Want your Power Automate flows to understand text from Tallyfy form fields, recognize images attached to tasks, or process documents that kick off a process? That’s where AI Builder comes in. It’s a feature inside Power Automate that lets you add AI capabilities to your automations without writing complex code - perfect for making your Tallyfy workflows smarter.
What is AI Builder?
AI Builder lets you add intelligence to your Power Automate flows (and Power Apps) without being a data scientist. You get pre-built AI models ready for common scenarios, plus the ability to create custom models tailored to your specific Tallyfy data.
Here’s the thing - AI Builder shines when you need to interpret unstructured data. Think about emails that should trigger a Tallyfy task, or scanned forms that need to launch a process. It can even predict outcomes based on your historical Tallyfy data. The result? Smarter integrations that actually understand your content.
Types of AI Builder models relevant to Tallyfy
AI Builder offers several models that work great with Tallyfy workflows:
Pre-built Models (Ready to Use): Microsoft trained these models, so you can use them right away with Tallyfy.
Text Recognition (OCR): Pulls text from images and PDFs. Perfect for processing scanned forms that need to feed into a Tallyfy process, making the content available for tasks downstream.
Sentiment Analysis: Detects whether text is positive or negative. Great for analyzing customer feedback from Tallyfy form fields - you can route angry customers to a priority queue instantly.
Key Phrase Extraction: Finds the main points in text. Handy for summarizing lengthy notes from a Tallyfy task.
Language Detection: Identifies which language someone’s using. Essential if your Tallyfy processes handle multilingual communications.
Business Card Reader: Grabs contact info from business card photos, then automatically fills in fields for your Tallyfy “Contact Creation” process.
Receipt Processing: Extracts expense data from receipts, feeding directly into your expense approval process in Tallyfy.
Custom Models (Train with Your Own Data): You’ll need to train these models using your actual data for your specific Tallyfy use case.
Form Processing: Teach the model to understand your invoices, purchase orders, or any forms that kick off a Tallyfy process. Works brilliantly with documents that don’t follow a standard template.
Object Detection: Train it to spot specific objects in images. Think quality control processes where team members upload photos to tasks - the AI can check if all required parts are visible.
Prediction: Uses your historical Tallyfy data to predict future outcomes. For instance, it can estimate whether a process will meet its SLA deadline based on the initial form fields submitted.
Category Classification (Text): Automatically sorts text from Tallyfy tasks or form fields into categories you define. Support tickets logged through Tallyfy? They’ll get tagged automatically.
Using a pre-built AI Builder model: sentiment analysis with Tallyfy data
Want to see this in action? Let’s use AI Builder’s Sentiment Analysis to automatically process customer feedback from a Tallyfy task.
Scenario: Your “Customer Feedback Collection” process has a task where customers type their feedback into a form field. You need to analyze whether they’re happy or upset - then route accordingly within Tallyfy.
Trigger: Tallyfy - “When a task is completed”.
Configure your Power Automate flow to trigger when the specific “Provide Feedback” task in your Tallyfy process is completed. Refer to creating your first flow for trigger basics.
Action: Tallyfy - “Get task details”.
Use the Task ID from the trigger to fetch the full details of the completed Tallyfy task, including the feedback text from the relevant form field (e.g., a field named CustomerFeedbackText).
Action: AI Builder - “Detect the language being used in text”.
Sentiment analysis works best when the language is known. Add this AI Builder action.
Text: Provide the dynamic content CustomerFeedbackText (or your equivalent field name) from the Tallyfy “Get task details” output.
Action: AI Builder - “Analyze positive or negative sentiment in text”.
Language: Use the Language dynamic content output from the “Detect the language being used in text” step.
Text: Again, provide the CustomerFeedbackText dynamic content from Tallyfy.
Value 1: Overall text sentiment (dynamic content output from the “Analyze positive or negative sentiment…” action).
Operator: is equal to.
Value 2: Negative.
IF YES (Sentiment is Negative):
Action: Tallyfy - “Create a task”. Create a new high-priority follow-up task in a Tallyfy “Customer Retention” process assigned to a customer service manager. Include the original feedback and customer details in the new Tallyfy task.
