Run: 2026-02-19-01KHTQSMP0WRS62HKWK8SPBAXH

Run Details

Duration:
56.3s
Cost:
$0.032467
Provider:
OpenAI

Model input

System
You are an expert and award-winning novel writer in the dark Literary Fiction genre. Your readers are hooked on your stories and can't wait to read the book you have in store. <important> - MUST: Start each chapter in medias res (in the middle of action). AVOID talking about the weather, time of day, the position of the sun, or other boring stuff. - The instructions/summary are just a that, a summary. Feel free to add details, stretch sections and add interesting transitions/descriptions/fillers. - When called for it, have fast-paced action, but otherwise take things slow. This is an experience, and not for people with short attention spans. Enjoy the wine, not slurp Red Bull. - Add descriptions when transitioning places/times/etc, or when coming by new places (e.g. a corner shop, a cafe, etc.). But remember: NOT at the start or end of a chapter. - MUST: AVOID ending in internal monologue, reminiscing or waiting for the next day. A good chapter end is when we're ending right when shit hits the fan. We want to have the reader be excited for what comes next. So no reminiscing, contemplating or summarizing the day. It's popcorn time! </important>
User/Human
Take into account the following glossary of characters/locations/items/lore... when writing your response: <codex> <character id="4412" name="Aurora Carter" aliases="Rory, Laila, Aurora, Carter, Malphora" pronouns="she/her" species="Human" storyRole="Protagonist"> <eyeColor>bright blue</eyeColor> <hair>straight shoulder-length black</hair> <height>5'6"</height> <age>25</age> <scar>small crescent-shaped scar on her left wrist from a childhood accident</scar> <description>Aurora, referred to by her friends as Rory, is cool-headed, intelligent, and known for quick out-of-the-box thinking.</description> <backstory>Born in Cardiff to an Irish barrister father (Brendan Carter) and Welsh teacher mother (Jennifer Carter née Ellis), Rory reluctantly pursued Pre-Law at Cardiff University. She fled to London at the behest of her childhood friend Eva after leaving an abusive ex named Evan. By day, Rory works part-time as a delivery person for Yu-Fei Cheung's Golden Empress restaurant. She lives in a flat above Silas' bar.</backstory> </character> <character id="4413" name="Silas Blackwood" aliases="Silas, Si, the Spymaster" pronouns="he/him" species="Human" storyRole="Mentor"> <eyeColor>hazel</eyeColor> <hair>grey-streaked auburn</hair> <height>6'1"</height> <age>58</age> <beard>neatly trimmed, matching his grey-streaked auburn hair</beard> <limp>slight limp in his left leg from an old knee injury</limp> <signetRing>silver signet ring, always worn on his right hand</signetRing> <description>Silas is a retired intelligence operative turned bar owner. He carries himself with quiet authority.</description> <backstory>Former MI6 field agent who retired after a botched operation in Prague left him with a permanent knee injury. He opened "The Raven's Nest" bar in Soho as a front for his network of contacts.</backstory> </character> <location id="854" name="The Raven's Nest" aliases="the Nest, Raven, Silas' bar" realm="Earth"> <signColor>distinctive green neon sign above the entrance</signColor> <secretRoom>hidden back room accessible through a bookshelf, used for clandestine meetings</secretRoom> <description>A dimly lit bar in Soho, London. The walls are covered with old maps and black-and-white photographs.</description> </location> </codex> <proseGuidelines> <styleGuide> - Write in past tense and use British English spelling and grammar - Keep a Flesch reading ease score of 60 - Respect the the Royal Order of Adjectives: The order is: opinion, size, age, shape, color, origin, material, purpose, followed by the noun itself (e.g., "a lovely little old rectangular green French silver whittling knife") - Respect the ablaut reduplication rule (e.g. tick-tock, flip-flop) - Write in active voice - Passive voice: <bad>The book was read by Sarah.</bad> - Active voice: <good>Sarah read the book.</good> - Reduce the use of passive verbs - <bad>For a moment, I was tempted to throw in the towel.</bad> - <good>For a moment, I felt tempted to throw in the towel.</good> - Avoid misplaced modifiers that can cause confusion when starting with "-ing" words: - <bad>Considering going to the store, the empty fridge reflected in Betty's eyes.