Internal reference

Identity.

Positioning, voice, and visual identity for Evalgist. Code sources from @evalgist/content-style and @evalgist/design-system.

Evalgist·Brand·v0·Geist Sans · Geist Mono

01Proposition

Evidence, not verdicts.

The brand promise. Every external surface stays beneath this ceiling.

The promise

Evalgist builds AI tools that help professionals evaluate a batch of structured documents against one criteria set — faster, more consistently, and with evidence. The human remains the decider; the AI supplies substantiation, not conclusions.

Three load-bearing clauses. Large volumes of structured documents: resumes, exam answers, proposals — not arbitrary conversation. Faster, more consistently, with evidence: three measurable promises. Substantiation, not conclusions: the product ceiling is set deliberately below "the AI decides."

02Audience

Professionals reviewing a batch.

Professionals evaluating documents against one criteria set. Academic work is the first outreach channel, not the product boundary.

For

Primary audience

Hiring managers and selection panels evaluating a batch of applications against the same criteria.

For

Segments

selection committees, hiring managers at SMBs and non-profits, academic and public-sector panels, grant and admissions reviewers

For

Origin, not boundary

Academic hiring is where the workflow was first built and proven. Treat it as origin and channel, never as the only intended user in marketing copy.

Not for

Deep ATS integration

teams that need deep ATS integration

Not for

Automated decisions

fully automated decision pipelines

03Voice

Sober. Confident. Dry.

Short sentences. Reference voice: The Economist, not TechCrunch. English even in Belgian context. The brand does not joke about regulators.

Prefer

evidencequoted evidenceone criteria setbatchevidence trailaudit trailexportable recordevaluateshortlistgradeconsistentfairfasterper criterionper candidateper answerreviewdecideverifyprofessionalhuman decision

Avoid

revolutionarygame-changingunleashsuperchargeseamlesslyeffortlessly10xcutting-edgenext-generationdisruptivebias-freeobjective AIfully compliantAI sparklemagical

Do say

Compare everyone against the same criteria. Shortlist with the evidence open, and keep a record of the decision.

Don't say

Supercharge your hiring with revolutionary AI-powered screening that seamlessly shortlists top talent.

Why: Names the workflow, the evidence, and the record. No superlatives or startup enthusiasm.

Do say

AI suggestion. Review the cited evidence, then make the decision.

Don't say

Our AI makes smarter hiring decisions for you, so you don't have to.

Why: Labels the suggestion and the human decision as different states.

Do say

Every match cites the resume line it rests on — or says that no quote was found.

Don't say

Trust our AI — it's been trained on millions of documents.

Why: Authority comes from visible evidence, not model scale.

Forbidden by default: emoji, exclamationMarks, superlatives, startupEnthusiasm, ironyTowardRegulators. On AI positioning: say "AI-assisted evaluation", not "Powered by AI". Name the function, not the marketing claim.

04Naming

Evalgist is the brand. Products take suffixes.

Never sub-brands with independent identity. First mention uses the full name; second mention may shorten to the suffix.

Pattern

Evalgist <Product>

First mention

Evalgist Shortlist

Second mention

Shortlist

Portfolio: Evalgist Shortlist · Evalgist Grade · Evalgist Extract.

05The mark

Eight cells of ink. One cell of tone.

No outline, no frame, no highlight. The absence is a quiet member of the field, not a UI state.

Standard · ≥24 px · slate-300

Small-size · <24 px · slate-400

Inverted · dark surfaces

Single-color · print, stamp, etch

06Size ladder

The sizes it will actually be seen at.

Above 24 px the tonal cell renders at slate-300. Below 24 px it lifts automatically to slate-400 so the cell stays legible.

128 px

64 px

32 px

20 px

16 px

07Lockups

Mark, wordmark, and their agreed proportions.

Geist Sans 600. Primary wordmark ≈ 0.78× mark size; product suffix 10 px uppercase with 0.15em tracking, stacked beneath. Gap between mark and wordmark is optical.

