You're Probably Sceptical. Good.

If you're a business school lecturer reading this, you've likely had the same reaction most academics have when someone says "AI essay feedback": a mix of wariness and mild irritation.

You've spent years developing the judgement to assess strategic thinking, to distinguish between a student who can apply Porter's Five Forces with genuine insight and one who merely fills in a SWOT grid like a checklist. The idea that software could do what you do is, at best, implausible.

I'm not going to argue with that. EssayHero can't do what you do.

What EssayHero Can Do

But it might be able to do something useful alongside what you do. And if you're going to consider recommending it to your students, you deserve to know exactly how it works, what it looks for, and where it falls short.

This post is that explanation.

Background: Why This Exists

I'm Joseph Lin. I've been marking essays for over twenty years, from primary school through to PhD dissertations.

I built EssayHero originally for HKDSE students in Hong Kong who weren't getting enough feedback between assignments. It's free, it has no commercial aims, and it's expanded to university level because lecturers asked for it.

A business school colleague asked me two pointed questions:

• "How do you assess whether a student actually understands a framework versus just name-dropping it?"
• "Can the AI tell good strategic analysis from description?"

This post answers both.

How University Assessment Differs from Exam-Board Marking

Standardised Exams: A Known Baseline

EssayHero's original configurations were built for standardised exams: HKDSE, IELTS, Cambridge IGCSE.

These exams have published marking criteria, official band descriptors, and examiner-graded exemplar essays. The AI's job is to apply those criteria consistently. The criteria are fixed, the mark schemes are public, and calibration is straightforward because you can validate against official scores.

University Essays: A Different Problem

University business essays are a different problem. There is no single published rubric that every business school uses.

Expectations vary by institution, by module, and by lecturer. A first-year introduction to management essay and a final-year strategic analysis case study require fundamentally different skills. The "right answer" isn't a band on a scale but a demonstration of analytical thinking applied to real business problems.

Building for Real Business Assessment

So building a university business configuration meant starting from different assumptions.

Instead of replicating an exam board's mark scheme, we built assessment criteria around what experienced business school lecturers consistently look for across institutions:

• Quality of strategic analysis — using frameworks to generate insight, not just fill grids
• Use of evidence and research — integrating academic literature and real-world data
• Structure of argumentation — clear recommendations grounded in analysis
• Precision of academic business writing — appropriate terminology and professional register

These aren't generic. They're informed by how business and management is actually taught and assessed in higher education.

Scoring Scale: Percentage-Based Marking

The scoring scale is different too. Instead of HKDSE's 1-7 per criterion or IELTS's 0-9 bands, business essays are scored 0-25 on each of four criteria, totalling 0-100.

This mirrors the percentage-based marking that most university business faculties use.

What the AI Actually Looks For

The four criteria are:

1. Analysis and Strategic Thinking
2. Research and Evidence
3. Structure and Communication
4. Academic Writing

Each has five bands with detailed descriptors. Here is what they measure.

1. Analysis and Strategic Thinking

This criterion assesses whether the student can move beyond description to genuine evaluation.

The AI is tuned to recognise the purposeful application of business frameworks — SWOT, PESTLE, Porter's Five Forces, Value Chain analysis, and others — but critically, it distinguishes between mechanical application (filling in a grid) and analytical application (using a framework to generate insight).

What earns high marks:

• Weighing competing factors and identifying trade-offs
• Exploring strategic implications with depth
• Demonstrating awareness of real-world complexity
• Original thinking or a distinctive analytical lens (21-25 band)

What earns low marks:

• Unsupported opinion without evidence
• Unstructured description without analysis
• Framework name-dropping without insight

2. Research and Evidence

This criterion evaluates how the student uses sources to build their argument. This includes academic literature, industry reports, company data, and real-world case examples.

Instead, it assesses how evidence is used:

21-25 band (Excellent):

• Critical engagement with sources
• Comparing perspectives across research
• Synthesising evidence into persuasive argument
• Citations integrated analytically, not decoratively

11-15 band (Adequate):

• Reliance on textbooks with limited independent research
• Basic source integration without critical engagement

3. Structure and Communication

This criterion looks at the professional quality of the essay's organisation.

Key assessment points:

• Does the introduction frame the question precisely?
• Does each paragraph develop a distinct point with effective transitions?
• Do conclusions draw together the analysis into well-grounded recommendations?
• Does the essay read as coherent business communication?

For recommendation-based essays, it assesses whether recommendations flow logically from the analysis or appear disconnected.

Business writing values efficiency of communication. This criterion rewards clear signposting, purposeful paragraph development, and actionable conclusions.

4. Academic Writing

This criterion covers the mechanics of professional business communication.

What it assesses:

• Accuracy of business terminology — not just using terms like "competitive advantage" or "market segmentation" but using them correctly
• Appropriate academic register — professional tone without excessive formality
• Sentence variety — mix of simple and complex structures
• Grammar and clarity — technically correct and easy to follow

What it rewards:

• Concise expression of complex ideas
• Precise vocabulary without jargon overload

What it penalises:

• Unnecessary verbosity and jargon

The Feedback Tone

One deliberate choice worth mentioning: the AI provides feedback in the voice of a collegial peer reviewer, not an authoritative examiner.

