecting Multiple Accounts
    • How To Invite Additional Team Members to Your Account
    • How Does the Trial Work?
    • What's a Table/Data Schema?
    • Number of Sub-Connections
    • Default Time Range for Downloading Data
    • Conduit Data Lake
    • Conduit vs Boost.Space
    • Conduit vs Reportz.io
    • Conduit vs Google Looker Studio
  • Use Cases
    • Use Case: AI-powered Text Extraction
    • Use Case: Track Ad Campaign Performance with Conduit
    • Use Case: Enhancing Project Management with Copilot
    • Use Case: Using Conduit for Financial Analysis
    • Use Case: Use ChatGPT with your data
    • Use Case: Build financial models from raw transactional data and generate P&L statements.
    • Use Case: Marketing data analytics
    • Use Case: Using data science frameworks using your data in spreadsheets Low-Code
    • Use Case: Custom Dimensions for Ad Operations
    • Use Case: Custom dimensions for E-Commerce
    • Use Case: Extract invoices from PDF
    • Use Case: Export data from SaaS applications to your spreadsheet
    • Use Case: Online store and a physical retail locations consolidated
    • Use Case: Pull data from Advertisement platforms to a spreadsheet
    • Use Case: Consolidation of data received as separate files, for example, separate Excel reports
    • Use Case: Names, IDs, SKUs normalization
    • Use Case: Integrating Conduit with a custom CRM using SSO/OAuth2
    • Use Case: Chat Bot for Your Data
    • Use Case: Display Net sales On a Dashboard by Subtracting Ad spend from Total Sales
    • Use Case: Conduit for Healthcare Applications
  • Security & Data Privacy
    • Data Retention Policy
    • How Conduit Complies with GDPR?
    • Security
  • Spreadsheets
    • Writing data to spreadsheets: Overwrite and Update
    • Using Formulas in Spreadsheets
    • The Time Range in formulas
    • The table in the spreadsheet does not start from the first line
  • Conduit for Digital Agencies
    • How to Use White Label
    • What is a Workspace and a Sub-account
    • Use Case: Creating a Dashboard for Two Clients
    • Users in Your Team vs. Sub-Accounts in Workspaces
    • Deleting a Workspace
    • How to Log Into a Workspace
    • How to Buy Additional Workspaces
    • Schedulers in Workspaces
  • Troubleshooting
    • Error codes and how to troubleshoot data-related issues
    • Google Drive Refusing To Connect
    • Why Are my Shopify stats different?
    • Facebook Integration: How to Fix the GraphMethodException Error
  • Copilot
    • Copilot Roles: Data Analyst vs AI Generalist
    • Conduit Copilot vs. ChatGPT – What's The Difference?
    • How to Tune the Copilot
    • Data Sources for Copilot
  • For Developers
    • IP Addresses of Conduit Servers
    • Create an AI Сopilot for your app
    • Manage your AI Copilot users
    • Upload CSV files to Conduit via API (Guide)
  • Integrations
    • Instagram Integration
    • Dashboard Widgets Based On a SQL Connection
    • GA4 Integration Notes
    • Salesloft Integration
    • Self-service and Manual integrations
    • Installing Google Sheets Add-On
    • Slack Integration
    • YouTube Integration
    • HubSpot Integration
    • Conduit integration for Bigcommerce
    • Xero Integration
    • Recharge integration
    • Wrike Integration
    • Zoho Integration
    • Monday.com Integration
    • ActiveCampaign Integration
    • ClickUp Integration
    • FreshSales Integration
    • Google Ads Quality Score
    • Facebook Ads Reach
    • Shopify Net Sales and Returns
    • Gorgias tickets with Spam/Deleted/Auto-Close statuses
    • Looker Studio Connector
  • Workflows
    • Workflows – Adding New Columns
    • Workflows – using the Join by Key block
    • Workflows – using the Union block
    • Workflows – using the Transpose block
    • Workflows – creating a weekly Ad Spend report
Powered by GitBook
On this page
Edit on GitHub
  1. Copilot

How to Tune the Copilot

Sometimes, the Copilot may struggle with identifying particular data within the spreadsheets or the connected data sources. To address such issues, you can supply the Copilot with contextual hints and there would be two ways of doing so. Let’s dive deeper into this.

Fine-tuning the prompt to Copilot

The first way would be to include the additional details in your prompt for the AI. Below is the example spreadsheet, which contains the agency’s partner’s data and comprises the following columns

Partner name
Partner Type
Partner Account Manager
Sales Manager
Status

Innovate Solutions

Reseller

John Doe

Jane Smith

Active

TechConnectors

Agency

Sarah Johnson

Mike Williams

Pending

DataInnovations

Integration

Alex Turner

Emily Davis

In Progress

Digital Dynamics

Reseller

Mark Anderson

Jessica Brown

Active

CloudTech Alliance

Agency

Laura Miller

Brian Taylor

Lost

Example 1

Let’s imagine we want to use the abbreviation PAM (*partner account manager) in our prompt for the AI and our prompt looks something like this:

Who is the PAM for Open AI?

In this scenario, the Copilot may lack the understanding what’s the meaning of PAM and, hence, will fail to provide the correct reply to this question

Let’s try modifying this query so that the AI would have an additional context:

a. Who is the Partner Account Manager for Open AI? b. Who is the PAM for Open AI? (PAM = Partner Account Manager) c. Who is the Partner Account Manager for partner Open AI?

Example 2

In this example, we want to pull the partner account manager for the company called ‘X X Corp Inc.’ Who is the partner account manager for X?

In this scenario, Copilot may struggle with matching ‘X’ with the companies listed in our source data sheet. Let’s modify our prompt, by adding some contextual hint

Who is the partner account manager for X? (Partial names accepted)

Example 3

In this example, we want to pull what projects one of the partner managers (Nick) handles

What does Nick handle?

In the scenario, the Copilot may respond with the request for additional clarifications, regarding Nick. Let’s modify the original prompt, adding the contextual hint:

What partners does partner account manager Nick handle?

Example 4

It's important to remember that it relies on data from your apps and tables. The AI's responses are only as good as the information you provide. To make the most of Copilot, ask specific, data-focused questions

Let’s say we want the AI to pull the data, related to Facebook Ads, using this query

How good are my Facebook Ads?

As you can see, this query lacks the details and the AI fails to respond with a quality reply

Now, let's try this one Retrieve the click-through rate (CTR) data from my Facebook Ads campaign, targeting the US. Please break it down by months

Configuring custom instructions

You can make your contextual hints persistent, by adding them to the 'Instructions' section on the Copilot chat tab. Just click on this button and enter your custom contextual hints

PreviousConduit Copilot vs. ChatGPT – What's The Difference?NextData Sources for Copilot

Last updated 11 months ago