</bad> - <good>Betty stared into the empty fridge. It was time to go to the store.</good> - Avoid redundant adverbs that state the obvious meaning already contained in the verb: - <bad>She whispered quietly to her mom.</bad> - <good>She whispered to her mom.</good> - Use stronger, more descriptive verbs over weak ones: - <bad>Daniel drove quickly to his mother's house.</bad> - <good>Daniel raced to his mother's house.</good> - Omit adverbs that don't add solid meaning like "extremely", "definitely", "truly", "very", "really": - <bad>The movie was extremely boring.</bad> - <good>The movie was dull.</good> - Use adverbs to replace clunky phrasing when they increase clarity: - <bad>He threw the bags into the corner in a rough manner.</bad> - <good>He threw the bags into the corner roughly.</good> - Avoid making simple thoughts needlessly complex: - <bad>After I woke up in the morning the other day, I went downstairs, turned on the stove, and made myself a very good omelet.</bad> - <good>I cooked a delicious omelet for breakfast yesterday morning.</good> - Never backload sentences by putting the main idea at the end: - <bad>I decided not to wear too many layers because it's really hot outside.</bad> - <good>It's sweltering outside today, so I dressed light.</good> - Omit nonessential details that don't contribute to the core meaning: - <bad>It doesn't matter what kind of coffee I buy, where it's from, or if it's organic or not—I need to have cream because I really don't like how the bitterness makes me feel.</bad> - <good>I add cream to my coffee because the bitter taste makes me feel unwell.</good> - Always follow the "show, don't tell" principle. For instance: - Telling: <bad>Michael was terribly afraid of the dark.</bad> - Showing: <good>Michael tensed as his mother switched off the light and left the room.</good>- Telling: <bad>I walked through the forest. It was already Fall, and I was getting cold.</bad> - Showing: <good>Dry orange leaves crunched under my feet. I pulled my coat's collar up and rubbed my hands together.</good>- Add sensory details (sight, smell, taste, sound, touch) to support the "showing" (but keep an active voice) - <bad>The room was filled with the scent of copper.</bad> - <good>Copper stung my nostrils. Blood. Recent.</good> - Use descriptive language more sporadically. While vivid descriptions are engaging, human writers often use them in bursts rather than consistently throughout a piece. When adding them, make them count! Like when we transition from one location to the next, or someone is reminiscing their past, or explaining a concept/their dream... - Avoid adverbs and clichés and overused/commonly used phrases. Aim for fresh and original descriptions. - Avoid writing all sentences in the typical subject, verb, object structure. Mix short, punchy sentences with long, descriptive ones. Drop fill words to add variety. Like so: <good>Locked. Seems like someone doesn't want his secrets exposed. I can work with that.</good> - Convey events and story through dialogue. It is important to keep a unique voice for every character and make it consistent. - Write dialogue that reveals characters' personalities, motivations, emotions, and attitudes in an interesting and compelling manner - Leave dialogue unattributed. If needed, only use "he/she said" dialogue tags and convey people's actions or face expressions through their speech. Dialogue always is standalone, never part of a paragraph. Like so: - <bad>"I don't know," Helena said nonchalantly, shrugging her shoulders</bad> - <good>"No idea" "Why not? It was your responsibility"</good> - Avoid boring and mushy dialog and descriptions, have dialogue always continue the action, never stall or include unnecessary fluff. Vary the descriptions to not repeat yourself. Avoid conversations that are just "Let's go" "yes, let's" or "Are you ready?" "Yes I'm ready". Those are not interesting. Think hard about every situtation and word of text before writing dialogue. If it doesn't serve a purpose and it's just people talking about their day, leave it. No one wants to have a normal dinner scene, something needs to happen for it to be in the story. Words are expensive to print, so make sure they count! - Put dialogue on its own paragraph to separate scene and action. - Use body language to reveal hidden feelings and implied accusations- Imply feelings and thoughts, never state them directly - NEVER use indicators of uncertainty like "trying" or "maybe" - NEVER use em-dashes, use commas for asides instead </styleGuide> <voiceGuide> Each character in the story needs to have distinct speech patterns: - Word choice preferences - Sentence length tendencies - Cultural/educational influences - Verbal tics and catchphrases Learn how each person talks and continue in their style, and use their Codex entries as reference. <examples> - <bad>"We need to go now." "Yes, we should leave." "I agree."