For supplemental materials and differentiation, districts that value accuracy, alignment, and quality turn to Diffit. To illustrate, we gave the same exact prompts to Diffit and Brisk, then scored both outputs against a 20-criterion rubric grounded in WestEd research.
CCSS.MATH.CONTENT.5.NF.A.2 — "Solve word problems involving addition and subtraction of fractions referring to the same whole, including cases of unlike denominators, e.g., by using visual fraction models or equations."
Brisk's worksheet is accurate, cleanly formatted, and even includes estimation tips — credit where it's due. But the standard names visual fraction models, and Brisk's worksheet is text-only; it tells students to “show your work” without leaving room to; and it builds no error-analysis task to push reasoning. Diffit returned three coordinated worksheets — visual models, word problems with estimation, and a misconception-analysis sheet.
CCSS.ELA-LITERACY.RI.5.3 — "Explain the relationships or interactions between two or more individuals, events, ideas, or concepts in a historical, scientific, or technical text based on specific information in the text."
Same NPS source, same standard — and Brisk's RI.5.3 questions are genuinely good (relationships, interactions, connections), with a teacher answer key too. But Brisk never produced the reading those questions depend on: Part 1 is a hyperlink, not a passage — so a student can't do the worksheet without the internet open, Question 4 asks for “an example from the text” that isn’t there, and the key is generic (no Edward Brodess, no Combahee River Raid, no Bucktown store), proving the source was linked, not read. Diffit built the packet from the source: a grade-level passage with the NPS specifics and images, three text-based analysis activities with room to write, and a key that quotes the details.
CCSS.ELA-LITERACY.RH.9-10.2 — "Determine the central ideas or information of a primary or secondary source; provide an accurate summary of how key events or ideas develop over the course of the text."
Brisk's one quote is real and accurately cited, but the “entire excerpt” is a single 40-word sentence — while the standard asks students to summarize how ideas develop over the course of the text (you can’t trace development across one sentence). Brisk’s four vocabulary words (injustice, mutuality, network, destiny) are simply the nouns lifted from that one quote. Diffit built from the whole letter — King’s point-by-point answers to the clergy, the “extremism” and “inevitability” arguments, a vocabulary of concepts from across the text, and a source-grounded answer key that quotes the letter directly.
RI.5.3), releveled to Grade 2
Give Brisk its due — the relevel did a clean job on the worksheet: the questions, the learning goal, and the sample answers all dropped to a natural Grade-2 voice, and the relationship framing held. What it left untouched is the reading. Brisk’s worksheet never had a passage, only a link to the adult NPS page, so the relevel had nothing to lower — a second grader is still pointed at an adult website. A teacher can paste the NPS text in and relevel that separately, but it’s a second pass. Diffit relevels the whole packet at once, passage included — rewritten for Grade 2 with the names, dates, and story intact.
It's important to note that Diffit didn't score perfectly on the rubric in a few areas, too. In the 2nd-grade rewrite, one prompt oversimplified a part of the reading; a Spanish translation used two different words for the same term ("pantanos" (swamps) in the reading passage but "marismas" (marshes) in one of the analysis activities); and the high-school lesson skipped images that may have helped with scaffolding. These are noted in the full analysis below.
The difference: a teacher can fix any of these inside Diffit in seconds — swap an image, edit a word — right in the packet. In a chatbot, that means re-prompting and hoping the rest of the lesson survives.
The side-by-sides above are just examples. Here's the full tally — every score is backed by cited evidence in the full evaluation.
| Prompt | Diffit | Brisk |
|---|---|---|
| 5th-grade ELA · Harriet Tubman | 17 / 17 | 7 / 17 |
| 5th-grade Math · Fractions | 16 / 17 | 8 / 17 |
| 9–10 ELA · MLK Letter | 17 / 17 | 5 / 17 |
* Each result is scored only on the criteria that apply to it, so a denominator can be under 20. Non-applicable criteria are marked N/A.
Both tools' materials were graded against the four things WestEd found teachers care about most: accuracy, standards alignment, ease of use, and meeting student needs — 20 criteria in all. Every score has cited evidence. All source files and the exact prompts are available upon request, so any district can rerun the comparison.
Grounded in WestEd's study, "How Teachers Judge the Quality of Instructional Materials: Selecting Instructional Materials, Brief 1 – Quality (Bugler et al., 2017)", and the Diffit Quality Constitution.
To see the full scoring, read the Diffit Quality Constitution, or learn more about Diffit, contact schools@diffit.me.