IF NO (and optionally check for Positive):
Action: (Optional) Send a thank you email to the customer if positive.
Action: (Optional) Log the feedback and sentiment score from Tallyfy to a SharePoint list or Excel sheet for trend analysis.
Save and test your flow. Submit feedback through your Tallyfy task and observe the sentiment analysis and subsequent actions. Refer to managing and monitoring flows for testing tips.
Training a custom AI Builder model: form processing with Tallyfy (conceptual overview)
Custom models take more work to set up, but they’re tailored exactly to your Tallyfy data. Here’s how Form Processing handles scanned documents that launch Tallyfy processes.
Scenario: You receive purchase orders as scanned PDFs - all different formats from various suppliers. Each PO has the essentials: PO Number, Customer Name, Items, and Quantities. You’re tired of manual data entry, so you want these to automatically launch your “Order Fulfillment” process in Tallyfy.
In AI Builder (within Power Automate portal):
Choose to create a new Form processing model.
Define the fields you want to extract (e.g., PO Number, Customer Name, ItemDescription, Quantity).
Create collections of documents. Upload at least 5 sample PO documents for each collection (representing different layouts if they vary significantly).
Tag your documents: For each uploaded sample, draw boxes around the data you want to extract and assign it to the fields you defined.
Train your model. Once training is complete, test it and publish it for use in flows connected to Tallyfy.
In your Power Automate Flow:
Trigger: E.g., “When a new file is created” in a SharePoint folder (where scanned POs are saved by an admin or another process).
Action: AI Builder - “Process and save information from forms”. (This might be named slightly differently, like “Extract information from forms”).
Select your published custom Form Processing model.
Form type:PDF Document (or image type).
Form: Provide the file content of the new PO from the trigger.
The outputs of this action will be the extracted fields you defined (e.g., PO Number value, Customer Name value) available as dynamic content.
Map the extracted dynamic content (e.g., PO Number value, Customer Name value) to the corresponding launch form fields in your Tallyfy template.
Licensing and considerations for AI Builder with Tallyfy
Licensing: AI Builder needs its own Power Platform credits - these aren’t included with standard Power Automate licenses. You’ll burn through credits each time your models process Tallyfy data.
Effort: Pre-built models? Easy. Custom models? Plan to spend time collecting sample documents from your Tallyfy processes, tagging them carefully, and training the model. It’s worth it though.
Accuracy: Your custom model is only as good as your training data. Feed it 100 varied examples, and it’ll handle real-world Tallyfy data beautifully. Give it 5 similar samples? Don’t expect miracles.
How AI Builder can make Tallyfy processes smarter
Here’s what happens when you combine AI Builder with your Tallyfy workflows:
Reduce manual data entry: Emails and documents get processed automatically - their data flows straight into Tallyfy form fields. No more typos, no more tedious copying between systems.
Gain deeper insights: Customer comments in Tallyfy tasks? Support notes buried in text? AI Builder analyzes them all, pulling out sentiment and key information you’d otherwise miss.
Intelligent routing: Before data even reaches Tallyfy, AI analyzes it and decides where it should go. Urgent issues get fast-tracked, routine requests follow standard paths.
Proactive actions: Prediction models watch your Tallyfy processes and spot trouble coming. That order heading for a delay? You’ll know 3 days early.
Adding AI Builder to your Power Automate flows transforms Tallyfy from a workflow tool into an intelligent business partner that actually understands your content.
Microsoft Power Automate enables workflow automation by connecting Tallyfy with various business applications through triggers and actions while Tallyfy manages human-centric processes and Power Automate handles system integrations and repetitive micro-tasks.
Microsoft Power Automate serves as an integration bridge that connects Tallyfy’s human-centric process management platform with Microsoft ecosystem applications and other business systems to automate data flows and system-to-system tasks while Tallyfy handles workflow management and process tracking.
Power Automate enables email automation by monitoring shared mailboxes and triggering Tallyfy actions based on incoming emails while handling attachments and sending automated notifications for streamlined workflow management.
This comprehensive guide demonstrates how to create an automated Power Automate flow that monitors your Outlook inbox for specific emails and instantly creates corresponding tasks in Tallyfy using the connector with detailed configuration steps and testing procedures.