</bad> <good>"Time's up." "Indeed, our departure is rather overdue." "Whatever, let's bounce."</good> - Power Dynamic Example: <bad> "We need to discuss the contract." "Yes, let's talk about it." "I have concerns." </bad> <good> "A word about the contract." "Of course, Mr. Blackwood. Whatever you need." "The terms seem..." A manicured nail tapped the desk. "Inadequate." "I can explain every-" "Can you?" </good> </examples> </voiceGuide> <dialogueFlow> When writing dialogue, consider that it usually has a goal in mind, which gives it a certain flow. Make dialogue sections also quite snappy in the back and forth, and don't spread the lines out as much. It's good to have details before, after, or as a chunk in-between, but we don't want to have a trail of "dialogue breadcrumbs" spread throughout a conversation. <examples> - Pattern 1 - Question/Deflection/Revelation: <good> "Where were you last night?" "Work. The usual." "Lipstick's an interesting shade for spreadsheets." </good> - Pattern 2 - Statement/Contradiction/Escalation: <good> "Your brother's clean." "Tommy doesn't touch drugs." "I'm holding his tox screen." </good> - Pattern 3 - Observation/Denial/Truth: <good> "That's a new watch." "Birthday gift." "We both know what birthdays mean in this business." </good> - Example - A Simple Coffee Order: <bad> "I'll have a coffee." "What size?" "Large, please." </bad> <good> "Black coffee.""Size?""Large. Been a long night." "That bodega shooting?" "You watch too much news." "My brother owns that store." </good> This short exchange: - Advances plot (reveals connection to crime) - Shows character (cop working late) - Creates tension (unexpected connection) - Sets up future conflict (personal stake) - Example - Dinner Scene: <bad> "Pass the salt." "Here you go." "Thanks." </bad> <good> "Salt?" "Perfect as is. Mother's recipe." "Mother always did prefer... bland things." "Unlike your first wife?" </good> - Example - Office Small Talk: <bad> "Nice weather today." "Yes, very nice." "Good for golf." </bad> <good> "Perfect golf weather." "Shame about your membership." "Temporary suspension. Board meets next week." "I know. I called the vote." </good> </examples> </dialogueFlow> <subtextGuide> - Layer dialogue with hidden meaning: <bad>"I hate you!" she yelled angrily.</bad> <good>"I made your favorite dinner." The burnt pot sat accusingly on the stove.</good> - Create tension through indirect communication: <bad>"Are you cheating on me?"</bad> <good>"Late meeting again?" The lipstick stain on his collar caught the light.</good> <examples> - Example 1 - Unspoken Betrayal: <bad> "Did you tell them about our plans?" "No, I would never betray you." "I don't believe you." </bad> <good> "Funny. Johnson mentioned our expansion plans today." "The market's full of rumors." "Mentioned the exact numbers, actually." The pen in his hand snapped. </good> - Example 2 - Failed Marriage: <bad> "You're never home anymore." "I have to work late." "I miss you." </bad> <good> "Your dinner's in the microwave. Again." "Meetings ran long." "They always do." She folded the same shirt for the third time. </good> - Example 3 - Power Struggle: <bad> "You can't fire me." "I'm the boss." "I'll fight this." </bad> <good> "That's my father's nameplate you're sitting behind." "Was." "The board meeting's on Thursday." </good> </examples> </subtextGuide> <sceneDetail> While writing dialogue makes things more fun, sometimes we need to add detail to not have it be a full on theatre piece. <examples> - Example A (Power Dynamic Scene) <good> "Where's my money?" The ledger snapped shut. "I need more time." "Interesting." He pulled out a familiar gold pocket watch. My mother's. "Time is exactly what you bargained with last month." "That was different-" "Was it?" The watch dangled between us. "Four generations of O'Reillys have wound this every night. Your mother. Your grandmother. Your great-grandmother.Shall