Run: 2026-04-25-01KQ2EQQG3VRSSZZM0P3MBHKEP

Run Details

Duration:
31.0s
Cost:
$0.000698
Provider:
DeepSeek

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 door groaned shut behind her, the familiar weight of it settling into its frame. Rory shrugged off her jacket, the polyester still smelling of sweet and sour sauce from the last delivery. A man sat at the bar, alone. Three empty glasses lined up in front of him like soldiers. He wore a cheap suit, the kind that promised interviews but never delivered promotions. His tie was loosened, his collar undone. Something about the slope of his shoulders. She ordered a tonic water from Silas, who raised an eyebrow but said nothing. The man turned at the sound of her voice. "Rory?" The name hit her like a punch to the chest. No one called her that anymore. Not since Cardiff. "Tom." She slid onto the stool next to him. "Christ. Look at you." He laughed, but it came out hollow. "Look at me. Yeah." His eyes swept over her uniform. "You're... delivering food now?" "Part-time. I work here too, sort of. Live upstairs." She gestured vaguely. "Long story." "Always were good at those. Long stories." He picked up his fourth glass, the ice clinking against the side. "I'm in town for a conference. Insurance stuff." "Insurance." She couldn't keep the disbelief from her voice. "You were top of our torts class. You argued before the mock court. Everyone said you'd be silk by thirty." "Everyone says a lot of things." He drank. "What about you? Last I heard, you were going to take the bar. Then you just... vanished." The tonic water tasted flat. She set it down. "I needed to leave." "Evan?" She didn't answer. The scar on her wrist itched beneath her sleeve. "He was bad news," Tom said. "I remember. We all told you." "You did." She turned the glass in her hands. "And I didn't listen. Took me two years and a broken rib to figure it out." Silas appeared at the end of the bar, polishing a glass. He didn't look at them, but Rory knew he was listening. The man missed nothing. "Anyway," she said. "I'm here now. It's not what I planned, but it's... mine." Tom nodded slowly. His hands were trembling slightly. "You look good. Healthy. Happy, even." "Most days." She studied him. "You don't." He laughed again, a bitter sound that bounced off the dark walls. "Honest as ever. That's why I liked studying with you. You never sugar-coated anything." "What happened, Tom?" He stared at his glass. The ice had melted. "Life happened. Graduated. Got a job at a decent firm. Then my mum got sick. I took time off to care for her. When I came back, someone else had my desk. They said I could start over at the bottom. I couldn't." He shrugged. "So here I am. Selling policies to people who don't read the fine print." "That's not how I imagined you." "No." He finally looked at her. "Not how I imagined you either. But here we are." Silas set a fresh glass of water in front of Tom. "On the house. You look like you need it." Tom nodded his thanks. The gesture was mechanical, worn. "I think about those days sometimes," Rory said. "The library. The all-nighters. How we thought we'd change the world." "I wanted to be a barrister so I could help people." Tom's voice cracked. "Now I help people's premiums go up." He rubbed his eyes. "Sorry. I didn't mean to dump this on you. I just... I haven't talked to anyone who knew me before. The real me." "We were kids," she said softly. "We had dreams. That's not nothing." "It's worse than nothing. It's a reminder." He drained the water. "You're lucky. You got out. You started over. I'm stuck in the same city, same routine, same everything. Except I'm older and more tired." The door to the bar swung open. A group of rowdy men stumbled in, laughing too loud. One of them spotted Tom. "Davies! There you are! We've been looking all over." Tom's face went pale. "I told them I was getting a drink. I should... I should go." "Them?" Rory asked. "Colleagues. They're clients. Important ones." He stood, adjusting his tie. "It was good to see you, Rory. Really." "Tom, wait." She touched his arm. "If you ever want to talk. I'm here. Most nights." He smiled, but it didn't reach his eyes. "Thanks. But I think we both know that ship's sailed." He walked toward the group, his shoulders hunched, his steps heavy. One of the men clapped him on the back, and Tom flinched. Rory watched until the door closed behind him. Silas appeared at her elbow. "Trouble?" "Old friend. We used to be the same." "No one stays the same." He picked up the empty glasses. "Especially not in this city." She stared at the door, the green neon sign casting its glow on the wet pavement outside. The memory of Tom's hollow laugh echoed in her ears. She didn't feel like finishing her tonic water.
created_at"2026-04-25T13:54:45.386Z" 4/25/2026, 1:54:45 PM
model"deepseek/deepseek-v4-flash-20260423"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency809
moderation_latency(null)
generation_time30935
tokens_prompt4618
tokens_completion2239
native_tokens_prompt4209
native_tokens_completion2028
native_tokens_completion_images(null)
native_tokens_reasoning887
native_tokens_cached4096
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"stop"
usage0.000698348
router(null)
provider_responses
0
endpoint_id"722e0746-2034-4d6e-a08f-e6271849ee9e"
id"90136956-3f78-463f-b279-e6dcfb057d66"
is_byokfalse
latency377
model_permaslug"deepseek/deepseek-v4-flash-20260423"
provider_name"DeepSeek"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer(null)
request_id"req-1777125285-wVcsqrJSpAW0FkNNYf78"
session_id(null)
api_type"completions"
id"gen-1777125285-Mo6YGkfDNvOeUY6apaUN"
upstream_id"90136956-3f78-463f-b279-e6dcfb057d66"
total_cost0.000698348
cache_discount0.000458752
upstream_inference_cost0
provider_name"DeepSeek"
response_cache_source_id(null)