Evalgist

EvalgistShortlist

EvalgistGrade

Evalgist

Scaling

Full lockup at markSize ≥ 24. In tight contexts (nav, breadcrumb, dense header) where mark size would fall below 24, use EvalgistWordmark — the wordmark alone at the desired size. Below is the wordmark at 15 px, the size used in the landing-page nav.

Evalgist

08Canonical values

Authoritative specification.

These values are the source of truth. Everything else is a derivation.

Ink	`#0f172a` — slate-900. Eight filled cells and the wordmark.
Tonal — standard	`#cbd5e1` — slate-300. Tonal cell at rendered sizes ≥ 24 px.
Tonal — small	`#94a3b8` — slate-400. Tonal cell at rendered sizes < 24 px (automatic lift).
Tonal — dark	`#94a3b8` — slate-400. Tonal cell on dark surfaces at all sizes.
viewBox	`0 0 100 100` for all standard renderings.
Cell size	`28u` — 28% of viewBox.
Gutter	`3u` — gap between cells.
Margin	`5u` — outer margin on all sides.
Cell positions	Columns at x=5, 36, 67. Rows at y=5, 36, 67.
Tonal cell	Middle-right. Position `(67, 36)` in viewBox coordinates.
Favicon geometry	16×16 pixel-tuned. Cells 4×4. Gutters 2 px.
Rendering	`shape-rendering="crispEdges"` — mandatory.
Clear space	One cell width (≈ 11% of symbol width) on all sides.
Minimum size	12 px digital. 8 mm print. Below this, use the wordmark alone.
Wordmark font	Geist Sans, weight 600.
Wordmark size	Primary: ≈ 0.78 × mark size. Product: ≈ 0.67 × mark size. Optically balanced.
Wordmark tracking	`-0.03em` primary. `-0.025em` product.
Suffix	Geist Sans 600, 10 px fixed, tracking `0.15em`, uppercase, slate-400.
Mark ↔ wordmark gap	≈ 28% of mark size. Optically balanced; not a fixed value.
Scaling	Full lockup at markSize ≥ 24. Below 24, use `EvalgistWordmark` (text only) or the mark alone. Do not compress the pairing.

09Usage in code

The component handles size- and surface-aware logic.

Never manually select between mark variants or hard-code lockup proportions. Import the primitive.

// Product UI — default size, inherits color
import { EvalgistMark } from "@evalgist/design-system/brand";

<EvalgistMark size={20} />

// Dark surface — sidebar, topbar, any inverted region
<EvalgistMark size={24} inverted />

// Full lockup — product pages, auth screens, hero
import { EvalgistLockup } from "@evalgist/design-system/brand";

<EvalgistLockup markSize={32} />

// Product header — Shortlist, Grade
import { EvalgistProductLockup } from "@evalgist/design-system/brand";

<EvalgistProductLockup product="Shortlist" markSize={32} />

// Tight context — nav, breadcrumb, dense header
import { EvalgistWordmark } from "@evalgist/design-system/brand";

<EvalgistWordmark size={15} />

// app/layout.tsx — wire the favicons
export const metadata = {
  title: "Evalgist",
  icons: {
    icon: [
      { url: "/favicon.svg", type: "image/svg+xml" },
      { url: "/favicon-32.png", sizes: "32x32", type: "image/png" },
      { url: "/favicon-16.png", sizes: "16x16", type: "image/png" },
    ],
    apple: "/apple-touch-icon.png",
  },
  manifest: "/site.webmanifest",
};

export const viewport = { themeColor: "#0f172a" };

10Do / don't

Constraints that protect the reading.

Rules first; then visual examples of violations.

DoRender on neutral backgrounds — white, slate-50, or slate-900 for inverted. Keep at least one cell of clear space.

Don'tOutline the open cell. Add a highlight, glow, or tile behind the mark. Recolor the tonal cell.

DoUse the mono variant for print jobs that cannot reproduce tone — stamps, embossing, single-ink silkscreen.

Don'tUse the mono variant on screen. The tonal relationship is part of the mark's identity.