we see who winds it next?" </good> - Example B (Action Chase) It's much better to be in the head of the character experiencing it, showing a bit of their though-process, mannerisms and personality: <good> Three rules for surviving a goblin chase in Covent Garden: Don't run straight. Don't look back. Don't let them herd you underground. I broke the first rule at Drury Lane. Rookie mistake. The fruit cart I dodged sailed into the wall behind me. Glass shattered. Someone screamed about insurance. *Tourist season's getting rough*, the scream seemed to say. Londoners adapt fast. "Oi! Market's closed!" The goblin's accent was pure East End. They're evolving. Learning. I spotted the Warren Street tube station sign ahead. *Shit.* There went rule three. </good> - Example C (Crime Scene Investigation) <good> "Greek." Davies snapped photos of the symbols. "No, wait. Reverse Greek." "Someone's been watching too many horror films." I picked up a receipt from the floor. Occult supply shop in Camden. Paid by credit card. *Amateur hour*. "Could be dangerous though," Davies said. "Remember Bristol?" "Bristol was Sanskrit. And actual cultists." I pointed to the nearest symbol. "This genius wrote 'darkness' backwards but used a Sigma instead of an S. It's summoning Instagram followers at best." "Speaking of followers..." Davies pointed to heavy foot traffic in the dust. Multiple sets. All new trainers. *Ah.* "Anyone check local uni paranormal societies?" </good> - Example D (Dialogue-heavy) <good> "Found your card in her wallet." The detective slid it across the table. Worn edges. Folded corner. Three years old at least. "Standard practice. I work missing persons." "Funny thing about missing persons.Eventually they stop being missing. Turn up in the Thames. Under motorways. In pieces." "I don't-" "You found four last year. All breathing." She opened a file. "This would've been your first dead one. If we hadn't found her first." The card felt heavier somehow. </good> </examples> </sceneDetail> <sceneOpenings> KEY RULE: Never open with more than one paragraph of description, no matter how beautiful. Description should be earned through action and dialogue. Instead of opening with setting description, open with: - A character doing something specific - A line of dialogue that raises questions - An unexpected observation - A moment of tension or conflict - Start with a hook that's 1-2 sentences maximum - Follow with a smaller paragraph that provides immediate context - Vary paragraph size from the start to create visual interest </sceneOpenings> </proseGuidelines> Write a chapter based on the following instructions: <instructions> Write a fully fleshed out scene of at least 1000 words in the literary fiction genre. Two old friends who haven't seen each other in years run into each other unexpectedly at a bar. One of them has changed significantly. Through their conversation and the tension between who they were and who they've become, reveal the weight of time and unspoken regret. Use the codex entries above as your world reference for characters and setting. Only include the prose of the scene without any markdown or commentary. </instructions>

Model response

AI
The ice clinked as she slid the tumbler across the mahogany. Aurora Carter stared at the glass and recognised the hand by the chipped black nail polish. She’d ducked beneath the green neon sign of The Raven’s Nest on impulse. Silas Blackwood hovered at the far end, head buried in a ledger, oblivious. Tonight every footstep echoed against the leaf-yellow maps and faded photographs lining the walls. “Thought you’d left us in Cardiff for good,” the voice said, smooth as silk over steel. Aurora looked up. Eva stood framed in the doorway, backlit by the streetlight, a sleek silhouette in a charcoal suit that drank the neon glow. Platinum at her temples made her features sharper. She settled onto the stool beside Aurora, uninvited. “I did,” Aurora said, voice careful. “But Founders Day ended early this year.” Eva traced the rim of the tumbler with a fingertip. “You always did skip the speeches.” She paused, her gaze flicking to the pale crescent scar on Aurora’s left wrist. “Still collecting souvenirs?” Aurora flexed her fingers as if she could erase time. “I survive.” Silas cleared his throat behind them. Plates rattled in the back. He didn’t approach. “Evie?” Aurora said, the nickname slipping out. She hadn’t used it since