Run: 2026-04-24-01KPZV5Z022DPBJYRE6QN8NX5R

Run Details

Duration:
33.4s
Cost:
$0.094820
Provider:
Amazon Bedrock

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 pint glass slipped from Rory's hand the moment she heard the laugh. Not the glass she was drying, thankfully, but the empty one she'd been ferrying toward the sink. It bounced off the rubber mat behind the bar and rolled, miraculously intact, into the ice well. Silas had asked her to cover an hour while he ran to the cash and carry. An hour. She could manage an hour. That was before the laugh. It came from the third stool along, where a woman in a camel coat had been nursing a gin and tonic for the last twenty minutes without looking up from her phone. The laugh was short, sharp, too loud for the room, and Rory knew it the way you know a song from the first bar. "Mei." The woman's head lifted. For a second there was nothing on her face, just the polite blankness strangers wear in London bars. Then the blankness cracked. "Oh my God. Rory?" "Rory now, is it? Not Aurora?" "Nobody's called me Aurora since my mum died." It landed between them, that sentence, before Rory had decided whether to offer it. Mei's mouth opened and closed. The gin and tonic went down in one long swallow. "Jen. I'm so sorry. I didn't-" "Three years ago. You wouldn't have known." She reached for the bottle of Bombay and refilled Mei's glass without asking. "On the house. Consider it a reunion tax." Mei was wearing a coat that cost more than Rory's month's rent. The bag on the stool beside her had a small gold clasp in the shape of a horse's head. Her hair, which had been a mess of bleached ends and black roots the last time Rory had seen her, sat now in a glossy bob that looked like it had been cut by someone who worked out of a townhouse rather than a salon. Even her hands had changed. The chewed nails were gone. In their place, a neat oval manicure the colour of old blood. "You work here." "I live here. Well, above here. Silas is, he's my landlord. Sort of." "Silas." "The owner. You'll meet him in about forty minutes if you stick around." She leaned on the bar, elbows finding the grooves they'd found a hundred times before. "Which you will, because you haven't told me anything yet, and I haven't seen you since, Christ, since the Lamb and Flag." "That was Eva's birthday." "Which one?" "Twenty-third." Rory did the sum. Four years. Four years since the garden of a pub in Covent Garden, since Mei Lin had been reading for a PhD in something Rory could never remember the name of and complaining about her supervisor and kissing a boy with a septum ring in the smoking area. Four years was not so long. Four years was a lifetime. "So what's the glossy magazine version." "Sorry?" "Of your life. The one you tell people at dinner parties." Mei laughed again, but this one was different. Quieter. It got stuck somewhere in her throat and came out more like a cough. "I left the PhD." "Yeah, I figured. The coat." "The coat?" "Academics don't dress like that. Academics dress like they lost a bet with a charity shop." "I married someone." There it was. Rory had felt it coming the way you feel a train before you hear it, through the soles of your feet. She kept her face doing the thing her mother used to do when clients told her embarrassing things on the phone, the small attentive smile that gave nothing back. "Someone I know?" "No. He's, he's older. He does something in, honestly, Rory, I've been married eighteen months and I still can't explain what he does. Something with hedge funds and something with property." The ice in her glass clicked. "We live in Chelsea." "Chelsea." "Don't." "I didn't say anything." "You said Chelsea like it was a venereal disease." "I said Chelsea like it was Chelsea." Mei looked down at her hands. The ring on the fourth finger was the size of a small sweet, a square-cut thing with smaller stones huddled around it. It caught the green from the neon sign outside and threw it back in odd green splinters onto the bar top. "What about you?" "I deliver Chinese food on a moped." "Shut up." "Six nights a week. Yu-Fei at the Golden Empress. She pays cash and doesn't ask questions, which, trust me, is what you want from an employer." "You were going to be a barrister." "My dad was going to be a barrister. I was going to do whatever got him off my back for three years." "And the fourth year?" Rory paused with her hand on the gin bottle. She hadn't been planning a drink. She poured one anyway, a short measure, no tonic, and knocked it back in