Why I prompt AI to write at a 7th-grade level
I prompt AI to write at a 7th-grade level by pinning it to ELA7, the US Common Core language standard for grade 7, the writing expected of a twelve-year-old. It forces precise, concise sentences and strips fancy vocabulary, so tickets and design docs come out scannable and easy to act on.
I could pick the AI-written tickets out of our backlog without checking who filed them. They were the ones stuffed with words nobody says in a standup ("leverage," "utilize," "robust") around sentences you had to read twice.
Learning the standard taught me something I now believe about all writing: the clearest document I produce is also the best prompt I can hand an AI. Most people work the other way around. They polish prose to sound intelligent and feed the machine sloppy instructions, then wonder why the output reads like a brochure.
Here is the assumption worth challenging: that smart readers want sophisticated prose. They don't. The stakeholder skimming your design doc wants something concise and scannable. The engineer opening a user story wants to grasp it without spending real focus to decode it. Big words spend the reader's attention without buying anything back.
What ELA7 actually says
ELA stands for English Language Arts. The Common Core standards define, grade by grade, what students in the US should be able to read and write. One line in the grade 7 language standard does most of the work for me. L.7.3 asks writers to "choose language that expresses ideas precisely and concisely, recognizing and eliminating wordiness and redundancy." That is a sharper editing instruction than most style guides manage in a chapter.
Why grade 7 and not grade 5? When I was learning something new, I used to ask AI to "explain like I'm 5" (ELI5). It works, but it strips out too much. ELA7 sits between baby talk and an academic paper. It keeps the real content and drops the ornament.
When I switched my learning prompts from ELI5 to ELA7, the explanations stopped feeling like cartoons and started reading like a sharp colleague explaining the thing over coffee.
One detail matters for the objection I get to below: the same standard (L.7.6) expects students to use "domain-specific words and phrases" accurately. ELA7 does not tell you to delete technical terms. It targets the sentence around them.
Why "sounding smart" costs your reader
The mechanism is plain. Every rare word and every nested clause adds parsing cost; linguists call it dependency distance. The reader holds the start of your sentence in working memory until the end arrives to complete it, and fancy vocabulary plus long wind-ups stretch that gap.
I have paid that tax twice over. Refinement sessions ran long because the team had to stop and decode what a fancy PBI was actually asking them to build. And my proposals came back covered in comments from my managers, asking me to clarify points that only read as complex because I had written them that way. Both burned time we did not have.
There is a motive worth naming too. A lot of fancy writing is a status move. We reach for the bigger word because it signals expertise. To anyone who knows the topic it signals the opposite, and to the stakeholder who just needed the decision and the date it signals nothing at all.
How I use ELA7 with AI
I have run backlogs in kanban and scrum since 2015, writing the PBIs (product backlog items) and acceptance criteria that fill them. Since I moved into management at Unity Technologies in 2021, the documents got bigger: technical proposals, engineering strategy, product requirements docs drafted with product managers. I came up as a software engineer first, so I know how it feels to open a fancy PBI and have to decode it before I can start.
When ChatGPT became usable in early 2023, I handed that backlog work to it. The drafts came back too fancy. Identifiable on sight. The trouble was never the length of a ticket; it was the wording. Once I learned the standard, I added one instruction to those prompts.
Rewrite this ticket using ELA7 (US Common Core grade 7) language:
precise, concise, no wordiness, no rare words used for flavor.
Keep all domain terms. Then check the result against ELA7 and
flag any sentence that fails.The change was immediate. Tickets got shorter and plainer. Acceptance criteria read as steps a person could follow instead of clauses in a contract. The backlog became something any engineer on the team could pick up and act on, rather than a document only the author and one or two specialists could parse.
Naming a concrete grade level beats telling the model to "write simply." In my own prompts, "simple" barely changed the output; the model had nothing to aim at. "ELA7" gave it a specific target, and the drafts came back shorter and plainer, usually clean enough to ship without a second pass.
Isn't this just dumbing it down?
Some of my most senior engineers pushed back. The tickets, they said, dumb the work down and lose precision. It is the strongest version of the objection, and part of it is right.
Precision matters. A domain term often carries information that no plain phrase replaces, and stripping it to sound friendly would lose real meaning. If ELA7 meant "delete the technical vocabulary," they would be right to fight it.
It doesn't. The standard keeps the domain terms (that is L.7.6) and goes after wordiness, rare words used for flavor, and sentences built to impress. So I held the line.
The argument I made then is the one I still make: the whole team needs a clear understanding of the work. A version only a chosen few can decode fails that test. Calling the dense version "precision" gets it wrong. It is a gate around knowledge, and gates slow everyone down, including the specialist the next time they are the one onboarding.
Where the rule stops
ELA7 is for documents whose job is to be understood: tickets, design docs, runbooks, status updates, anything a team or a stakeholder reads to act. It is not a law of all writing. A legal contract needs its precise, ugly language. Marketing plays by other rules. A deep technical spec for a specialist audience can run denser than grade 7 and still be the right call. The test is always the reader. If the point is for someone to understand and act, write it at ELA7.
The easiest way to feel the difference is to try it on something you have already written. Take your last ticket or design doc, paste it into an AI tool, and ask it to check the text against ELA7 and flag every sentence that fails. Read what comes back. I wrote this post to the same rule.