We have given all users access to our SQL Transform Builder in Data Cloud. SQL Transforms allow users to manipulate and combine Datasets within NinjaCat using SQL as well as our AI-powered chat. This feature enables users to apply complex transformations, joins, unions and aggregations beyond basic filtering and roll-ups. Learn more about how to use our SQL Transform Builder here: https://docs.ninjacat.io/docs/transform-data-with-sql

For anyone who had utilized our "Unions" combine option, we have retired this feature as it wasn't quite meeting the needs, whereas our SQL Transform Builder allows for much easier handling of complex transformations. Any existing "Union" datasets that had been creating through the Unions feature will still function appropriately.

You are now able to generate PDFs from a convo w/ an Agent, simply by asking the Agent to generate one for you. This is helpful if you're looking for a way to export the Agent's analysis into a shareable format either with teammembers or with a customer.

Requirements for generating a PDF in-convo:
-Code Interpreter must be enabled for that Agent
-Not required, but does seem to work best with the following models so far: Claude 3.7 Sonnet and GPT 4.1.

Over the past week, we have added support for OpenAI's newly released models, which joined our existing options of GPT-4o, o3-mini and Claude 3.7 Sonnet:

-GPT 4.1 - OpenAI's Flagship GPT Model for complex tasks (an upgrade to GPT-4o)
-GPT 4.1-mini - Balanced for intelligence, speed and cost
-GPT 4.1-nano - Fastest, most cost-effective GPT 4.1 model
-o4-mini (w/ Low, Medium and High reasoning levels) - smaller model optimized for fast, cost-efficient reasoning
-o3 (w/ Low, Medium and High reasoning levels) - most powerful reasoning model

With this additional support, we have also revamped our model selection dropdown menu in the Agent Builder, giving you a cleaner, more helpful menu of the NinjaCat-supported model options. With this, we have also made the default model for new Agents be Claude 3.7 Sonnet as we've seen this model work well with many use cases. However it is still up to the user to test out other models with their Agent configuration and select the best for that Agent's task. Learn more about these models through OpenAI's help documentation here:
-Introducing 4.1 Models: https://openai.com/index/gpt-4-1/
-Introducing o3 & o4-mini Models: https://openai.com/index/introducing-o3-and-o4-mini/

We are pleased to announce that we have successfully upgraded our Criteo API to the latest stable version of 2025.01. This update ensures our system remains current and efficient, providing you with the best possible experience.

We are pleased to announce that we have successfully upgraded our Facebook Ads Marketing API to version 21. This update ensures our system remains current and efficient, providing you with the best possible experience.

We are excited to announce that our Google Ads provider now offers four new reports, providing you with deeper insights into your advertising performance:

• Asset Group Report
• Campaign Asset Report
• Performance Max Placement Report
• Search Term Performance Report

With the addition of these new reports, the following new fields have been added:
Asset Group Id
Asset Group Name
Asset Group Primary Status
Asset Group Primary Status Reasons
Asset Group Resource Name
Asset Group Status
Conversion Value Per Cost
Cost of Goods Sold
Cross Device Conversions Value Micros
Cross-sell Cost of Goods Sold Micros
Cross-sell Gross Profit Micros
Cross-sell Revenue Micros
Cross-sell Units Sold
Gross Profit Margin
Gross Profit
Lead Cost of Goods Sold
Lead Gross Profit
Lead Revenue
Lead Units Sold
Orders
Asset Interaction Target
Asset Interaction Target Interaction
Campaign Asset Field Type
Campaign Asset Primary Status
Campaign Asset Primary Status Details
Campaign Asset Primary Status Reasons
Campaign Asset Source
Asset Resource Name
Asset Name
Asset Type
Asset Text
Image Asset Full Size URL
YouTube Video Asset Video ID
Max. CPC
Target URL
Placement Display Name
Placement Type

New Report: Performance Max Placement
With the addition of the new report called “Performance Max Placement”. the following new fields have been brought in:

• Placement Display Name
• Placement
• Placement Type
• Resource Name
• Target URL

How Has Performance Max Reporting Changed or Enhanced?
Performance Max reporting is now more transparent and actionable, thanks to the new placement view. This enhancement allows for a better understanding of ad distribution and enables more informed decisions on campaign adjustments. While this report focuses on impressions, it offers several key benefits:
Clear Visibility:
You can see exactly where your ads are served, giving you a complete inventory of all placements.
Diagnostic Insights:
Even though impressions don’t capture clicks or conversions, they help you identify placements that might be overexposed or underperforming. You can then compare these findings with other campaign metrics.
Optimization Opportunities:
By knowing which placements are getting the most impressions, you can fine-tune your targeting or creative strategy, especially if certain placements don’t drive clicks or conversions.
Enhanced Transparency:
This view offers a clear picture of your ad exposure, which is crucial for maintaining brand safety and ensuring your marketing strategy is aligned with where your ads are appearing.

Note: Since this particular report only supports the impressions metric, if other metrics are needed (and not these specific dimensions), users can apply the Advertising Channel filter for Performance Max on other reports

We have extended the functionality of our automated Triggers- you can now optionally enable Email Notifications for those Triggers. Once a Trigger has completed, the output will still be posted in the Conversation History for review, and an email will also be sent to the listed email recipients (if enabled). The email contains a button that directs the user back to the listed Trigger output in the Agent's Conversation History.

We now support agent-level model selection between a couple OpenAI models. By default, our Agents are driven by GPT-4o, but you now have the option to select o3-mini (with a Low, Medium or High Reasoning level).

GPT-4o is OpenAI’s fast, versatile and high-intelligence flagship model, and is a great option for most Agent use cases. OpenAI’s o3-mini model is a part of their advanced reasoning suite of models which excel at complex, multi-step tasks. We offer all 3 levels of reasoning capabilities for o3-mini where the High reasoning model will think harder, but also take up more time. o3-mini (with Medium Reasoning) is probably a good choice if you would like to use the o3-mini model. Note that prompt adjustments are likely required between the two in order to get the desired output.

Learn more here about o3-mini: https://openai.com/index/openai-o3-mini/

Coming soon: Support for Anthropic Claude 3.7 Sonnet.

We’re excited to announce the launch of our native integration with Agorapulse.

Agorapulse is a native integration within Ninjacat that leverages Agorapulse’s API to aggregate social media performance data from multiple platforms (Facebook, Instagram, LinkedIn, Twitter, TikTok, YouTube).

It delivers two comprehensive reports: an Audience report that provides a daily breakdown of profile activities (e.g., engagements, comments, shares) and a Content report that offers detailed insights on individual posts.

Detailed help documentation will be available on docs.ninjacat.io

We’re excited to announce that our new and improved Smart Connector UI is now available for Snowflake Share and BigQuery! 🎉 This enhancement builds on the recent Google Sheets UI overhaul, providing a faster, more intuitive, and AI-powered workflow for mapping your data in DataCloud.

🔥 What’s New?
1. ✅ Unified UI Workflow: The same intuitive experience from Google Sheets now extends to Snowflake Share and BigQuery, making data mapping easier than ever.
2. ✅ AI-Powered Auto-Mapping: Save time with intelligent suggestions that automatically match your data.
3. ✅ Automatic Dataset Creation: Once mapped, your data is structured and ready to use in DataCloud.
4. ✅ Faster Performance: Optimized backend processing ensures faster load times and a more seamless experience.

This update is live now for all customers with DataCloud enabled! 🚀