✅ Deploy Preview for hyprnote ready!

Name	Link
🔨 Latest commit	215eaf1
🔍 Latest deploy log	https://app.netlify.com/projects/hyprnote/deploys/69ca4bcbf8b5c10008ce6ea2
😎 Deploy Preview	https://deploy-preview-4820--hyprnote.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

To edit notification comments on pull requests, go to your Netlify project configuration.

✅ Deploy Preview for char-cli-web canceled.

Grammar Check Results

Reviewed 1 article.

Here's How Mistral Retains Your Data

📄 apps/web/content/articles/mistral-data-retention-policy.mdx

The article is well-written and clear overall. The content is organized logically with good use of headers and specific technical details. Only two minor issues were found: a spelling variant (prioritizes vs prioritises) for consistency with British English conventions, and a missing period on one section header. No em-dashes appear in the content, and punctuation placement with quotation marks follows the correct British style throughout.

Found 2 issues:

🔤 Spelling

Line 29

Mistral explicitly states that it prioritizes EU-based infrastructure providers and applies GDPR-standard safeguards when any non-EU provider is involved.

Consistent with British English spelling used in punctuation rules

Mistral [explicitly states](https://legal.mistral.ai/terms/privacy-policy) that it prioritises EU-based infrastructure providers and applies GDPR-standard safeguards when any non-EU provider is involved.

🔹 Punctuation Placement

Line 57

Use Mistral API to Take Meeting Notes Through Char

Section headers should end with a period for consistency and proper punctuation

## Use Mistral API to Take Meeting Notes Through Char.

Powered by Claude Haiku 4.5

AI Slop Check Results

Reviewed 1 article for AI writing patterns.

Here's How Mistral Retains Your Data

apps/web/content/articles/mistral-data-retention-policy.mdx

Score: 33/50 (NEEDS REVISION)

This is a technically accurate, well-structured policy explanation with moderate AI-slop patterns. The dominant issues are: (1) metronomic sentence structures (lines 32, 44) using parallel construction for artificial rhythm rather than varied prose, (2) conversational announcements (lines 2, 6) that tell readers what to think instead of letting facts stand, (3) clickbait heading templates (lines 24, 48) using question or imperative framing instead of descriptive labels, and (4) soft anthropomorphization and significance inflation scattered throughout. The writing is not egregiously AI-generated—the content is substantive and accurate—but it carries multiple structural tells that would make a technical reader suspect LLM assistance. Tightening the paragraph rhythms, removing preview sentences, using direct headings, and simplifying abstractions would elevate it to fully human-written credibility. Score: 27/50—functional but needs revision to sound authentically human.

Found 15 issues (0 high, 5 medium, 10 low)

MEDIUM — Likely AI Pattern

Line 11 — conversational-announcement

That is not a minor detail.

Conversational announcement that tells the reader what to think instead of letting facts speak. Artificially elevates the significance of the following point.

Delete this sentence or replace with: "This has direct compliance implications."

Line 15 — conversational-announcement

Here is how the policy works in practice.

Conversational announcement/preview. Unnecessary scaffolding. A technical reader expects the next section to show how the policy works without being told.

Delete entirely. Jump to the heading and facts.

Line 41 — metronomic-rhythm

Free Le Chat users are opted in to training by default and can opt out via Privacy settings. Paid Le Chat and paid API users are opted out by default. ZDR API customers have no training risk because their data is never retained to begin with.

Metronomic rhythm. Three statements using nearly identical sentence structure: [Category] [state of opt status]. The parallel construction feels mechanical. Collapse to a list or vary construction.

Free Le Chat: opted in by default, opt out in Privacy settings. Paid Le Chat and API: opted out by default. ZDR API: no training risk (data never retained).

Line 53 — metronomic-rhythm

The structural difference between Mistral and the US-based providers is data residency by default. With OpenAI, Anthropic, or Google, you are opting into EU data residency as an enterprise feature. With Mistral, EU residency is the baseline and US routing is the opt-in.

Metronomic rhythm. Three parallel statements with near-identical structure using 'With [provider], [status].' Repetitive construction. Also mild antithesis pattern ('baseline and X is opt-in') that could be flattened.

Mistral defaults to EU data residency. OpenAI, Anthropic, and Google require you to opt in to EU residency as an enterprise feature.

Line 57 — clickbait-heading

Use Mistral API to Take Meeting Notes Through Char

Imperative command heading ('Use Mistral API to...') reads like marketing/listicle template. Also awkward syntax ('Through Char'). Use a descriptive label instead.

## Mistral in Char: Data Handling

LOW — Subtle but Suspicious

Line 33 — clickbait-heading

Is Zero Data Retention Applicable?

Question-format heading reads like clickbait listicle template. More direct: state what the section contains rather than frame it as an open question the reader should care about.

## Zero Data Retention Availability

Line 37 — metronomic-rhythm

Because the consumer product relies on stored conversation history to function, ZDR cannot be applied there.

