Run: 2026-02-24-01KJ8WTJBAS9EHE4AW31HSDWBF

Run Details

Duration:
2m 55s
Cost:
$0.161550
Provider:
Anthropic

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 glass slipped. Rory caught it before it hit the floor, fingers closing around the cold pint glass on instinct, and she set it back on the tray harder than necessary. The couple at table four didn't notice. They were arguing in hushed, knife-edged tones, the way couples do when they're trying not to make a scene and making one anyway. She'd been watching them for twenty minutes, partly out of boredom, partly because the woman's red wool coat reminded her of something she couldn't quite place. The Raven's Nest was doing modest Thursday business. A cluster of office workers at the bar with loosened ties, a group of tourists near the door who kept photographing the old maps on the walls as though they were in a gallery. Silas moved behind the bar with the unhurried efficiency of a man who'd operated in smaller, more dangerous spaces, his grey-streaked hair catching the amber light above the taps. He raised an eyebrow as she returned the tray. "You're loitering." "I live here." "Upstairs. Down here, you're blocking my sightline." She leaned on the bar anyway, pulling her hair back. The crescent scar on her left wrist caught the light, pale against her skin. She'd been restless all evening, for no reason she could name. That was when she saw Meg. Megan Ashworth. Same long auburn hair, though straightened now, professional. Same wide-set grey eyes scanning the room with the focused look of someone who never entered a space without calculating exits. She'd always done that. Rory used to tease her for it, back in Cardiff, back when they shared a flat on Cathays Terrace and survived on tinned soup and library coffee. Meg hadn't seen her yet. For three full seconds, Rory considered the door. Then Meg's gaze swept the room, landed, and froze. "Aurora Carter." She said it like a verdict. Rory managed a smile. "The one and only." Meg crossed the room in quick, confident strides. A grey blazer and tailored trousers, polished shoes, a watch that cost more than Rory earned in a month. Three years had filed away every soft edge Meg used to carry. "What are you doing here?" "I live here. Upstairs." Meg glanced at the ceiling, then back. "You're joking." "Above a bar in Soho. Not exactly Chambers-level accommodation, I know." The laugh that escaped Meg was genuine, surprised, a little like the old version of her. They found a table near the wall, beneath a black-and-white photograph of a city neither of them could identify, and Silas appeared with two glasses of wine without being asked. Old habit, reading rooms. "You look well," Meg said. "You look like you've become your mother." "God." Meg tugged at her blazer lapel with a rueful grin. "I have, haven't I." Then the grin settled into something more careful. "I've been trying to find you. Your Cardiff number's dead. Your mum wouldn't say where you'd gone." "Mum's protective." "Mum's tight-lipped." Meg turned her wine glass by its stem. "Eva knew. She said you were fine. Settled. Working." "All of those things." "Delivering food." Rory took a sip. "Among other things." The pause between them stretched long enough to become its own conversation. Meg had joined a firm in Bristol straight after university, moved to London eighteen months ago. Commercial litigation. Long hours, solid pay, the kind of career trajectory that Rory had once mapped on a university library napkin and pinned to their kitchen corkboard. Meg described it all without quite bragging, but without apology either. That seemed fair. She'd earned it. "You were better at Property Law than I was," Meg said. "I hated Property Law." "You got a First." "I hated it with exceptional thoroughness." Meg smiled, but her eyes stayed measured. She was building to something. She'd always built to things, circling a point the way a bird circles a wire, looking for the safe place to land. "When you left," she said, "we all assumed it was Evan." There it was. The name settled on the table between them with the weight of something dropped from a height. "We?" Rory said. "The group. Sioned, Dafydd, me. We thought, right, she's finally had enough, she'll come back in a month." Meg's fingers tightened around her glass. "You weren't, though." "No." "And you never said why." The couple at table four had stopped arguing. The man stared at the