the same motion. "The fourth year I met Evan." Mei's face did something complicated. Rory watched it happen in fragments, the small downward pull at the corner of her mouth, the way her eyes flicked to Rory's left wrist where the crescent scar sat white against the inside skin. The scar was from when she was nine. But Mei's eyes had gone there anyway, because that is what people do when they hear a name like Evan's in a voice like the one Rory had used. "I heard things. About him. Later." "From who?" "Eva. She, she rang me. A couple of times." "And you didn't ring me." "Rory." "I'm not, I'm just asking. I'm not making a thing of it." "You're making a thing of it." "Bit, yeah." The silence that settled was not the silence of strangers. It was the silence of two people who had once sat on the floor of a student flat at four in the morning eating cold chips and telling each other the worst things they'd ever done, and who now sat three feet apart on either side of a bar and did not know what to do with their hands. "I was a coward," Mei said. "I knew something was wrong. Eva told me. I told myself I'd call at the weekend, and then I told myself I'd call after Christmas, and then I met Daniel and, and it got easier to not call." "Daniel's the hedge fund." "Daniel's the hedge fund." "He makes it easier to not call people." "He makes a lot of things easier." Rory picked up the glass she'd dropped earlier, fished it out of the ice, and set it under the tap. Water ran. She watched it run. "I got out," she said. "In case you were going to ask. I got out, I came to London, I live above a bar in Soho, and some nights I make ninety quid in tips and some nights I get followed home by a bloke in a Vauxhall Astra and I carry a screwdriver in my jacket pocket. That's the update." "Rory." "Don't cry in my bar, Mei. Silas hates it when they cry." "I'm not crying." "You're about to." "I'm allowed." "You're really not." Mei laughed, the old laugh this time, the one that had made Rory drop the pint glass in the first place, and for a moment she was twenty-one again and her hair was bleached and there was a boy with a septum ring somewhere and nothing had happened yet that couldn't be undone. Then the bell above the door rang, and the cold came in, and a man in a good coat stepped onto the mat and said, in a voice that was used to being listened to, "Darling. I've been calling you." Mei's hand closed around her phone. Rory put both palms flat on the bar and looked at the man, and at Mei, and at the door behind him, and felt the screwdriver in her jacket pocket like a small iron tooth.
created_at"2026-04-24T13:34:31.456Z" 4/24/2026, 1:34:31 PM
model"anthropic/claude-4.7-opus-20260416"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency759
moderation_latency(null)
generation_time33295
tokens_prompt4618
tokens_completion1880
native_tokens_prompt6499
native_tokens_completion2493
native_tokens_completion_images(null)
native_tokens_reasoning0
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
num_fetches(null)
web_search_engine(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"end_turn"
usage0.09482
router(null)
provider_responses
0
endpoint_id"0fa65117-00d9-4835-808d-9b68041d9ce4"
id"34406851-29b5-4022-b401-308272f18cef"
is_byokfalse
latency756
model_permaslug"anthropic/claude-4.7-opus-20260416"
provider_name"Amazon Bedrock"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer(null)
request_id"req-1777037671-gL6lCLnAxqdgF4jDknYD"
session_id(null)
api_type"completions"
id"gen-1777037671-XQCD9ewVC5xD8u2Ug7kX"
upstream_id"34406851-29b5-4022-b401-308272f18cef"
total_cost0.09482
cache_discount(null)
upstream_inference_cost0
provider_name"Amazon Bedrock"
response_cache_source_id(null)

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags6
adverbTagCount0
adverbTags(empty)
dialogueSentences62
tagDensity0.097
leniency0.194
rawRatio0
effectiveRatio0
96.22% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1323
totalAiIsmAdverbs1
found
0
adverb"really"
count1
highlights
0"really"
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)
84.88% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1323
totalAiIsms4
found
0
word"flicked"
count1
1
word"silence"
count3
highlights
0"flicked"
1"silence"
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
narrationSentences56
matches(empty)
40.82% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount4
hedgeCount0
narrationSentences56
filterMatches
0"know"
1"feel hear"
2"hear"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences112
