Participant Layer Input

Assessdo begins with direct participant engagement, integrating both objective context and lived experience. It gathers inputs through regular and characteristic ongoing reflective check-ins which obtain participant thoughts, self-identified perceptions and participant-validated emotional insights.

Data processing & ai reading layer

Assessdo takes an open approach to data, enabling unified access without requiring full data migration. Users can easily upload information through simple formats like PDF or CSV files.

By aggregating and interpreting data from multiple validated sources including profiles, session notes, observations, performance metrics, emotional insights, and historical check-ins, Assessdo ensures accurate, connected insights that grow stronger over time.

Qualitative Insights

Assessdo connects the why and how behind each participants experience. It highlights where emotions start, where they’re headed, and how they connect, giving a clear, complete picture of each student.

  • Qualitative inputs (stats, notes, observations) are analyzed to identify emotional sources, emotional connections, and targets of emotion, transforming unstructured language into interpretable insight.

Human-Validated ai for bias reduction

Assessdo is designed to work with humans—not over them. It continuously validates its reasoning with users to ensure emotional interpretations are accurate, culturally aligned, and grounded in real-world feedback. By reducing bias and aligning recommendations with each person’s natural emotional environment, values, and lived experience, Assessdo delivers insights that are both ethical and practical.

Session Insights

  • Pulls relevant data reference points from self-check-ins, performance metrics, and qualitative inputs.
  • Assesses the relevance and alignment of each data point in relation to the question posed.
  • Connects recommendations to historical patterns, identified goals, and participant-specific motivators or obstacles.
  • Track changes over time across emotions, goals, and self-awareness patterns.

AI-Prompt Guide

Session Insights Generated Insights Qualitative Insights
Data Pulled

Characteristic Check-Ins

System Instruction

“Self-reported behavior marker”

(e.g. What had Brian feeling good about his behavior today according to his self-reported behavior markers?)

Data Pulled

Connections

System Instruction

“Source of Emotion” / “Target of Emotion”

(e.g. What have been the positive sources or targets of emotion for Baye based on the Connections data?)

Data Pulled

Session Information

System Instruction

“Key Session Information”

(e.g. What key session information do I need to flag as a concern for Baye?)

Data Pulled

Regular Check-Ins

System Instruction
Data Pulled
System Instruction
Data Pulled
System Instruction
Display Label
System Instruction
Display Label
System Instruction

“

Display Label
System Instruction
Display Label
System Instruction
Display Label
System Instruction
Display Label
System Instruction