DoPlace the mark on colored UI chrome if the underlying surface is neutral (mark on white inside a colored badge — fine).

Don'tPlace the mark on a tinted or gradient background. The tonal cell stops reading as tonal.

Mark violations

DoSquare cells, slate-300 tonal at ≥ 24 px.

Don'tRound the cells. Dashboard chrome.

Don'tRecolor the tonal cell.

Don'tFrame the mark. The field is the frame.

11Accent

One accent. Brand, never state.

Editorial Plum — oklch(0.39 0.105 325) · #602e63 · 10.1:1 on white. Selected 2026-07-07 after a two-round shootout gated on one test: it must never read as a fourth confidence band.

--eg-accent

base · links, rules, dots

--eg-accent-soft

7% tint · eyebrow pill fill

--eg-accent-border

28% tint · pill border

Where it may appear, by surface tier: brand — lockup-adjacent furniture, OG cards, press layouts, but never inside the mark. Marketing — eyebrow dots, links, article and blockquote rules, illustration highlights; at least one ownable anchor per primary page. Product chrome — links only. Buttons stay near-black, band pills keep their semantic hues, and the focus ring stays neutral.

DoAccent as nearby furniture — rules, dots, links. The mark stays slate.

Don'tCarry the accent into the mark. The tonal cell stays slate-300/400.

12Imagery

Evidence Editorial. Evaluation made inspectable, not mysterious.

Illustration and generated imagery extend the design system — they do not start a second brand. Synthetic documents, evaluation grids, quote evidence, and slate composition. The full agent-readable contract lives in packages/design-system/IMAGE_STYLE.md.

The formula

Synthetic documents + evaluation grids + highlighted quote evidence + restrained product UI + slate editorial composition. Every image centers a source artifact. The human remains the decider; imagery shows the substantiation, never an AI verdict.

Synthetic composites

Built from owned shapes — no stock, no captures

Hero composite: a document fragment, a criteria matrix banded by confidence, and a quote card. All data synthetic; bands carry the only color.

DocumentCriterionEvidenceDecision

Spot diagram: source to human decision in four nodes.

Evalgist default Open Graph card: grid, document stack, evidence card, and human-review panel

OG card: one artifact, heading added in code — never generated. Rendered live from /api/og.

Image families

Hero composites

Synthetic documents, an evaluation matrix, quote cards, and bands as one product-led scene. Negative space holds the headline.

Publication headers

One large analytical artifact — criteria chart, band distribution, evidence trail — as the image for a guide or post.

Spot diagrams

A short flow: document, criterion, evidence quote, human decision. Used inline in body copy.

Product composites

A restrained slice of real product UI, recomposed through Evalgist tokens with synthetic data.

Social / OG cards

One strong evidence artifact, 1200×630, with a short heading added in code — never generated.

Token-to-image mapping

Slate railBase composition--eg-slate-50 → 900 carry every image

Band colorsEvaluation state only--eg-band-likely / uncertain / unlikely

SkyNeutral source accent--eg-sky-* for references and links

Editorial PlumBrand keyline only--eg-accent · brand, never state

Geist Sans / MonoReal textSet in code or Figma, never generated

Radius + shadowQuiet shape1px borders, --eg-shadow-sm at most

Prompt anatomy

Copy-ready base clause

Restrained editorial evidence illustration for Evalgist. Crisp document geometry, structured review grids, highlighted source quotes, small annotation marks, slate-and-white palette, one semantic accent only when meaningful, flat daylight, no readable generated text, no robots, no mascots, no purple glow, no stock business people.

Add a surface line per family (hero, publication, spot, OG) and the negative-prompt list. Full templates in IMAGE_STYLE.md.

Open Graph examples

Rendered at preview scale; generated at 1200 x 630

Imagery contract

Use the ambient grid as the recognisable field.
Keep text regions protected and quiet.
Show evidence paths, document surfaces, or product UI when the image needs substance.
Avoid stock photography, decorative gradients, mascot illustration, and standalone logo cards.