Metronomic rhythm + excessive explanation. The sentence leads with 'Because' when it should lead with the fact. Also slightly anthropomorphizes (product 'relies on').

ZDR cannot be applied to Le Chat because the consumer product requires stored conversation history.

Line 39 — filler-phrase

Training Opt-Out in Plain Terms

"In Plain Terms" is filler throat-clearing jargon suggesting the author will simplify a complex idea. A technical blog should assume readers can parse complexity. Just say what the section covers.

## Training Opt-Out Defaults by Plan

Line 45 — other

GDPR and Compliance

Generic heading. Minor: 'GDPR and Compliance' is redundant (GDPR is compliance). Could be more specific about what the section contains.

## GDPR Coverage and Rights

Line 47 — antithesis-binary

As an EU company, Mistral operates under GDPR natively rather than as a compliance overlay.

Mild binary antithesis pattern ('natively rather than'). The phrasing sets up a contrast to imply superiority rather than stating the fact directly. Simplify.

Mistral operates under GDPR by design, not as an added layer.

Line 49 — antithesis-binary

For US healthcare organizations that need HIPAA coverage, Mistral is not the right choice without confirming a BAA is available for your specific plan.

Negative framing ('is not the right choice') instead of direct statement. Awkward double negative with 'without confirming.' Reframe as affirmative requirement.

US healthcare organizations should confirm HIPAA BAA coverage with Mistral before committing.

Line 55 — significance-inflation

For organizations in the EU or those operating under GDPR, that reversal is meaningful. It shifts the burden of compliance from your team to Mistral's default configuration.

Mild significance inflation ('meaningful') and slightly abstract framing ('shifts the burden') instead of concrete language. Also conversational announcement tone.

For EU organizations, this default matters: compliance responsibility shifts to Mistral's configuration rather than your team's choices.

Line 59 — anthropomorphization

When you bring your own Mistral API key, your meeting data is handled under Mistral's API policy: 30-day retention for abuse monitoring, not used for training, stored in the EU by default.

Slight anthropomorphization ('handled under') and awkward pronoun reference ('your meeting data is handled'). Also minor metronomic list rhythm in the latter part.

Your meeting data follows Mistral's API policy: 30-day retention for abuse monitoring, no training use, EU storage by default.

Line 61 — anthropomorphization

If you activate ZDR on your Mistral API account, that protection applies to requests made through Char as well. Nothing is stored beyond the time needed to process the result.

Mild anthropomorphization ('protection applies') and slightly formal/abstract tone. Simplify with active, concrete language.

If you enable ZDR on your Mistral API account, the same protection applies to Char requests. No data persists after processing.

Line 63 — anthropomorphization

And if your data governance requirements change, or a different provider gets approved by your security team, you can switch inside Char without changing how your notes are stored or structured. Your files stay on your device regardless.

Minor filler and weak anthropomorphization ('gets approved'). The opening 'And if' reads conversational/redundant given context. Tighten and simplify.

You can switch providers in Char without restructuring your notes. Files remain on your device.

Powered by Claude Haiku 4.5 with stop-slop rules

Blog Post Review: Humanizer + Stop-Slop

File: apps/web/content/articles/mistral-data-retention-policy.mdx

Humanizer Check (24 AI writing patterns)

Score: 39/50 (PASS)

Overall the article is well-written with strong specifics (30 days, 5 years, named settings paths) and mostly free of major AI tells. The main issues are subtle: slightly stiff phrasing, significance inflation, and an overly even rhythm.

HIGH

MEDIUM

LOW

Patterns NOT found (good): No em dash overuse (#13), no emojis (#17), no collaborative artifacts (#19), no knowledge-cutoff disclaimers (#20), no sycophantic tone (#21), no negative parallelisms (#9), no bold overuse (#14), no curly quotes (#18), no synonym cycling (#11), no false ranges (#12), no inline-header lists (#15). The article avoids the majority of the 24 patterns.

Stop-Slop Check (phrases, structures, rhythm)

Score: 41/50 (PASS)

The writing is strong overall. The dominant weakness is passive voice throughout (data "is stored," users "are opted in," features "are available"). The article avoids em-dashes, dramatic fragmentation, business jargon, adverbs, and meta-commentary.

Passive Voice (Primary Issue)

Most significant recurring pattern. Converting to active voice with Mistral as the named actor would improve authenticity.

Structural Issues

Rhythm Issues

Positive Patterns (No Issues Found)

• No em-dashes
• No dramatic fragmentation
• No "Not X, but Y" binary contrasts
• No business jargon
• No adverbs or filler words
• No meta-commentary
• No rhetorical questions
• Concrete specifics throughout (30 days, 5 years, 1 year, named UI paths)
• Good sentence length variation overall

Summary

Top 3 Priority Fixes:

1. Delete throat-clearing sentences (lines 11, 15) — "That is not a minor detail." and "Here is how the policy works in practice." add no information.
2. Convert passive to active voice — Name Mistral as the actor throughout. This is the single biggest AI tell in the article.
3. Break metronomic patterns (lines 41, 53) — Vary the parallel opt-in/opt-out list structure and the "With X...With Y" comparison.

