Run: 2026-03-11-01KKFHX8TTPZ5PRJQSWZYY1YQJ

Run Details

Duration:
1m 35s
Cost:
$0.009142
Provider:
Seed

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 crate of empty takeaway tubs slipped from Rory’s grip, clattering into the shadow of the Raven’s Nest’s green neon sign. Plastic skittered across the wet Soho pavement, one tub rolling straight for the tyre of a idling black cab. A scuffed black combat boot planted itself on the tub’s edge, halting its progress. Rory bent to grab it, her straight black shoulder-length hair falling into her face, and looked up. The split lip was new, the cropped black hair a shock, but the gap in the front tooth’s old blue dental glaze, the faint smattering of freckles across the nose that never faded even in winter, marked the girl in front of her as unmistakable. She had not seen her in three years. “Eva.” Eva wiped a fleck of rain from her cheek, the frayed cotton friendship bracelet Rory had woven her for their 18th birthday still wrapped tight around her left wrist. The red thread had faded to pale pink, but it held. “Rory. You still run like you’re late for last call. I almost didn’t recognise you.” They hauled the crate back through the bar’s oak door, the bell above the entrance jingling loud enough to cut through the hum of the jukebox’s Bowie track. Silas looked up from wiping a pint glass, his grey-streaked auburn beard neat as ever, hazel eyes narrowing as he took in Eva’s split lip and the black eye peeking out from under her cropped hair. His silver signet ring tapped once against the bar’s worn oak top, a quiet warning he had noted the trouble that walked through his door. “Leave the recycling by the back door,” he said. “I’ll sort it in the morning.” He gestured to the faded leather booth at the far end of the room, tucked under a tattered 1990s map of Prague, the one he kept up even though no one but Rory knew why. “Take a seat. First round’s on the house.” Rory led Eva to the booth, the vinyl sticking faintly to the back of her jeans. The bar smelled of stale lager, spiced cider simmering on a small stove behind the bar, and the old cigarette smoke that had seeped into the walls ten years before the smoking ban. The walls were lined with black and white photographs of men and women no one in the bar could name, all grinning into the lens like they shared a secret no one else would ever learn. “I thought you were still in Cardiff,” Rory said. She rubbed the small crescent scar on her own left wrist, the habit she had never broken when she was tense. She told everyone the scar came from a childhood bike crash, that she had flown over the handlebars and split her skin on a rock. Only Eva knew the truth. Only Eva had seen Evan grab her that hard, his nails digging deep enough to leave a permanent mark. “Got a flat teaching Year 2, you said. You were going to paint the classroom walls sunflower yellow. You were going to send me photos every week.” Eva laughed, the sound sharp and broken, and picked at a loose thread on the booth’s armrest. “Evan found me three months after you left. Smashed the classroom window with a brick. Left a stray cat’s body on my mum’s back porch with a note that said she should have kept her mouth shut. I couldn’t stay. Sold my car, bought a coach ticket to London, crashed on a stranger’s couch in Brixton. Haven’t been back since.” Rory’s throat tightened. She had blamed herself for leaving Eva behind for three years, for boarding that night coach to London and never looking back, even though Eva had been the one to pack her bag, the one to press fifty pounds into her palm and tell her to run before Evan came back. She had thought Eva was safe, living the life they had both planned when they were 17, lying on the sand of a Gower beach and talking about the cottage they would buy together, the rottweiler they would adopt from the local shelter and name Muffin, even though the shelter worker had said he was too fierce for a silly name. “Why didn’t you call?” Rory said. “I would have sent you money. I would have come to get you. Silas would have helped. He knows people.” “What for?” Eva said. She wiped a tear from her cheek with the back of her hand, and Rory saw her knuckles were split, like she had punched something, or someone. “You finally got out. You were the one who escaped him. I couldn’t be the reason you had to run all over again. I got a job stacking shelves in a Tesco. I pay my rent. I don’t need anyone to save me.” Silas limped over to the booth, his left leg dragging faintly from the old knee injury that had forced him out of MI6, and set two pints of lager down on the sticky table. He tapped his signet ring once against the wood, the same gesture he had used when Rory first moved in, when she told him she was running from someone, and he said no one would hurt her under his roof. He did not say anything else, just turned and limped back to the bar, pulling out his phone to type a quiet message Rory could not see. “We were supposed to get that cottage,” Rory said, her voice quieter now. The Gower beach they had dreamed of felt like it existed in another life, in a world where they had never met Evan, never had to run. “Remember Muffin? The shelter posted that they rehomed him, right after I left. I saw it on Facebook. He got a family with two little kids. He got the life we were supposed to have.” Eva laughed, and this time it was wet, half a sob. “I still check that family’s Instagram. They take him to the beach every weekend. He wears a little red bandana. It’s better than anything we could have given him, anyway. We would have spent the whole time looking over our shoulders.” Rory opened her mouth to ask Eva to move into the spare room in her flat above the bar, to say she could clear the boxes of takeaway menus and old university textbooks by the end of the week, to say they could finally stop running alone, when the bell above the door jingled again. She looked up. Evan stood in the entrance, his leather jacket still dusted with rain, his dark hair cut the same way it had been in Cardiff, his eyes scanning the bar slowly. They locked on the back booth, on Rory and Eva huddled together, and he smiled. The same cold smile he had worn the night he hit her, the night Eva had packed her bag and told her to run. He lifted a hand, waving like they were old friends meeting for a quiet pint, and started walking toward the booth.
