Piqosity now integrates with ChatGPT to AI-grade student essays. Essay prompts are found throughout Piqosity including in standardized test prep courses like TSI, ACT, and ISEE plus our English Language Arts (ELA) courses for grades 5-11. 


Note that the Essay on the ISEE is not scored. Simply use Piqosity's new AI-scoring as a tool for helping students to improve their writing. Click here to read more about the ISEE Essay.


Upon writing their essay and scoring the quiz, students will now see an AI-generated score and specific feedback. As deployed on January 30, 2025, we are currently using ChatGPT 4o-mini.


The AI score is viewable in two places:


  1. Test Results Page by clicking on the expansion carat
  2. Essay View page by clicking to the page showing the essay prompt


Screenshot of Test Results Page


Screenshot of Essay View page


Category Scores


Piqosity will give each essay a score across six categories:


  1. Purpose and Focus - primarily responsiveness to the prompt and overall coherence
  2. Organization and Structure - paragraph usage and transitions
  3. Development and Support - related, specific examples
  4. Sentence Variety and Style - different types of sentence structures
  5. Mechanical Conventions - grammar and spelling
  6. Critical Thinking - following through on a thesis


Each of the six categories receives an AI-generated score of 1 to 9 where 1 is the lowest score and 9 is the highest:


  • Scores of 1, 2, and 3 are below average
  • Scores of 4, 5, and 6 are average
  • Scores of 7, 8, and 9 are above average


Piqosity will justify its score in each category including citations from the student's response. For example, if students receive a low score in the category "Mechanical Conventions," Piqosity may specifically point out mistakes in grammar and spelling.


Overall Score


Additionally, students will receive an Overall Score, which is simply the average of the six category scores. This Overall Score is accompanied by a summary justification of the score including:


  • what the student did well,
  • where they fell short, and
  • specific steps to improve their essay.


Mapping Piqosity Essay Scores to Standardized Test Scores


There are only two standardized courses on Piqosity with graded essays:


  1. TSIA2
  2. ACT Writing


Given the subjective nature of essay scoring, particularly the human-scored ACT essays, it's difficult to provide exact score concordance. Instead, it's better to think of Piqosity's scores as below average, average, and average and use the scores plus explanations to improve your writing. 


However, we provide numerical mapping guidance below.


TSIA2 Score Mapping


The actual TSIA2 Essay receives just one holistic score from 0 to 8 versus Piqosity's 1 to 9 scale. Therefore, to technically match Piqosity's score with the TSIA2, you would take Piqosity's Overall Score and subtract 1. However, our testing reveals a little bit more nuance:


  • Piqosity scores of 1, 2, and 3 are probably too high, so subtract 1
  • Piqosity scores of 4, 5, and 6 probably don't need adjustment
  • Piqosity scores of 6 and 7 are too low and would probably be a 7 or 8 on the TSIA


ACT Writing Score Mapping


The actual ACT writing test receives both an Overall score and a Domain score. Here's how to map ACT's domains to Piqosity's categories:


  • ACT "Ideas and Analysis" = Piqosity Purpose & Focus + Critical Thinking
  • ACT "Development and Support" = Piqosity Development and Support
  • ACT "Organization" = Piqosity Organization and Logic
  • ACT "Language Use and Conventions" = Piqosity Mechanical Conventions + Sentence Variety and Style


Here's how to Match Piqosity's 9-point scale to ACT's 6-point scale:


  1. Piqosity scores of 1, 2, and 3 are equivalent to ACT's scores of 1 and 2
  2. Piqosity's scores of 4, 5, and 6 are equivalent to ACT's scores of 3 and 4
  3. Piqosity's scores of 7, 8, and 9 are equivalent to ACT's scores of 5 and 6


Comparing AI Scoring to Human Scoring


Fourth generation large language models (LLMs) like ChatGPT 4o-mini are powerful tools but they do have limitations. We spent dozens of hours engineering our AI prompts and comparing the results to human-scored essays.


  • Piqosity is a "fair grader" of bad to good essays
  • But a "hard grader" of great essays


The AI is good at providing detailed feedback and providing "ballpark scores" for about 85% of essays that most educators would score as decent to good. However, it's less capable at identifying truly exceptional work according to a student's grade level or recognizing when the student simply didn't try.


Our current implementation does a good job of mitigating for the truly bad essays by feeding specific data from the app to the AI like word-count expectations and examples of what an automatic failure looks like. However, we have been admittedly less successful at getting it to score remarkable essays as 8 and 9 on our grading scale.


As a result of these known limitations, students could probably describe our essay scoring as a "fair grader" for poor to good essays but a "hard grader" of exceptional essays. We will continue to refine our scoring methodology and look forward to even better results in the future by updating to newer LLM versions and further prompt refinement according to specific courses.


Usage Limitations


The number of essays a student can submit for AI scoring is limited by their subscription plan:


  • On-Track - 4 submissions
  • Honors - 30
  • Advanced - 60