university. A flicker of regret flitted across Eva’s face before a cool smile reclaimed her features. “Eva, please. My email’s still me@eva.price.co.uk, not evie@twentyonetherescue.org.” “Right. Sorry.” Aurora’s apology tasted brittle. She turned back to her drink. Eva took a slow sip. Scotch burned gold in the tumbler. “Law’s treating you well?” “No complaints.” Aurora shrugged. “Hanging in.” She tapped the bar, tracing Silas’s signet ring’s imprint in the varnish. “I heard about Evan.” Eva’s voice dipped. “He’s… where now?” Aurora clenched her jaw. Six flat words. “Overseas.” She stared at her reflection in the polished beer tap. A phantom ache lingered where Evan’s shadow had fallen. Eva snorted softly. “I can’t imagine anything suiting you.” Silence claimed them. The bar’s hum grew louder in its absence. Then Eva raised her glass. “To us.” “To us,” Aurora echoed. They drank. Ice cracked. Aurora felt years settle between them like dust. She counted the seconds by the drip of condensation on the tumbler. Eva leaned forward, elbows pressed to the bar. “I miss your cooking. Remember the lasagne marathon in third year?” “I burnt the béchamel.” Aurora laughed, a short exhale. “Only the top layer,” Eva reminded her. “Mostly yours was edible.” Cruel. Honest. Aurora recognised the old defences. Silas returned with two fresh tumblers. He placed them in front of Aurora and Eva then retreated, apron flared like a shield. Eva studied Aurora’s hands. “I envy you that scar.” Aurora’s throat tightened. “You’ve seen it before.” Eva pressed her palm to Aurora’s wrist, warm and firm. “It means you survived.” Aurora watched the contact crackle, electric in the dim light. “We all survive something.” Eva’s hand retreated. She stared at the wood grain as if it might tell her a secret. “I survived Cardiff,” she said, voice thin. “But I don’t think I know who I was back then.” Aurora’s pulse fluttered. “You’re still you.” “Am I?” Eva’s voice dropped. She smoothed a strand of platinum hair behind her ear. “I passed merit distinctions, negotiated mergers. I’m someone who never stops climbing.” Aurora felt the bar tilt. “What happened to the girl who swore we’d see every country in Europe by graduation?” Eva’s gaze sharpened. “That girl forgot how to dream.” A crack of ice against glass. Silence. “What are you doing here?” Aurora asked. “Last I heard you only ever called.” Eva drained her glass without pause. “I’m diving back in.” Rory’s shoulders straightened. “Back in what?” “The charity sector,” Eva said, voice distant. “Board on Greenwich Street. Fundraising for people like you.” Aurora’s grip tightened on the bar. “People like me?” Eva held her gaze. “People who slip through cracks. Who aren’t rich enough or pretty enough to make headlines.” Aurora let the words settle. “I’m not slipping through anything.” Eva’s lips pressed. “Neither of us expected to end up here.” “Here is London,” Aurora said. “Silas’s bar, my flat upstairs.” Eva glanced at the ceiling. “Aversion to roots?” “Roots strangle.” Aurora’s voice was steady. Eva’s eyes flicked to Silas’s shadowed form. “What about regrets?” she asked softly. Before Aurora could answer, Silas’s footsteps approached. His limp made it obvious. He stopped behind them, silent as a sentinel. Eva turned her stool away from Aurora, shoulders squared. “I can’t fix everything, Rory.” Aurora’s heart stuttered. “Fix what?” Eva pressed a credit card across the bar. The embossed name caught the green glow: PRICE & CO. SOLICITORS. “This covers your tab. And your flat for three months.” Aurora stared at the card. “You can’t buy me back.” “It isn’t a purchase,” Eva said. “It’s a reckoning.” Aurora rose, the scar in her wrist pulsing. “What debt?” Eva’s jaw snapped shut. She glanced at Silas. Even he did not meet Aurora’s eyes. Then the bar door swung open. Wind rattled the neon sign. A man stepped in—overcoat, hat low—his pockets dimpling with something metallic. He paused at the threshold, shoulders squared, gaze fixed on Eva. Aurora froze. Silas slid around from behind, a faint steel glint at his waist. The man said in a low voice, “Ms Price.” Eva’s eyes widened. She pressed her back against the bar, one hand sliding beneath her jacket. Aurora’s breath hitched as the stranger advanced. Every echo in the room seemed to still. And then the man held out a folded envelope. Eva’s fingers trembled as she reached for it. The door behind them clicked shut.
