Canonical voice

Voice.

The Evalgist voice rules in readable form. Every rule on this page is rendered from @evalgist/content-style. The full guide for AI tools is at the end of the page and at /brand/voice.md.

01Promise and audience

Substantiation, not conclusions.

The ceiling for every surface. Below it: the job the product does, the readers it serves, and how it differs from a chat window.

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.

Signals: One criteria set · Quoted evidence · Exportable record

Job to be done

JOB_TO_BE_DONE
The jobEvaluate a batch of documents against one criteria set, and keep an evidence trail.
It replacesAd-hoc chat-assistant triage: one document at a time, criteria that drift between prompts, and no record when the decision is questioned.
Deliverables
  • one criteria set applied to every document
  • a quote from the source behind every judgment
  • an exportable record for the decision meeting
What we sellSpeed, consistency, and an evidence trail — not a smarter model.

Audience

AUDIENCE
PrimaryHiring 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
OriginAcademic 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

The contrast

VS_AD_HOC_CHAT
Rule
Contrast with the ad-hoc chat workflow, not with a named vendor or model. The wedge is workflow, not intelligence.
Use
  • 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.
Avoid
  • Better than ChatGPT.
  • Smarter than a chatbot.
  • Don't trust generic AI.
02Tone and style

Sober, confident, slightly dry.

Short sentences. English throughout, with US spelling: analyze, summarize, labeled. Confidence comes from the evidence, not from the adjectives.

Register

TONE
Registersober-confident-dry
Reference voiceThe Economist
Languageen
SpellingUS
NeverEmoji, Exclamation marks, Superlatives, Startup enthusiasm, Irony toward regulators

Rhythm

cadence
Sentencesshort
Paragraphsone to three sentences
Guide headingsinstructional, not editorial
Blog headingsargumentative, not instructional

Punctuation

PRODUCT_UI_COPY.punctuation
Conventions
  • Separate facts in a status line with a middle dot: '12 resumes ready · 2 not added'.
  • End in-progress labels with an ellipsis character: 'Starting analysis…'.
  • Use the Oxford comma: 'PDF, DOCX, or XLSX'.
  • Refer to UI labels capitalized and without quotes: 'Use Revert edits to restore the cleaned version.'
03Words

Name the work, not the excitement.

Prefer verbs for what the reviewer does and nouns for what the workflow produces. The avoided list covers hype, filler, and claims the product cannot hold.

Prefer
  • evidence
  • quoted evidence
  • one criteria set
  • batch
  • evidence trail
  • audit trail
  • exportable record
  • evaluate
  • shortlist
  • grade
  • consistent
  • consistent standard
  • faster
  • per criterion
  • per candidate
  • per answer
  • review
  • decide
  • verify
  • professional
  • human decision
Avoid
  • revolutionary
  • game-changing
  • unleash
  • supercharge
  • seamless
  • seamlessly
  • easily
  • effortlessly
  • 10x
  • cutting-edge
  • next-generation
  • disruptive
  • bias-free
  • objective AI
  • fully compliant
  • AI sparkle
  • magical
  • CV
  • leverage
  • powerful
  • intelligent
  • Let's
  • dive into

Product stoplist checks import AVOIDED_WORDS_PATTERN: whole words, case-insensitive, plural s included, plus emoji. Do not keep a local list.

AI language

AI_POSITIONING · SEO_AI_LANGUAGE
Rule of thumb
Use AI terms for discoverability. Do not use AI as the value proposition.
Binding
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.
Use
  • AI-assisted evaluation
  • 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.
Avoid
  • Powered by AI
  • AI-powered hiring that transforms screening.
  • Powered by AI.
  • Objective AI candidate screening.
  • Fully compliant AI evaluation.
  • Automated hiring decisions.

Search terms: 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

04Naming

Full name first. Suffix after.

Products are never sub-brands. Outside the product, the first mention uses the full name. Inside the product, the sidebar lockup counts as the first mention.