Open Graph reference

Canonical size: 1200 x 630 px
Runtime generator: apps/www/app/api/og/route.tsx
Metadata helper: apps/www/lib/social-metadata.ts
Production URL: https://evalgist.ai/api/og?eyebrow=...&title=...&description=...
Static fallback: apps/www/public/og-image.png

Evalgist default card

grid, document stack, evidence card, human review

Evalgist default Open Graph card with grid, document stack, evidence card, and human-review panel

Actual generated image, rendered here at preview scale. Source aspect ratio: 1200 x 630.

Evalgist Shortlist

same artifact, product lockup plus its own headline

Actual generated image, rendered here at preview scale. Source aspect ratio: 1200 x 630.

Approved, rejected

DoCenter a source artifact. Slate composition, one band accent, synthetic data.

Don'tNo generic AI decoration. No purple glow, robots, mascots, sparkles, stock people, scores, or readable generated text.

Mobbin references

Composition cues — cited, not bundled

These captures informed the direction. They are references only — never committed as Evalgist assets. Each notes what to borrow and what to leave behind.

ReductoBorrow Document-to-data motifReject Loud purple campaign energy LegoraBorrow Visible workflow stepsReject Luxury warmth as default EqualsBorrow Chart as editorial artifactReject Decorative multi-color looseness V7Borrow Judgments buried in documentsReject Black-heavy mood as default VantaBorrow Source-anchored answer cardReject Purple AI theatre and mascot ContractbookBorrow Visible product objectReject Doodles, badges, arrows SanaBorrow Concrete AI outputReject Device glamour, chat-first framing MazeBorrow Featured report + modulesReject Generic illustrated thumbnails

13Downloads

Source files for non-React contexts.

In product code, always use the React components. These files are for slide decks, email signatures, partner decks, press.

Vector

Raster

14Content guide

One prompt. The complete voice.

Copy the current guide into an AI agent before drafting Evalgist copy. It is generated from the same content-style package used by the products. Dedicated page: /brand/voice. Raw markdown: /brand/voice.md.

# Evalgist content style guide

Copy this entire guide into your AI agent as context before writing any Evalgist copy — landing pages, guides, blog posts, product text, emails, or sales material. It is the current, authoritative voice. Do not invent rules beyond it.

This guide is generated from `@evalgist/content-style`. Do not edit it by hand; edit the constants and regenerate.

## What Evalgist is

Evalgist builds AI tools that help professionals evaluate a batch of structured documents against one criteria set — faster, more consistently, and with evidence. The human remains the decider; the AI supplies substantiation, not conclusions.

Three-beat distillation: One criteria set · Quoted evidence · Exportable record.

The human is always the decider. The AI supplies substantiation, extraction, comparison, sorting, summary, or citation — never the conclusion.

## The job being sold

Evaluate a batch of documents against one criteria set, and keep an evidence trail.

It replaces: Ad-hoc chat-assistant triage: one document at a time, criteria that drift between prompts, and no record when the decision is questioned.

What the user gets:

- one criteria set applied to every document
- a quote from the source behind every judgment
- an exportable record for the decision meeting

Sell: Speed, consistency, and an evidence trail — not a smarter model.

## Who it is for

Hiring managers and selection panels evaluating a batch of applications against the same criteria.

Segments: selection committees, hiring managers at SMBs and non-profits, academic and public-sector panels, grant and admissions reviewers.

Academic hiring is where the workflow was first built and proven. Treat it as origin and channel, never as the only intended user in marketing copy.

Not built for: teams that need deep ATS integration; fully automated decision pipelines.

## Contrasting with ad-hoc chat workflows

Contrast with the ad-hoc chat workflow, not with a named vendor or model. The wedge is workflow, not intelligence.

The three contrasts:

- Criteria drift: a chat re-interprets the standard with every prompt; a criteria set holds it across the whole batch.
- No quotes: a chat summarises; an evaluation cites the source line behind each judgment.
- No packet: a chat leaves a scrollback; an evaluation leaves a record you can bring to the meeting.