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags20
adverbTagCount2
adverbTags
0"She gestured vaguely [vaguely]"
1"she said softly [softly]"
dialogueSentences53
tagDensity0.377
leniency0.755
rawRatio0.1
effectiveRatio0.075
76.08% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount836
totalAiIsmAdverbs4
found
0
adverb"slowly"
count1
1
adverb"slightly"
count1
2
adverb"softly"
count1
3
adverb"really"
count1
highlights
0"slowly"
1"slightly"
2"softly"
3"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)
58.13% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount836
totalAiIsms7
found
0
word"familiar"
count1
1
word"weight"
count1
2
word"eyebrow"
count1
3
word"silk"
count1
4
word"mechanical"
count1
5
word"reminder"
count1
6
word"echoed"
count1
highlights
0"familiar"
1"weight"
2"eyebrow"
3"silk"
4"mechanical"
5"reminder"
6"echoed"
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
narrationSentences61
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences61
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences93
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen46
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords836
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions10
unquotedAttributions0
matches(empty)
33.33% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions19
wordCount422
uniqueNames4
maxNameDensity2.13
worstName"Tom"
maxWindowNameDensity4
worstWindowName"Tom"
discoveredNames
Silas4
Cardiff1
Rory5
Tom9
persons
0"Silas"
1"Rory"
2"Tom"
places
0"Cardiff"
globalScore0.434
windowScore0.333
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences32
glossingSentenceCount0
matches(empty)
80.38% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches1
per1kWords1.196
wordCount836
matches
0"not what I planned, but it's"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences93
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs47
mean17.79
std12.35
cv0.694
sampleLengths
033
139
27
323
41
519
613
721
814
927
1029
1125
1213
131
1412
1512
1625
1726
1814
1914
207
2126
223
2368
246
2516
2620
279
2819
2948
3012
3135
3222
339
3417
353
3618
3716
3818
3923
408
416
428
4316
4417
4510
468
99.51% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences61
matches
0"was loosened"
29.06% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount2
totalVerbs78
matches
0"was listening"
1"were trembling"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences93
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount422
adjectiveStacks0
stackExamples(empty)
adverbCount11
adverbRatio0.026066350710900472
lyAdverbCount5
lyAdverbRatio0.011848341232227487
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences93
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences93
mean8.99
std6.04
cv0.672
sampleLengths
015
118
27
311
414
57
67
714
89
91
1010
116
123
139
144
157
1610
174
1812
192
2019
218
229
2320
248
2517
265
274
284
291
303
319
326
336
349
3516
3611
3711
384
393
4011
413
425
436
445
452
4612
4714
483
495
77.78% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats1
diversityRatio0.4731182795698925
totalSentences93
uniqueOpeners44
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences55
matches(empty)
ratio0
16.36% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount28
totalSentences55
matches
0"He wore a cheap suit,"
1"His tie was loosened, his"
2"She ordered a tonic water"
3"She slid onto the stool"
4"He laughed, but it came"
5"His eyes swept over her"
6"She gestured vaguely"
7"He picked up his fourth"
8"She couldn't keep the disbelief"
9"She set it down."
10"She didn't answer."
11"She turned the glass in"
12"He didn't look at them,"
13"His hands were trembling slightly."
14"She studied him"
15"He laughed again, a bitter"
16"He stared at his glass."
17"He finally looked at her"
18"He rubbed his eyes"
19"she said softly"
ratio0.509
5.45% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount50
totalSentences55
matches
0"The door groaned shut behind"
1"Rory shrugged off her jacket,"
2"A man sat at the"
3"He wore a cheap suit,"
4"His tie was loosened, his"
5"Something about the slope of"
6"She ordered a tonic water"
7"The man turned at the"
8"The name hit her like"
9"She slid onto the stool"
10"He laughed, but it came"
11"His eyes swept over her"
12"She gestured vaguely"
13"He picked up his fourth"
14"She couldn't keep the disbelief"
15"The tonic water tasted flat."
16"She set it down."
17"She didn't answer."
18"The scar on her wrist"
19"She turned the glass in"
ratio0.909
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences55
matches(empty)
ratio0
95.24% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences15
technicalSentenceCount1
matches
0"He wore a cheap suit, the kind that promised interviews but never delivered promotions."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags20
uselessAdditionCount1
matches
0"He picked up, the ice clinking against the side"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags5
fancyCount0
fancyTags(empty)
dialogueSentences53
tagDensity0.094
leniency0.189
rawRatio0
effectiveRatio0
79.0444%