Run: 2026-02-19-01KHTRM5YS9DWAR1ZZSWYA7HMG

Run Details

Model:
GPT-4.1
Duration:
40.2s
Cost:
$0.014728
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
“Put that back, you prat, this isn’t a buffet.” Aurora Carter froze, pint glass half-raised, as the owner’s voice cut through the low radio din. Someone else had beaten her to it—a red-cheeked banker type with his hand still hovering in the peanut bowl, eyes darting. She exhaled, but the moment of borrowed bravado stuck. At the far end, Silas Blackwood’s gaze slipped from customer to customer, collecting debts and secrets with equal indifference. Behind the bar: wavering neon, muted shouts from Soho’s street, the memory of laughter lingering in the worn timber. Aurora fitted in like a knife in a cutlery drawer—useful, faintly menacing, never quite belonging. She slid her glass against the bar, searching for a clean spot among the scorch marks and ring stains. Then: a shape, a voice. Unmistakable, despite the altered edge. “Rory? Bloody hell, is that actually you?” Eva Penrose. The hair had changed—tied back, longer, darker than Aurora remembered, but the voice still carved through memory like a carving knife, each beat too familiar. “I’ll owe you five quid if you guess what I’m drinking.” Aurora’s heart stuttered. She looked up, slow—a gambler revealing a losing hand. “Milk and gin, if it’s still you.” Eva’s eyebrow twitched. “Close enough. Don’t tell anyone.” Her lips shaped a sly smile, but the warmth of old afternoons at university had weathered into something harder. “Wouldn’t do for clients to know I’m off the wagon.” Aurora signalled for another pint, fingers drumming the bar top. “Clients? Thought you swore off law after all that—” Her words stumbled over memories, the old Cardiff library, fluorescent ticks on fat tomes, Eva’s laugh echoing in stacks. Eva’s jaw tightened. “Not the criminal sort. Corporate caseload. Paper cuts instead of stab wounds.” “Less blood. More soul.” Eva scanned Aurora up and down, a surgeon eyeing an open wound. “So this is where you ended up then.” Her gaze snagged on the battered boots and the Golden Empress leaflet poking from Aurora’s bag. “Delivering to the Soho drunks?” Aurora shrugged. “Pays for chips and rent. London’s expensive, in case you haven’t heard.” She met Eva’s gaze, let the surface coolness settle. “What brings you to this end of Soho anyway? Can’t imagine mergers and acquisitions take you past the kebab shops often.” Eva hesitated, the barest catch. “Looking for a friend. Except she turned into a spectre.” A thin silence pooled between them. Near the door, Silas set down his cane and regarded the pair over reading glasses, invisible judge in an invisible court. “You could’ve called,” Aurora said. “I did. Once. Got your old burner, some bloke with a Brummie accent telling me you’d legged it. Figured you changed numbers, or just changed.” Eva tilted her head, searching for the younger Rory buried beneath six years of silence. “You could’ve called, too.” “I didn’t fancy walking into that graveyard.” Eva’s lips parted, as if she wanted to say more—then closed. She picked a peanut from the bowl, rolled it between her fingers, but didn’t eat it. “I still see him sometimes, you know. Evan. Cardiff’s small when it wants to be. He’s in better shape than he deserves.” Aurora’s stomach clenched. The crescent scar on her left wrist itched in memory, hot iron beneath her sleeve. “People like him always land on two feet. Cats with claws.” “You could testify, you know. Police’d fall over themselves for some ammunition.” “I’m done with fights that end with me in casualty, Eva.” The words came quiet, cold. “There’s no winning. Just smaller failures.” Eva laughed, but it sounded wrong—like laughter in an empty church. “You always had a way of making it sound cleverer than it was.” Behind them, the jukebox skipped. The soft jazz warped into a tune Aurora half-recognised from a night when Eva had spun her around a dance floor until she’d forgotten her own name. Eva pulled out her phone, studied the homescreen, and then set it down screen-first. Old habit. “So what now? Delivery girl forever?” “’S honest work.” Aurora sipped her pint, bitterness blooming at the back of her mouth. “And I get a discount on Kung Pao.” Eva looked at her, really looked, eyes flitting from the dark circles under Aurora’s eyes to the loose thread at her cuff. “You had plans, you know?” she said, words stretched thin by the years. “You talked about