floor now with the empty look of someone who'd run out of ammunition. The woman's red coat was buttoned to the collar, ready to leave. Rory watched them. "There wasn't much to say." "Rory." Meg's voice dropped. That register meant honesty was coming. It used to be Rory's favourite thing about her. "I'm not trying to pry. I just..." She exhaled. "I always felt like I missed something. A chapter I wasn't given." "You didn't miss anything good." "That's not an answer." "No," Rory said. "It's not." A car alarm started outside, then stopped. Behind the bar, glass clinked against glass. The tourist group near the door burst into laughter over someone's phone. Meg reached into her blazer pocket and placed a business card on the table. Morgan & Ashworth. Megan Ashworth, Associate. "Morgan's her married name. Dafydd and Sioned are engaged. Everyone sort of... continued." She studied Rory's face and something in her own softened. "Not everyone gets to know where you ended up." "I'm fine where I ended up." "I know you are." Meg's smile was small, genuine, a little sad. "I also know you're the most stubborn woman I've ever met, and if you'd wanted to be found, you'd have left a trail." "You found me." "Accidentally." The red-coat woman stood and left without looking back. Her partner stayed behind, staring at the space she'd left. Meg watched him for a moment, then looked back at Rory, and the careful, circling look returned. "Evan's in London." The music didn't cut out. Nobody looked up. The world continued precisely as it had been. Rory's hand rested flat on the table. "He's at a firm in Canary Wharf," Meg said, her voice flattening into careful neutrality, the tone of someone who has realised they've stepped onto ice and doesn't know its thickness. "He mentioned he thought he'd spotted you once. Near Soho. I didn't think anything of it at the time, but then I walked in here tonight and—" "He sent you." "What? No." Meg shook her head. "No, Rory, I was meeting a client two streets over. I just wanted a drink." "Did he ask you to look for me?" "I haven't spoken to him in six months." Her jaw stayed loose, honest. Meg had always been a dreadful liar, her jaw tightening around untruths like a tell in cards. "I swear. I walked in and there you were. That's all this is." Rory looked at her. Believed her. Which meant something worse. It meant Evan had spotted her himself. Had done the searching himself. Had told Meg, the way you mention a coincidence, just to see what information floated back. Her phone lit up between them on the table. Unknown number. London area code. Meg stared at the screen. Rory didn't move.
created_at"2026-02-24T22:37:55.959Z" 2/24/2026, 10:37:55 PM
model"anthropic/claude-4.6-sonnet-20260217"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency572
moderation_latency(null)
generation_time174738
tokens_prompt4618
tokens_completion4779
native_tokens_prompt4735
native_tokens_completion9823
native_tokens_completion_images(null)
native_tokens_reasoning2920
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"stop"
usage0.16155
router(null)
provider_responses
0
endpoint_id"6d408764-7dd7-4626-bb87-a6cc1589bc86"
id"msg_01B1eH3f3nYQxZwLbpGVffVg"
is_byokfalse
latency561
model_permaslug"anthropic/claude-4.6-sonnet-20260217"
provider_name"Anthropic"
status200
api_type"completions"
id"gen-1771972675-eHvHlNqWbmssDQfNBBUE"
upstream_id"msg_01B1eH3f3nYQxZwLbpGVffVg"
total_cost0.16155
cache_discount(null)
upstream_inference_cost0
provider_name"Anthropic"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags16
adverbTagCount1
adverbTags
0"Meg's fingers tightened around [around]"
dialogueSentences54
tagDensity0.296
leniency0.593
rawRatio0.063
effectiveRatio0.037
95.83% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1200
totalAiIsmAdverbs1
found
0
adverb"precisely"
count1
highlights
0"precisely"
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)
79.17% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1200
totalAiIsms5
found
0
word"eyebrow"
count1
1
word"scanning"
count1
2
word"calculating"
count1
3
word"measured"
count1
4
word"weight"
count1
highlights
0"eyebrow"
1"scanning"
2"calculating"
3"measured"
4"weight"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches0
maxInWindow0
found(empty)
highlights(empty)
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences90
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences90
filterMatches