The article is well above the revision threshold on both checks. Content is substantive, specific, and well-sourced. The fixes above are refinements, not rewrites.

Blog Post Review: Humanizer + Stop-Slop

Humanizer Check (24 AI writing patterns)

Score: 38/50 (PASS)

The post is clean technical writing that largely avoids obvious AI patterns. Specificity is strong (actual retention periods, specific UI paths, named products). The main tell isn't pattern abuse — it's the absence of a human perspective. No reactions, no acknowledgment of uncertainty. It reads like a well-researched report, not someone sharing what they learned.

HIGH

No high-severity issues found.

MEDIUM

Line 11 — Pattern #21: Sycophantic/Servile Tone

That is not a minor detail.

Artificial emphasis telling the reader what to think.

Line 13 — Pattern #1: Undue Emphasis on Significance

For teams evaluating AI providers on data governance grounds, that starting point matters.

Telling readers what to conclude rather than showing evidence.

Line 15 — Pattern #19: Collaborative Communication Artifact

Here is how the policy works in practice.

Chatbot-style transitional phrase.

Line 55 — Pattern #1: Undue Emphasis on Significance

For organizations in the EU or those operating under GDPR, that reversal is meaningful.

Telling readers what to conclude instead of showing.

For organizations in the EU or those operating under GDPR, that reversal shifts compliance burden from your team to Mistral's infrastructure.

LOW

Line 11 — Pattern #7/#4: Overused AI Vocabulary / Promotional Language

was built from the ground up under stricter privacy regulation

"From the ground up" is a cliché that adds no information.

was designed under stricter privacy regulation

Line 37 — Pattern #11: Elegant Variation (Synonym Cycling)

Because the consumer product relies on stored conversation history to function, ZDR cannot be applied there.

"Consumer product" is a mild synonym cycle when you've already named "Le Chat."

Le Chat needs stored conversation history to work, so ZDR cannot be applied there.

Line 41 — Pattern #10: Rule of Three

Free Le Chat users are opted in to training by default and can opt out via Privacy settings. Paid Le Chat and paid API users are opted out by default. ZDR API customers have no training risk because their data is never retained to begin with.

Three parallel statements feel slightly assembled, and "to begin with" is filler.

Free Le Chat users are opted in to training by default and can opt out via Privacy settings. Paid Le Chat and paid API users are opted out by default. ZDR API customers have no training risk—Mistral never retains their data.

Line 35 — Pattern #22: Filler Phrase

Mistral does not retain your inputs or outputs beyond what is needed to return the result.

"Beyond what is needed" is wordy.

Mistral only retains your data long enough to return the result.

Line 43 — Pattern #22: Filler Phrase

If you are a paid API customer, you do not need to take any action to keep your data out of training pipelines. It is already excluded.

Slightly wordy.

Paid API customers don't need to do anything. Your data is already excluded from training.

Line 61 — Pattern #22: Filler Phrase

Nothing is stored beyond the time needed to process the result.

"Beyond the time needed" is wordy.

Nothing is stored after processing.

Stop-Slop Check (phrases, structures, rhythm)

Score: 38/50 (PASS)

The post is solid on authenticity and trust but suffers from passive voice overload. The content is direct and specific, but the delivery is often indirect. The single throat-clearing opener ("Here is how...") is minor but should be cut. The binary contrast in the comparison section is the only structural cliche, and it's mild.

Banned Phrases

Line 15 — Throat-clearing opener

Here is how the policy works in practice.

Matches "Here's what/this/that" pattern from phrases.md.

Line 11 — Emphasis crutch / Telling instead of showing

That is not a minor detail.

Announces significance rather than demonstrating it.

Structural Cliches

Line 53 — Binary contrast

With OpenAI, Anthropic, or Google, you are opting into EU data residency as an enterprise feature. With Mistral, EU residency is the baseline and US routing is the opt-in.

Mechanical "With X... With Y..." contrast pattern.

OpenAI, Anthropic, and Google treat EU residency as an enterprise feature. Mistral makes it the default.

Line 55 — Vague declarative

that reversal is meaningful.

Announces importance without naming the specific thing.

That matters for EU teams: compliance responsibility shifts to Mistral's configuration rather than your team's choices.

Passive Voice (primary issue — 10+ instances)

The post relies heavily on passive constructions. Key examples:

Rhythm Patterns

No em-dashes found. No three-item dramatic lists. Good paragraph length variation. Sentence lengths are reasonably varied. Minor metronomic quality in the training opt-out section (line 41) with three parallel statements.

Powered by humanizer + stop-slop