moving to Paris. Working for the court. Shouting down corrupt solicitors in a tailored suit.” “Plans change.” “No, people change. Plans just… sit there. Gather dust.” Aurora bristled. “Easy for you to say. Looks like you got all you wanted—posh job, smart coat. Bet no one calls you ‘Laila’ in the Tesco queue anymore.” Eva’s tongue darted between her teeth. “There’s always a price, Rory. Sometimes you don’t see the bill until you’ve paid it for years.” Aurora found herself watching the old scar, chalky line half-hidden against her wrist as she twisted the glass. The weight of old promises pressed in, familiar as bruises. “You lost weight,” Eva said, suddenly. “You lost yours in your voice.” Aurora’s answer snapped, sharper than she meant. Eva winced, but pushed on. “Just tell me you’re all right. Or if you aren’t, tell me that, at least.” Aurora set her glass down with a thunk. “You want the truth? I’m surviving. I work, I sleep, I try not to think about Cardiff, or Evan, or anything further back than yesterday. That’s what’s left.” “I came because I thought maybe—” Eva paused, brushing imaginary dust from the bar, “—I don’t know. I thought you might want an ally again.” “I don’t need saving.” A swallow, sharp as gin. “No. But you might want company. Not everyone gets to walk alone and come out whole.” A pause. Silas passed, cane clicking, and nodded to Aurora. An acknowledgement, no comfort. Aurora looked away, toward the racks of old maps behind the bar, rivers cutting ancient routes through broken lands. “You haven’t changed as much as you think,” she said. “You still try to fix what’s left behind.” Eva’s smile this time was brittle, no softness left. “And you still pretend you’re unbreakable.” They sat. The bar clock ticked. Aurora found herself tracing the rim of her glass, the friction almost a comfort. “You want to run?” Eva asked, eyes searching for a challenge. Aurora forced a grin. “Only when someone chases.” Neither moved to leave. The silence built, thicker than smoke. Somewhere nearby, a bottle shattered, muted curse following. Then: a man’s shadow slid across the neon-lit door, stopping. Aurora’s attention sharpened, fight or flight humming under skin. Loud knock, too precise. Silas’s eyes narrowed, his hand closing round the cane like something heavier. Eva straightened. “You expecting anyone?” Aurora shook her head once. And the front door burst wide open.
created_at"2026-02-19T10:55:10.302Z" 2/19/2026, 10:55:10 AM
model"openai/gpt-4.1-2025-04-14"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency260
moderation_latency(null)
generation_time39994
tokens_prompt4618
tokens_completion1897
native_tokens_prompt4132
native_tokens_completion1576
native_tokens_completion_images0
native_tokens_reasoning0
native_tokens_cached4096
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"
usage0.014728
router(null)
provider_responses
0
endpoint_id"c235abe8-11cc-42d3-95ad-72f4d198287a"
id"resp_035a12719997f8f7016996ec0e620c8193ab6328f7d9420dc6"
is_byokfalse
latency113
model_permaslug"openai/gpt-4.1-2025-04-14"
provider_name"OpenAI"
status200
api_type"completions"
id"gen-1771498510-j3anM1QZcpwbovDsCvII"
upstream_id"resp_035a12719997f8f7016996ec0e620c8193ab6328f7d9420dc6"
total_cost0.014728
cache_discount0.006144
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
totalTags14
adverbTagCount0
adverbTags(empty)
dialogueSentences46
tagDensity0.304
leniency0.609
rawRatio0
effectiveRatio0
91.27% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1146
totalAiIsmAdverbs2
found
0
adverb"really"
count1
1
adverb"suddenly"
count1
highlights
0"really"
1"suddenly"
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)
30.19% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1146
totalAiIsms16
found
0
word"wavering"
count1
1
word"familiar"
count2
2
word"eyebrow"
count1
3
word"warmth"
count1
4
word"echoing"
count1
5
word"scanned"
count1
6
word"silence"
count3
7
word"stomach"
count1
8
word"dance"
count1
9
word"weight"
count2
10
word"tracing"
count1
11
word"shattered"
count1
highlights
0"wavering"
1"familiar"
2"eyebrow"
3"warmth"
4"echoing"
5"scanned"
6"silence"
7"stomach"
8"dance"
9"weight"
10"tracing"
11"shattered"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"eyes widened/narrowed"
count1
highlights
0"eyes narrowed"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences71
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences71
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences103