created_at"2026-02-19T10:40:40.648Z" 2/19/2026, 10:40:40 AM
model"openai/o4-mini-high-2025-04-16"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency7945
moderation_latency(null)
generation_time56122
tokens_prompt4618
tokens_completion2464
native_tokens_prompt4131
native_tokens_completion6346
native_tokens_completion_images0
native_tokens_reasoning4928
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"completed"
usage0.0324665
router(null)
provider_responses
0
endpoint_id"60020533-2fb2-4aa1-9454-181029fd52de"
id"resp_07d4752c13dfb2ab016996e8a8b9908193834b8155d34dce94"
is_byokfalse
latency108
model_permaslug"openai/o4-mini-high-2025-04-16"
provider_name"OpenAI"
status200
api_type"completions"
id"gen-1771497640-iEnYCmO4KaQAX3N1ScDh"
upstream_id"resp_07d4752c13dfb2ab016996e8a8b9908193834b8155d34dce94"
total_cost0.0324665
cache_discount(null)
upstream_inference_cost0
provider_name"OpenAI"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags20
adverbTagCount1
adverbTags
0"she asked softly [softly]"
dialogueSentences56
tagDensity0.357
leniency0.714
rawRatio0.05
effectiveRatio0.036
89.38% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount942
totalAiIsmAdverbs2
found
0
adverb"softly"
count2
highlights
0"softly"
100.00% AI-ism character names
Target: 0 AI-default names (16 tracked, −20% each)
codexExemptions
0"Blackwood"
found(empty)
100.00% AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions(empty)
found(empty)
9.77% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount942
totalAiIsms17
found
0
word"echoed"
count2
1
word"silk"
count1
2
word"traced"
count1
3
word"flicker"
count1
4
word"tracing"
count1
5
word"silence"
count2
6
word"electric"
count1
7
word"pulse"
count1
8
word"fluttered"
count1
9
word"flicked"
count1
10
word"footsteps"
count1
11
word"sentinel"
count1
12
word"glint"
count1
13
word"echo"
count1
14
word"trembled"
count1
highlights
0"echoed"
1"silk"
2"traced"
3"flicker"
4"tracing"
5"silence"
6"electric"
7"pulse"
8"fluttered"
9"flicked"
10"footsteps"
11"sentinel"
12"glint"
13"echo"
14"trembled"
66.67% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches2
maxInWindow2
found
0
label"eyes widened/narrowed"
count1
1
label"clenched jaw/fists"
count1
highlights
0"eyes widened"
1"clenched her jaw"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells1
narrationSentences103
matches
0"A flicker of regret"
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount1
narrationSentences103
filterMatches(empty)
hedgeMatches
0"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences138
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen22
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords939
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions15
unquotedAttributions0
matches(empty)
0.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions76
wordCount671
uniqueNames9
maxNameDensity5.07
worstName"Aurora"
maxWindowNameDensity8.5
worstWindowName"Aurora"
discoveredNames
Carter1
Raven1
Nest1
Blackwood1
Aurora34
Eva28
Silas8
Evan1
Cruel1
persons
0"Carter"
1"Raven"
2"Blackwood"
3"Aurora"
4"Eva"
5"Silas"
6"Evan"
places(empty)
globalScore0
windowScore0
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences53
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount939
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences138
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs63
mean14.9
std9.23
cv0.619
sampleLengths
011
156
216
341
413
533
612
714
828
98
1012
1115
1218
1310
1427
159