Approved patterns:

- `A chat can score one resume. It will not hold one standard across two hundred, or hand you a packet for the meeting.`
- `A chat window starts every conversation from zero. A criteria set holds the same standard for every document in the batch.`
- `You can ask a chat why it ranked someone. You cannot hand its answer to the committee.`

Forbidden patterns:

- `Better than ChatGPT.`
- `Smarter than a chatbot.`
- `Don't trust generic AI.`

## Selling vs telling (marketing surfaces)

Sell the job, not the disclaimer. The reader is drowning in documents and has a review to finish; meet that first, and let the trust surface carry the caution.

- Lead with the pain and the artifact — the batch, the quote, the record. Never with controls, storage, retention, or provider names.
- Compliance is furniture, not a feature. EU storage, ZDR routing, and retention windows belong on trust pages and in the FAQ; on a marketing page they get at most one line with links.
- Never invent segment jargon that needs a glossary. Describe the situation instead: hundreds of applications, one criteria set.
- Do not pre-reject buyers in the funnel. Scope boundaries ('not built for …') belong in the FAQ, not in heroes or feature copy.
- The origin story is one line on marketing pages and a section on the about page. It never becomes the target audience.
- Say 'the human decides' once per page. Repeating it reads as apologizing for the product.
- Use the record as the payoff, not the mood. Name the evidence trail first. Say 'defend' or 'defensible record' only when the full source survives the relevant retention window.
- Every section must earn its place against the 10-second test: what job does this do, what do I get out, can I try it now. Cut or demote everything else.
- Footers are navigation, not a legal register. Account-level trust links only; product legal lives with the product surface.

Smell test: If a section would fit a procurement portal or a privacy notice better than a product page, it is in the wrong place.

## Defend and defensible claims

Originals and extracted text are kept only for a 14-day recovery window. Evidence quotes and exportable summaries remain until the customer deletes the job or account.

Say defend, defensible, or defensible record only when the full source document survives the relevant retention window.

Allowed for the current recovery-window posture:

- evidence trail
- audit trail
- anchored to source at evaluation time
- exportable record

Do not use without source retention:

- defend
- defensible
- defensible record

## Tone

Sober, confident, slightly dry. Short sentences. The Economist, not TechCrunch. English as the primary language, even in a Belgian context.

Never use:

- emojis
- exclamation marks
- superlatives
- startup enthusiasm ("we're so excited", "the future of…")
- irony or provocation toward regulators

## Product naming

Pattern: `Evalgist <Product>`. Products are descriptive suffixes under the Evalgist parent, never sub-brands with independent identity. The set: Shortlist, Grade, Extract.

- First mention on any external surface uses the full name: `Evalgist Shortlist`.
- Second mention may shorten to the suffix: `Shortlist`.
- Inside the signed-in product, the sidebar lockup is the first mention; body copy may then use the suffix as a proper noun ("Shortlist is processing…") or as a common noun for the deliverable ("Start your first shortlist").

When in doubt: outside the auth boundary, full name on first mention; inside it, the lockup carries first mention.

## Words

Prefer:

- evidence
- quoted evidence
- one criteria set
- batch
- evidence trail
- audit trail
- exportable record
- evaluate
- shortlist
- grade
- consistent
- fair
- faster
- per criterion
- per candidate
- per answer
- review
- decide
- verify
- professional
- human decision

Avoid:

- revolutionary
- game-changing
- unleash
- supercharge
- seamlessly
- effortlessly
- 10x
- cutting-edge
- next-generation
- disruptive
- bias-free
- objective AI
- fully compliant
- AI sparkle
- magical

## How to talk about AI

Name the function, not the marketing claim. AI is the means, not the product.

- Good: `AI-assisted evaluation`
- Good for SEO: `AI resume screening with quoted evidence`
- Good for in-product status: `AI-assisted, sorted by match`
- Bad: `Powered by AI`

### Multi-pass analysis tiers

An extra pass tells the reviewer where to look. It does not make the suggestion more correct, and it never decides.

