The Scenario
You're a content designer at an e-learning company and the curriculum review is next Thursday. You have 300 rows in your Excel workbook: column A has the reference answer for each quiz question, column B has a student response pulled from the LMS, and column C needs a 0–1 similarity score to flag responses that answer the question but miss the key concept. The scores need to be calibrated consistently — not eyeballed.
The bad version:
- Try a token overlap formula in Excel — realize it gives you word-match percentage, not semantic meaning, so "dogs eat meat" scores 0 against "canines are carnivores" even though they mean the same thing
- Ask engineering to run a similarity model, get told it's Q3 roadmap and today is May
- Score the first 40 rows manually and realize your calibration drifted somewhere around row 25 — your early scores were harsher than your later ones and now the dataset is internally inconsistent
The curriculum review is in a week. Three hundred scores. Your self-scored calibration already broke.
The Easy Way: One Prompt in SheetXAI
SheetXAI is an AI agent that lives inside your Excel workbook. It uses Tisane's semantic similarity engine to score each text pair and write the result directly back into your workbook.
For every row, calculate the Tisane semantic similarity score between the text in 'Reference Answer' and 'Student Response' columns and write the score into a new 'Similarity' column
What You Get
- A 'Similarity' column filled with numeric scores between 0 and 1 for all 300 rows
- Scores reflect semantic overlap, not word matching — "dogs are carnivores" and "canines primarily eat meat" score high even with no shared words
- Rows where either column is blank get a blank in 'Similarity', not a zero
What If the Data Is Not Quite Ready
Some student responses are very short — a single word or a sentence fragment
Calculate Tisane similarity scores between 'Reference Answer' and 'Student Response' for all rows — flag any row where 'Student Response' is fewer than 5 words with 'Too Short' in the 'Similarity' column instead of a score
The columns have extra newlines and formatting artifacts from the LMS export
Before scoring, strip leading and trailing whitespace and remove any line breaks from both the 'Reference Answer' and 'Student Response' columns, then calculate Tisane similarity and write the score into 'Similarity'
You want to highlight low-scoring rows immediately
Calculate Tisane semantic similarity between columns A and B for all 300 rows, write the score into column C, then highlight any row in red where the score is below 0.4
Full pipeline: score, flag outliers, and summarize distribution in one shot
Calculate Tisane similarity scores for all rows, write results to 'Similarity', highlight rows below 0.4 in red, and create a summary table at the bottom of the worksheet showing the count of rows in each band: below 0.4, 0.4–0.7, above 0.7
Scoring, formatting, and the distribution breakdown in a single instruction.
Try It
Get the 7-day free trial of SheetXAI and open any Excel workbook where you need to compare two text columns for meaning, then ask it to score semantic similarity across all rows. To extend this into a full content review pipeline, see bulk text analysis or bulk translation with Tisane. The full Tisane integration is documented at the hub.