0"look"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences127
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen34
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1200
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions18
unquotedAttributions0
matches(empty)
0.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions56
wordCount864
uniqueNames14
maxNameDensity2.78
worstName"Meg"
maxWindowNameDensity5
worstWindowName"Meg"
discoveredNames
Raven1
Nest1
Thursday1
Meg24
Ashworth3
Cardiff1
Cathays1
Terrace1
Rory16
Silas2
Bristol1
London2
Associate1
Evan1
persons
0"Raven"
1"Meg"
2"Ashworth"
3"Rory"
4"Silas"
5"Evan"
places
0"Cardiff"
1"Cathays"
2"Terrace"
3"Bristol"
4"London"
globalScore0.111
windowScore0
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences56
glossingSentenceCount1
matches
0"quite place"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1200
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences127
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs71
mean16.9
std19.21
cv1.137
sampleLengths
03
184
280
32
43
57
635
76
862
95
108
119
128
138
1439
155
164
179
1811
1950
205
217
2240
232
2419
254
262
277
2812
2960
3011
314
324
336
3434
3511
363
3717
383
3927
401
415
4238
433
445
4540
465
474
485
4926
97.47% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences90
matches
0"being asked"
1"was buttoned"
29.06% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount4
totalVerbs156
matches
0"were arguing"
1"was doing"
2"was building"
3"was coming"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences127
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount870
adjectiveStacks0
stackExamples(empty)
adverbCount28
adverbRatio0.03218390804597701
lyAdverbCount3
lyAdverbRatio0.0034482758620689655
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences127
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences127
mean9.45
std7.52
cv0.796
sampleLengths
03
128
27
323
426
58
634
729
89
92
103
117
1210
1314
1411
156
162
178
1821
194
2027
215
228
239
248
254
264
278
2819
2912
305
314
327
332
3411
3516
3630
374
385
397
4011
4112
4217
432
4410
459
464
472
484
493
52.76% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats13
diversityRatio0.3779527559055118
totalSentences127
uniqueOpeners48
83.33% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences80
matches
0"Then Meg's gaze swept the"
1"Then the grin settled into"
ratio0.025
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount17
totalSentences80
matches
0"They were arguing in hushed,"
1"She'd been watching them for"
2"He raised an eyebrow as"
3"She leaned on the bar"
4"She'd been restless all evening,"
5"She'd always done that."
6"She said it like a"
7"They found a table near"
8"She'd earned it."
9"She was building to something."
10"She'd always built to things,"
11"It used to be Rory's"
12"She studied Rory's face and"
13"Her partner stayed behind, staring"
14"Her jaw stayed loose, honest"
15"It meant Evan had spotted"
16"Her phone lit up between"
ratio0.213
41.25% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount67
totalSentences80
matches
0"The glass slipped."
1"Rory caught it before it"
2"The couple at table four"
3"They were arguing in hushed,"
4"She'd been watching them for"
5"The Raven's Nest was doing"
6"A cluster of office workers"
7"Silas moved behind the bar"
8"He raised an eyebrow as"
9"She leaned on the bar"
10"The crescent scar on her"
11"She'd been restless all evening,"
12"That was when she saw"
13"She'd always done that."
14"Rory used to tease her"
15"Meg hadn't seen her yet."
16"She said it like a"
17"Rory managed a smile."
18"Meg crossed the room in"
19"A grey blazer and tailored"
ratio0.838
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences80
matches(empty)
ratio0
93.60% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences29
technicalSentenceCount2
matches
0"A cluster of office workers at the bar with loosened ties, a group of tourists near the door who kept photographing the old maps on the walls as though they wer…"
1"Silas moved behind the bar with the unhurried efficiency of a man who'd operated in smaller, more dangerous spaces, his grey-streaked hair catching the amber li…"
93.75% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags16
uselessAdditionCount1
matches
0"Her jaw stayed, honest"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags7
fancyCount0
fancyTags(empty)
dialogueSentences54
tagDensity0.13
leniency0.259
rawRatio0
effectiveRatio0
85.5404%