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen59
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1323
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions18
unquotedAttributions0
matches(empty)
61.03% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions38
wordCount843
uniqueNames10
maxNameDensity1.78
worstName"Rory"
maxWindowNameDensity2.5
worstWindowName"Rory"
discoveredNames
Rory15
London1
Bombay1
Mei12
Covent1
Garden1
Lin1
PhD1
Evan1
Four4
persons
0"Rory"
1"Mei"
2"Lin"
3"PhD"
4"Evan"
places
0"London"
1"Covent"
2"Garden"
3"Four"
globalScore0.61
windowScore0.833
84.21% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences38
glossingSentenceCount1
matches
0"looked like it had been cut by someone wh"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches1
per1kWords0.756
wordCount1323
matches
0"Not the glass she was drying, thankfully, but the empty one she'd been ferrying toward the sink"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences112
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs74
mean17.88
std22.04
cv1.233
sampleLengths
013
162
256
31
426
54
66
78
829
96
1028
1198
123
1313
141
1550
164
172
181
1963
206
211
2211
2323
244
255
262
2716
283
2953
303
3141
321
331
344
359
367
3749
383
397
402
4126
427
4322
444
4532
466
4777
486
492
80.20% Passive voice overuse
Target: ≤2% passive sentences
passiveCount4
totalSentences56
matches
0"were gone"
1"got stuck"
2"was bleached"
3"being listened"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount2
totalVerbs136
matches
0"was drying"
1"was wearing"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences112
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount845
adjectiveStacks0
stackExamples(empty)
adverbCount25
adverbRatio0.029585798816568046
lyAdverbCount2
lyAdverbRatio0.002366863905325444
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences112
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences112
mean11.81
std12.71
cv1.076
sampleLengths
013
117
217
316
42
55
65
732
824
91
104
1118
124
134
146
158
1614
175
1810
196
2020
218
2212
2319
2445
255
265
2712
283
2913
301
3128
3222
334
342
351
364
372
3846
396
405
416
421
4311
448
451
4614
474
485
492
65.18% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats7
diversityRatio0.42857142857142855
totalSentences112
uniqueOpeners48
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount3
totalSentences50
matches
0"Then the blankness cracked."
1"Even her hands had changed."
2"Then the bell above the"
ratio0.06
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount14
totalSentences50
matches
0"It bounced off the rubber"
1"She could manage an hour."
2"It came from the third"
3"It landed between them, that"
4"She reached for the bottle"
5"Her hair, which had been"
6"She leaned on the bar,"
7"It got stuck somewhere in"
8"She kept her face doing"
9"It caught the green from"
10"She hadn't been planning a"
11"She poured one anyway, a"
12"It was the silence of"
13"She watched it run."
ratio0.28
70.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount39
totalSentences50
matches
0"The pint glass slipped from"
1"It bounced off the rubber"
2"Silas had asked her to"
3"She could manage an hour."
4"That was before the laugh."
5"It came from the third"
6"The laugh was short, sharp,"
7"The woman's head lifted."
8"It landed between them, that"
9"Mei's mouth opened and closed."
10"The gin and tonic went"
11"She reached for the bottle"
12"Mei was wearing a coat"
13"The bag on the stool"
14"Her hair, which had been"
15"The chewed nails were gone."
16"She leaned on the bar,"
17"Rory did the sum."
18"Mei laughed again, but this"
19"It got stuck somewhere in"
ratio0.78
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences50
matches(empty)
ratio0
63.49% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences27
technicalSentenceCount3
matches
0"Her hair, which had been a mess of bleached ends and black roots the last time Rory had seen her, sat now in a glossy bob that looked like it had been cut by so…"
1"She kept her face doing the thing her mother used to do when clients told her embarrassing things on the phone, the small attentive smile that gave nothing back…"
2"It was the silence of two people who had once sat on the floor of a student flat at four in the morning eating cold chips and telling each other the worst thing…"
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags6
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags2
fancyCount0
fancyTags(empty)
dialogueSentences62
tagDensity0.032
leniency0.065
rawRatio0
effectiveRatio0
88.2011%