created_at"2026-03-11T22:57:33.05Z" 3/11/2026, 10:57:33 PM
model"bytedance-seed/seed-2.0-lite-20260309"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1880
moderation_latency(null)
generation_time94874
tokens_prompt4618
tokens_completion4223
native_tokens_prompt4521
native_tokens_completion4006
native_tokens_completion_images(null)
native_tokens_reasoning2530
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"
usage0.00914225
router(null)
provider_responses
0
endpoint_id"bf1a3473-7a0a-46d3-aaa5-adb8f876a697"
id"0217732698533927701a42f23cc3d37ac47a8e8735f343a7e6dcc"
is_byokfalse
latency1880
model_permaslug"bytedance-seed/seed-2.0-lite-20260309"
provider_name"Seed"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer(null)
api_type"completions"
id"gen-1773269853-BXJkKcuMBWvCAsZG6YLk"
upstream_id"0217732698533927701a42f23cc3d37ac47a8e8735f343a7e6dcc"
total_cost0.00914225
cache_discount(null)
upstream_inference_cost0
provider_name"Seed"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags6
adverbTagCount0
adverbTags(empty)
dialogueSentences15
tagDensity0.4
leniency0.8
rawRatio0
effectiveRatio0
95.78% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1186
totalAiIsmAdverbs1
found
0
adverb"slowly"
count1
highlights
0"slowly"
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)
91.57% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1186
totalAiIsms2
found
0
word"simmering"
count1
1
word"scanning"
count1
highlights
0"simmering"
1"scanning"
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
narrationSentences40
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences40
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences49
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen61
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1186
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions8
unquotedAttributions0
matches(empty)
50.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions42
wordCount903
uniqueNames12
maxNameDensity1.55
worstName"Rory"
maxWindowNameDensity3.5
worstWindowName"Eva"
discoveredNames
Rory14
Raven1
Nest1
Soho1
Bowie1
Eva14
Prague1
Evan4
London1
Gower2
Muffin1
Cardiff1
persons
0"Rory"
1"Raven"
2"Nest"
3"Eva"
4"Evan"
places
0"Soho"
1"Prague"
2"London"
3"Gower"
4"Cardiff"
globalScore0.725
windowScore0.5
74.24% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences33
glossingSentenceCount1
matches
0"felt like it existed in another life, i"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches1
per1kWords0.843
wordCount1186
matches
0"no one but"
98.64% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences49
matches
0"boarding that night"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs21
mean56.48
std31.05
cv0.55
sampleLengths
071
153
21
340
415
589
658
785
879
927
1077
11115
1226
1374
14101
1575
1652
1755
183
1969
2021
96.49% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences40
matches
0"were lined"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount1
totalVerbs150
matches
0"was running"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences49
ratio0
matches(empty)
94.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount905
adjectiveStacks1
stackExamples
0"old blue dental glaze,"
adverbCount25
adverbRatio0.027624309392265192
lyAdverbCount7
lyAdverbRatio0.0077348066298342545
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences49
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences49
mean24.2
std15.07
cv0.623
sampleLengths
021
119
214
317
445
58
61
729
811
915
1028
1136
1225
139
1441
158
1616
1733
1836
199
2021
2125
225
2319
2427
2517
2660
273
2851
2961
306
3120
324
3327
3443
3534
3640
3727
3813
3927
4035
4111
4241
4355
443
4530
4615
4724
4821
59.18% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats6
diversityRatio0.42857142857142855
totalSentences49
uniqueOpeners21
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences36
matches
0"Only Eva knew the truth."
1"Only Eva had seen Evan"
ratio0.056
64.44% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount14
totalSentences36
matches
0"She had not seen her"
1"They hauled the crate back"
2"His silver signet ring tapped"
3"He gestured to the faded"
4"She rubbed the small crescent"
5"She told everyone the scar"
6"She had blamed herself for"
7"She had thought Eva was"
8"She wiped a tear from"
9"He tapped his signet ring"
10"He did not say anything"
11"She looked up."
12"They locked on the back"
13"He lifted a hand, waving"
ratio0.389
0.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount34
totalSentences36
matches
0"The crate of empty takeaway"
1"Plastic skittered across the wet"
2"A scuffed black combat boot"
3"Rory bent to grab it,"
4"The split lip was new,"
5"She had not seen her"
6"Eva wiped a fleck of"
7"The red thread had faded"
8"They hauled the crate back"
9"Silas looked up from wiping"
10"His silver signet ring tapped"
11"He gestured to the faded"
12"Rory led Eva to the"
13"The bar smelled of stale"
14"The walls were lined with"
15"She rubbed the small crescent"
16"She told everyone the scar"
17"Eva laughed, the sound sharp"
18"Rory’s throat tightened."
19"She had blamed herself for"
ratio0.944
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences36
matches(empty)
ratio0
71.43% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences30
technicalSentenceCount3
matches
0"His silver signet ring tapped once against the bar’s worn oak top, a quiet warning he had noted the trouble that walked through his door."
1"The bar smelled of stale lager, spiced cider simmering on a small stove behind the bar, and the old cigarette smoke that had seeped into the walls ten years bef…"
2"Silas limped over to the booth, his left leg dragging faintly from the old knee injury that had forced him out of MI6, and set two pints of lager down on the st…"
41.67% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags6
uselessAdditionCount1
matches
0"Rory said, her voice quieter now"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags5
fancyCount0
fancyTags(empty)
dialogueSentences15
tagDensity0.333
leniency0.667
rawRatio0
effectiveRatio0
84.5816%