Examples:

• "Consider strengthening this section" rather than "You should have included"
• "The argument could be extended by" rather than "You failed to"

This was intentional. Students respond better to constructive suggestion than to top-down correction.

The feedback is more useful when it points toward specific improvements rather than merely cataloguing faults.

What We Can't Do

This is the section that matters most, so I'll be direct.

We Can't Verify Financial Data or Market Statistics

The AI doesn't know whether the market growth rate a student cites is accurate, whether a company's reported revenue figures are correct, or whether a particular industry statistic is current.

What it can do:

• Assess whether quantitative evidence is used effectively in the argument

What it can't do:

• Verify whether the numbers themselves are real

If data accuracy matters (and in business, it always does), that's something a human needs to check.

We Can't Assess Real-World Feasibility

The AI can evaluate whether a recommendation is logically grounded in the analysis and well-argued, but it doesn't have the domain expertise to know whether a proposed market entry strategy would actually work.

What it evaluates:

• Whether the argument is well-structured
• Whether recommendations flow from the analysis

What it can't evaluate:

• Current regulatory conditions
• Competitive dynamics
• Organisational constraints
• Whether the strategy would succeed in practice

We Can't Verify Case Study Accuracy

When a student writes about Netflix's pivot to streaming or Tesla's vertical integration strategy, the AI can assess whether the case is analytically integrated and supports the argument.

But it cannot confirm that the specific details — dates, figures, market shares, strategic decisions — are factually correct.

We Can't Replace Summative Marking

EssayHero's scores are indicative, not definitive.

If you give an essay 58 and EssayHero gives it 72, you are right.

The AI is applying generalised criteria without knowing:

• Your module's specific expectations
• Your institution's marking conventions
• The particular learning outcomes you've set

The scores are useful as a rough benchmark for students working between drafts, not as a predictor of the mark they'll receive.

This Is Formative, Not Summative

The tool is designed for the gap between drafts, not for final assessment.

It's useful in the same way that a study group is useful:

• It gives you another perspective
• It catches structural weaknesses
• It forces you to articulate your argument clearly

But it's not a marker. It's a practice partner.

What It Is Good For

After that list of limitations, you might reasonably ask: so what's the point?

Faster Iteration Between Drafts

The point is faster iteration.

A student working on a strategic analysis case study at midnight can:

1. Submit a draft
2. Get paragraph-by-paragraph feedback on their framework application
3. Identify where their PESTLE analysis is mechanical rather than analytical
4. Revise it
5. Bring a better draft to your seminar

That revision cycle is where the learning happens. Most students don't get enough of it because feedback is scarce and slow.

Consistent Criteria Application

The criteria don't change based on workload or mood.

If a student submits the same essay on a Monday and a Friday, the feedback will be consistent. That's useful for building a student's understanding of what the criteria actually mean, even if the scores themselves are rough estimates.

Examples of what students can identify and fix:

• Recommendations lack grounding in the analysis
• Case examples are superficial rather than analytically developed
• Framework application reads like a checklist rather than a tool for insight

These are all things a student can fix before submission.

Strictness Calibration

The strictness modes let students calibrate their expectations:

• Lenient mode — AI gives benefit of the doubt and focuses on strengths
• Baseline mode — Standard marking criteria applied
• Harsh mode — Rigorous standards where scores of 21-25 are reserved for genuinely excellent work

A student who scores well on harsh mode has reason to feel confident. One who struggles on lenient mode knows there's significant work to do.

Not a Replacement

None of this replaces your feedback.

But it might mean that when students do come to you, they've already caught the structural and argumentative weaknesses they could have found themselves.

Full Transparency

Open Source Assessment Criteria

The complete assessment criteria, the detailed band descriptors, and the full instructions that the AI receives are published in the source code.

EssayHero is open source under AGPL-3.0. You can read every line of the prompt configuration and decide for yourself whether the standards align with what you'd expect.

Privacy and Data Handling

Essays are processed and discarded. They are not:

• Stored permanently (unless student is logged in and chooses to save)
• Used for model training
• Accessible to anyone after the feedback is generated

If a student is logged in, they can choose to save their analysis to their own account, but that's opt-in.

Try It Yourself

EssayHero is free. No account required.

Test It With Your Own Sample

If you want to see what the feedback looks like on a business essay:

1. Go to essayhero.app/?exam=uni-business
2. Paste a sample essay
3. Read the output
4. Decide whether it's something worth sharing with your students

Your Feedback Matters

If you think it could help them iterate faster between drafts, share it.

If you think the criteria don't align with your expectations, or the feedback isn't useful, I'd genuinely like to hear why. Email hello@essayhero.app.

I built this to help students write better. If it can do that for your students, I'm glad. If not, I understand.

EssayHero is free, has no commercial aims, and is built by a Hong Kong teacher for students worldwide. Questions? Email hello@essayhero.app.