- Never claim independence between passes. Passes run on related model families and share blind spots; describe them as cross-checked, never as independent reviewers or as models that 'agree'.
- Never imply an extra pass improves the score, grade, or ranking. Sell what it produces: the criteria worth the reviewer's time.
- Name the tier after the process, not the outcome. 'Cross-checked' describes what ran; 'Verified' asserts a result the product cannot stand behind.
- Never name a model in public copy. A model is a config value that changes; the processor behind it is named in the subprocessor register, which is where that question belongs.

Approved:

- `A second pass challenges every judgment and flags the ones that do not hold up.`
- `Cross-checked analysis tells you which twelve of four hundred criteria to look at.`
- `The extra pass does not change the suggested mark. It changes where you spend your attention.`

Never:

- `Two independent AI graders agreed.`
- `Verified by a second model.`
- `Higher accuracy with multi-model consensus.`
- `Powered by <model name>.`

### AI search terms

Evalgist competes for real search intent around AI-assisted evaluation. Using the word "AI" is fine; AI theatre is not.

Allowed terms — use in title, description, summary, H1, H2, early body copy when the page actually answers that intent:

- `AI resume screening`
- `AI-assisted resume screening`
- `AI candidate screening`
- `AI-assisted evaluation`
- `AI document review`
- `AI-assisted document review`
- `AI grading`
- `AI-assisted grading`

Binding rule: When an AI search term appears, bind it in the same sentence or the next sentence to a concrete function: extract, compare, sort, summarize, cite, or produce an evidence trail.

Good patterns:

- `AI resume screening with quoted evidence. Every match cites the resume line it rests on.`
- `AI resume screening with quoted evidence.`
- `AI-assisted evaluation that keeps the human as the decider.`
- `AI document review that cites the source line behind each judgment.`
- `The AI extracts, compares, and cites evidence. The reviewer decides.`

Bad patterns:

- `AI-powered hiring that transforms screening.`
- `Powered by AI.`
- `Objective AI candidate screening.`
- `Fully compliant AI evaluation.`
- `Automated hiring decisions.`

Rule of thumb: Use AI terms for discoverability. Do not use AI as the value proposition.

## Rules for every surface

Always:

- Anchor evaluation language in evidence, criteria, and human decision-making.
- Label AI suggestions and human decisions as different states.
- Name AI as the method only when it explains a visible function.
- Use SEO-visible AI terms when they match real search intent, then bind them immediately to criteria, quoted evidence, records, or human review.
- Use the full product name on first mention outside the authenticated product frame.
- Treat every trust claim as a public claim that may be read by a customer, candidate, auditor, or regulator.

Never:

- Promise bias elimination, objectivity, complete compliance, or automated correctness.
- Use startup acceleration language to make evaluation work sound effortless.
- Make the customer, candidate, regulator, or protected group the butt of the joke.
- Replace a concrete source, quote, criterion, or workflow detail with generic AI capability language.

### Claim boundaries

- Bias: Say reduce avoidable bias, improve consistency, or make evidence visible. Do not say bias-free.
- Compliance: Say evidence trail, audit trail, or GDPR/EU AI Act caution for the current recovery-window posture. Say defensible record only when the full source survives the relevant retention window. Do not imply certification or full compliance from copy alone.
- Speed: Tie speed to a workflow artifact: faster review, faster comparison, faster evidence lookup. Do not imply the human judgment disappears.
- AI: Tie AI to a function: extract, compare, sort, summarize, cite. Do not use AI as a standalone value proposition.
- SEO: Put AI search terms in titles, descriptions, headings, and early body copy when relevant. The next clause or sentence must explain what the AI does and what the human still decides.

## Compliance posture

External copy avoids irony or provocation toward regulators. Reason: GDPR + EU AI Act audit-caution. No wordplay around pretending, faking, cheating, or fraud. No absolute fairness or full-compliance claims.

## Citing claims

The stricter the claim, the more explicit the backing.