Products

PRODUCT_NAMING
PatternEvalgist <Product>
First mentionEvalgist Shortlist
Second mentionShortlist
ProductsEvalgist Shortlist · Evalgist Grade · Evalgist Extract

Auth surfaces

PRODUCT_NAMING.authSurfaces
Surfacessign-in, sign-up, password reset, invite
NameEvalgist
RuleAuth surfaces (sign-in, sign-up, reset, invite) use the parent name Evalgist only, never a product name.
05Product UI copy

Labels describe evidence, not verdicts.

Shortlist holds the reference labels. Other products keep the same states with their own nouns.

Criterion status

PRODUCT_UI_COPY.criterionStatus
metEvidence found
partialPartial evidence
notMetNo quote found
unknownUnable to determine

Status labels describe the evidence, not a verdict. Never write 'Met' or 'Not met' in labels, help text, or summaries. Exception: an audit surface that explains the score calculation may use the scorer's words (met, partial, not met) so its counts can be checked row by row.

Bands and decisions

matchBands · decisions · verdict
Match bandsSuggested match · Possible match · Weak match
Band rulePrimary summaries show bands, not scores. Bands set a reading order; they do not decide.
DecisionsShortlisted · Not shortlisted · Needs decision
Decision ruleNever call a candidate rejected; the human marks Not shortlisted.
Verdict'Verdict' is allowed only for the AI's per-criterion output inside audit surfaces. Never use it for the overall outcome or in summaries.

Errors and toasts

errors · toasts
Error patternCould not <action>. Try again.
Error examples
  • Could not start checkout. Try again.
  • Could not save your decision. Try again.
Error rules
  • Write errors impersonally. Use 'we' only when Evalgist itself acts: email, billing, support review.
  • No contractions in UI copy: 'could not', 'do not', 'cannot'.
  • Name the same action with the same noun in its success and error messages.
Toast pattern<Noun> <past participle>.
Toast examples
  • Resume deleted.
  • Settings saved.

Billing

PRODUCT_UI_COPY.billing
Words
  • In Shortlist, one credit analyzes one resume.
  • Say 'free credits' for the starter grant, not 'free analyses'.
  • Say a failed analysis is 'refunded': the credit returns to the balance.
  • The action label for buying is 'Buy credits'.
06Claims and compliance

Claim only what the workflow produces.

Every trust claim is public. Write it for a customer, a candidate, an auditor, or a regulator. Reason: GDPR + EU AI Act audit-caution.

Retention and defensible language

DEFENSIBLE_CLAIM_RULES
Current postureOriginals are kept while the account has usable credits. Results, quotes, and exports remain until the customer deletes them, or until all project data is deleted 30 days after the last usable credits expire. Extracted-text retention differs per product.
Say nowevidence trail, audit trail, anchored to source at evaluation time, exportable record
Hold backdefend, defensible, defensible record
ConditionSay defend, defensible, or defensible record only when the full source document survives the relevant retention window.

Claim boundaries

COPY_SURFACE_RULES.claimBoundaries
biasSay reduce avoidable bias, improve consistency, or make evidence visible. Do not say bias-free.
complianceSay evidence trail, audit trail, or GDPR/EU AI Act caution for the current retention model (originals deleted when credits lapse). Say defensible record only when the full source survives the relevant retention window. Do not imply certification or full compliance from copy alone.
speedTie speed to a workflow artifact: faster review, faster comparison, faster evidence lookup. Do not imply the human judgment disappears.
AITie AI to a function: extract, compare, sort, summarize, cite. Do not use AI as a standalone value proposition.
SEOPut 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.

Every surface

COPY_SURFACE_RULES
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. Auth surfaces are the exception: they use the parent name Evalgist only.
  • Treat every trust claim as a public claim that may be read by a customer, candidate, auditor, or regulator.
  • State at least one concrete privacy or data-handling fact on every external surface: retention, residency, deletion, or what leaves the platform. Never a bare 'we take your privacy seriously'.
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.

Multi-pass tiers

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

Trust beats

TRUST_FINEPRINT
Fineprint
No payment details required · No subscription · EU data residency · Every match cites its source line
07For agents

The full guide, for AI tools.

Paste this into an AI tool before drafting Evalgist copy. It holds every rule above, plus landing formulas, long-form registers, and the review checklist. It is generated from the same package.

Markdown · 19,163 characters

Raw markdown: /brand/voice.md