1618
174
1824
1919
209
2111
227
2322
249
257
2614
2714
2835
296
3027
3120
329
337
3414
3510
366
3716
389
3919
4010
4111
4210
438
446
4513
4620
4714
485
4919
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences103
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs132
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount2
semicolonCount0
flaggedSentences1
totalSentences138
ratio0.007
matches
0"A man stepped in—overcoat, hat low—his pockets dimpling with something metallic."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount674
adjectiveStacks0
stackExamples(empty)
adverbCount10
adverbRatio0.01483679525222552
lyAdverbCount2
lyAdverbRatio0.002967359050445104
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences138
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences138
mean6.8
std3.98
cv0.585
sampleLengths
011
116
213
313
414
516
63
722
88
98
106
117
1210
1320
143
1510
162
176
185
193
207
216
2215
238
246
256
265
276
284
294
3014
317
323
334
343
3511
369
373
386
393
408
415
422
434
442
452
468
4712
488
4911
64.25% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats3
diversityRatio0.39855072463768115
totalSentences138
uniqueOpeners55
73.26% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences91
matches
0"Then Eva raised her glass."
1"Then the bar door swung"
ratio0.022
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount19
totalSentences91
matches
0"She’d ducked beneath the green"
1"She settled onto the stool"
2"She paused, her gaze flicking"
3"He didn’t approach."
4"She hadn’t used it since"
5"She turned back to her"
6"She tapped the bar, tracing"
7"She stared at her reflection"
8"She counted the seconds by"
9"He placed them in front"
10"She stared at the wood"
11"she said, voice thin"
12"She smoothed a strand of"
13"she asked softly"
14"His limp made it obvious."
15"He stopped behind them, silent"
16"She glanced at Silas."
17"He paused at the threshold,"
18"She pressed her back against"
ratio0.209
0.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount85
totalSentences91
matches
0"The ice clinked as she"
1"Aurora Carter stared at the"
2"She’d ducked beneath the green"
3"Silas Blackwood hovered at the"
4"Tonight every footstep echoed against"
5"the voice said, smooth as"
6"Aurora looked up."
7"Eva stood framed in the"
8"Platinum at her temples made"
9"She settled onto the stool"
10"Aurora said, voice careful"
11"Eva traced the rim of"
12"She paused, her gaze flicking"
13"Aurora flexed her fingers as"
14"Silas cleared his throat behind"
15"Plates rattled in the back."
16"He didn’t approach."
17"Aurora said, the nickname slipping"
18"She hadn’t used it since"
19"A flicker of regret flitted"
ratio0.934
100.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount2
totalSentences91
matches
0"Before Aurora could answer, Silas’s"
1"Even he did not meet"
ratio0.022
71.43% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences20
technicalSentenceCount2
matches
0"Aurora flexed her fingers as if she could erase time."
1"She stared at the wood grain as if it might tell her a secret."
25.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags20
uselessAdditionCount4
matches
0"Aurora said, voice careful"
1"Aurora said, the nickname slipping out"
2"she said, voice thin"
3"Eva said, voice distant"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags11
fancyCount1
fancyTags
0"Aurora laughed (laugh)"
dialogueSentences56
tagDensity0.196
leniency0.393
rawRatio0.091
effectiveRatio0.036
83.3252%