- Cite or link: statistics, study findings, legal claims, regulatory expectations, scientific claims, market facts, named authorities.
- Soften or remove: claims you cannot support quickly — especially "bias-free", "objective", "fully compliant", "guaranteed", "automatic".
- Attribute precisely: "Ladders reported 7.4 seconds in its 2018 eye-tracking study" beats "research shows recruiters spend seconds".
- Keep product claims bounded to what the workflow produces: evidence quotes, criteria comparisons, records, exports, retained or deleted data, human-review controls.

## Landing pages

### Hero formula

- Eyebrow: full product name + a trust beat, 50 characters max
- H1: 7 words max, declarative
- Subhead: 14 words max, evidence-led
- CTA: 4 words max, verb + object, no period
- Fineprint: 2-3 trust beats joined by `·`

### Closing CTA formula

- Eyebrow: "Built for" or equivalent
- Body: 20 words max, evidence-led, ends with the audience constraint
- CTA: 4 words max

### Trust beats

Approved fineprint, shown next to a CTA (each is a public claim):

- No payment details required
- No subscription
- GDPR-compliant
- EU data residency
- Every result backed by evidence

## Long-form: pick a register first

### Guides — evidence-first practical guide

Use for: guides, how-to pages, evergreen explainers. Do not use for: dated blog essays, launch notes, legal pages, in-product task copy.

Evergreen, practical, search-oriented. The reader should leave with a method they can use without buying Evalgist.

- Opening: Open on the practical failure the reader recognises, then move quickly to the method. Example: "Most screening goes wrong before anyone reads a word."
- Evidence: Cite external research or authority when making broad causal, legal, statistical, or scientific claims. Plain workflow advice may stand without a citation.
- Structure: Use direct instructional headings. Each section should name an action, a trap, or a record the reader can produce.
- Product: Mention the relevant Evalgist product only after the useful method has been explained, and keep the CTA secondary.
- Ending: End on the professional standard the method creates, not on a sales flourish.
- Cadence: short sentences, paragraphs of one to three sentences, headings instructional, not editorial.

### Blog essays — contrarian-evidence essay

Use for: blog essays, LinkedIn-native posts, opinion-led newsletter notes. Do not use for: legal pages, regulator-facing copy, in-product task copy, evergreen guides.

Opinion-led and built to travel, but still sober Evalgist voice. Be provocative about weak evaluation practice, never about the law, the customer, or the person being evaluated.

- Opening: Open on a claim, not a definition. Example: "Your shortlist was mostly decided before the meeting. The rest was paperwork."
- Antagonist: Name the bad practice, never a protected group, regulator, customer, or individual.
- Evidence: Include at least one concrete study, number, or cited authority when making the central claim.
- Pull-quotes: Write two or three short, standalone sentences that can be quoted without context.
- Ending: End on a line the reader can repost as a statement of professional standards.
- Allowed edge: dry criticism of lazy evaluation; contrarian framing of common hiring habits; plainly naming bias hiding behind taste, fit, prestige, or speed.
- Forbidden edge: mocking regulators; claiming compliance as a joke; fraud or pretending wordplay; startup hype punctuation; humour that makes the customer look foolish.
- Cadence: short sentences, paragraphs of one to three sentences, headings argumentative, not instructional.

## Check before you ship

- Does the copy preserve the human-as-decider / AI-as-substantiation distinction?
- Are AI suggestions and human decisions labelled as different states?
- Does the copy name the evidence trail, and use defend/defensible only when the full source survives the relevant retention window?
- Is every broad factual, legal, statistical, or research claim either sourced or softened?
- If an AI search term appears, is it immediately bound to criteria, quoted evidence, records, or human review?
- Does the first external product mention use the full Evalgist <Product> name?
- Does any line imply bias-free, objective, fully compliant, or automatic decision-making?
- For a multi-pass tier: does the copy avoid claiming independence between passes, a better result, or a named model?
- Could the same sentence appear in a sober professional publication without exclamation marks, hype, or forced warmth?
- For guides: can the reader use the method without buying Evalgist?
- For blog posts: is the antagonist a weak evaluation practice, not a person, customer, regulator, or protected group?

Readable voice page · Raw markdown