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen40
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1134
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions14
unquotedAttributions0
matches(empty)
0.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions55
wordCount674
uniqueNames11
maxNameDensity3.41
worstName"Aurora"
maxWindowNameDensity5
worstWindowName"Aurora"
discoveredNames
Carter1
Silas4
Blackwood1
Soho1
Penrose1
Aurora23
Cardiff1
Eva20
Golden1
Empress1
Rory1
persons
0"Carter"
1"Silas"
2"Blackwood"
3"Penrose"
4"Aurora"
5"Eva"
6"Rory"
places
0"Soho"
1"Cardiff"
globalScore0
windowScore0
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences44
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1134
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences103
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs52
mean21.81
std13.55
cv0.622
sampleLengths
09
146
253
329
47
538
612
77
837
938
1015
114
1241
1344
1415
1527
165
1744
187
1949
2029
2112
2222
2324
2432
2522
2623
2722
2831
292
309
3128
3223
3328
346
3513
3620
3736
3825
394
4021
4114
4237
4315
4420
4511
468
4718
4835
495
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences71
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs125
matches(empty)
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount6
semicolonCount0
flaggedSentences6
totalSentences103
ratio0.058
matches
0"Someone else had beaten her to it—a red-cheeked banker type with his hand still hovering in the peanut bowl, eyes darting."
1"Aurora fitted in like a knife in a cutlery drawer—useful, faintly menacing, never quite belonging."
2"The hair had changed—tied back, longer, darker than Aurora remembered, but the voice still carved through memory like a carving knife, each beat too familiar."
3"She looked up, slow—a gambler revealing a losing hand."
4"Eva’s lips parted, as if she wanted to say more—then closed."
5"Eva laughed, but it sounded wrong—like laughter in an empty church."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount685
adjectiveStacks0
stackExamples(empty)
adverbCount16
adverbRatio0.02335766423357664
lyAdverbCount4
lyAdverbRatio0.00583941605839416
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences103
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences103
mean11.01
std7.57
cv0.688
sampleLengths
09
116
221
39
419
519
615
719
85
95
107
112
1225
1311
143
159
167
173
1824
1910
2010
2128
223
2312
244
2512
2624
275
282
2921
3021
315
3210
336
3421
355
3640
374
387
3911
4016
4122
423
4315
4411
4512
4616
476
4811
4913
64.08% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats4
diversityRatio0.4077669902912621
totalSentences103
uniqueOpeners42
53.76% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences62
matches
0"Somewhere nearby, a bottle shattered,"
ratio0.016
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount9
totalSentences62
matches
0"She exhaled, but the moment"
1"She slid her glass against"
2"She looked up, slow—a gambler"
3"Her lips shaped a sly"
4"Her words stumbled over memories,"
5"Her gaze snagged on the"
6"She met Eva’s gaze, let"
7"She picked a peanut from"
8"she said, words stretched thin"
ratio0.145
40.65% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount52
totalSentences62
matches
0"Aurora Carter froze, pint glass"
1"Someone else had beaten her"
2"She exhaled, but the moment"
3"Aurora fitted in like a"
4"She slid her glass against"
5"The hair had changed—tied back,"
6"Aurora’s heart stuttered."
7"She looked up, slow—a gambler"
8"Eva’s eyebrow twitched."
9"Her lips shaped a sly"
10"Aurora signalled for another pint,"
11"Her words stumbled over memories,"
12"Eva’s jaw tightened."
13"Eva scanned Aurora up and"
14"Her gaze snagged on the"
15"She met Eva’s gaze, let"
16"Eva hesitated, the barest catch."
17"A thin silence pooled between"
18"Eva tilted her head, searching"
19"Eva’s lips parted, as if"
ratio0.839
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences62
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences24
technicalSentenceCount0
matches(empty)
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags14
uselessAdditionCount4
matches
0"The words came, cold"
1"Aurora sipped, bitterness blooming at the back of her mouth"
2"Eva said, suddenly"
3"Eva asked, eyes searching for a challenge"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags6
fancyCount1
fancyTags
0"Aurora’s answer snapped (snap)"
dialogueSentences46
tagDensity0.13
leniency0.261
rawRatio0.167
effectiveRatio0.043
79.3317%