Run: 2026-02-19-01KHVPF6FEFE85BW3EFDFYS1AK

Run Details

Duration:
2m 28s
Cost:
$0.180942
Provider:
Google AI Studio

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
Rain hammered against my visor, reducing the vibrant streetlights of Soho to long yellow streaks. I threw the motorcycle onto its kickstand, killed the bleeding engine, and snatched the insulated thermal bag from the cargo box. Yu-Fei Cheung runs the Golden Empress with a heavy iron fist and a stopwatch. Lateness means docked wages. I sprinted across the slick pavement, ducking under the awning of The Raven's Nest. I pushed through the entrance. The low rhythm of an upright bass and a raspy saxophone replaced the relentless London traffic. "Two portions of crispy shredded beef, one golden roasted duck, and a side of steamed dumplings." I slammed the grease-stained brown paper bags onto the mahogany bar. Heat radiated through the damp thin material, filling the room with the heavy scent of five-spice and garlic. Silas polished the counter with a clean white rag. He wore a jagged scar across his chin and a permanent scowl, souvenirs from a previous life serving a government agency that did not technically exist. "You made excellent time, Rory," Silas said. "Yu-Fei screams if the duck gets cold." I unclipped my helmet and shoved it under my arm. Rainwater dripped from my jacket onto the ancient floorboards. "That comes to twenty-four quid." Silas reached into his pockets. "You forgot the plum sauce." Cardiff vowels. Crisp consonants. The voice originated from the darkest corner booth. It anchored my heavy boots to the sticky floorboards. The stale pub air instantly tasted like copper and cold rain. I turned. A woman sat deep in the shadows. The distinctive green neon sign above the entrance bled through the frosted window, washing her sharp cheekbones in a sickly glow. Eva. I abandoned the cash arrangement. My left thumb instinctively jumped to the small crescent-shaped scar on my wrist, tracing the raised flesh. I navigated past the wobbly empty stools. The brick walls displayed an eclectic mish-mash of faded black-and-white photographs and detailed maps of Victorian London. I felt their forgotten historical faces staring at me as I closed the distance. She wore a tailored charcoal blazer, crisp white blouse, and pearl earrings. The sensible canvas shoes of our university days had vanished, replaced by expensive black stilettos. She belonged in a prestigious corporate boardroom, not a hidden Soho pub. "You cut your hair," I said. "Easier to maintain." "Evan prefers long hair. He claims it shows proper femininity." "Evan demands many things. I convinced him a sharp bob suits a prominent barrister's wife far better." I slid into the opposite side of the booth. The cracked leather seat groaned under my weight. "You married him." "Last spring. A beautiful private ceremony in the valleys." Eva pulled a silver cigarette case from her breast pocket. "Your mother cried." "My mother cries at laundry detergent commercials." "Your father delivered a lovely toast. Brendan called it a magnificent merging of Welsh legal minds." "My father measures human worth by billable hours." I crossed my arms over my damp delivery uniform. "You traveled three hundred miles just to recount your wedding reception?" "I came to see my oldest friend." "We ceased being friends the night you packed my duffel bag and shoved me onto the midnight train to Paddington." Silas approached the table. He carried a heavy glass tumbler and a bottle of top-shelf Irish whisky. He stepped carefully, his left leg dragging slightly across the floorboards. An unpaid physical debt from a botched intelligence operation in Prague years ago. He set the glass down with a heavy thud. The silver signet ring on his right hand caught the neon light. "Friend of yours, Rory?" Silas locked his hazel eyes onto Eva. "We share history," I said. "History gets people killed." Silas filled the tumbler halfway. "Drink up, then vacate the premises." "I prefer to stay." Eva traced the rim of her glass. "The Raven's Nest serves a specific clientele." Silas crossed his massive arms. His neatly trimmed grey-streaked auburn beard matched his fierce expression. "You lack the required dirt under your fingernails." "I possess plenty of dirt." Eva swallowed a mouthful of the amber liquid. "Just none you can see." "Give us a minute, Si," I ordered. Silas gave a single curt nod. He retreated to the far end of the room near the heavy oak bookshelf. Behind that timber facade sat the secret back room, a secure vault used for clandestine network meetings. He gave us physical distance, but kept his lethal attention firmly locked on our booth. The antique grandfather clock beside the jukebox kept a steady tick-tock, counting down seconds to a disaster I felt brewing in my gut. "He misses his star pupil," Eva said. "I abandoned Pre-Law three years ago." "A tactical error." "An absolute necessity." I leaned forward, resting my elbows on the sticky table. "Evan demands a punching bag, an accessory, a stepping stone. I refused to play the victim." "He changed." "Men like Evan simply learn to punch where the bruises stay hidden." Eva shifted her weight. The dim lighting caught a thick smear of expensive foundation covering a severe yellowing mark along her jawbone. "You tripped," I said, nodding at her chin. "The foyer staircase requires new carpeting." Eva refused to break eye contact. She placed an ugly heavy old square black German leather document folder onto the table. "I need your signature." "I own zero assets." "You own an identity." She unlatched the metal clasps. "He discovered the offshore accounts. The ones bearing your name." "I arrived in London with a suitcase and two hundred quid." "I required an escape fund. I diverted five hundred thousand pounds from his client trust accounts." She tapped a French manicured nail against the leather flap. "I used your old bank credentials. I forged your signature. It provided the ultimate cover." "Your theft. Your problem." "He holds you responsible." "You expect me to accept the blame for your embezzlement." "I expect you to act rationally." Eva's polished facade cracked. Her chest heaved, and she gripped the table edge until her knuckles turned white. "Sign the transfer documents. Relinquish the stolen funds to him. You excel at surviving in the shadows. Take the fall. He hunts you, I escape." "He slaughters every loose end." "A calculated risk." The sheer selfish audacity hitched my breath. I slid out of the booth. "Pack your papers and walk out the door." "Aurora, please." "Leave." Eva drank the remaining whisky. Her hands vibrated the empty glass against the table. The air inside the pub turned thick and suffocating. "How did you locate me?" I asked, a fresh wave of ice flooding my veins. "Yu-Fei Cheung." "She never speaks to strangers." "She spoke to him." A loud crash echoed from outside the dusty front window. Glass shattered across the wet pavement. The distinctive green neon sign blinked twice, went flip-flop, and died, plunging the quiet street into utter darkness. "I brought him to you," Eva said, her voice stripped entirely of emotion. "You led a monster to my sanctuary." "I purchased my safety." "By trading my life." "He granted me a five-minute head start." Eva checked her expensive gold wristwatch. "Four minutes ago." "Rory, get behind the bar!" Silas barked the command, abandoning his stoic posture completely. He reached under the register, retrieving a beautiful large long old black Russian steel combat shotgun. The solid oak front door splintered under a massive blow. Ragged wood fragments flew across the room, striking the vintage maps. A towering familiar figure kicked through the ruined frame, swinging a rusted iron crowbar into the nearest wooden chair. I locked eyes with Evan, snatched a jagged broken bottle from the floor, and stepped directly into his path.
created_at"2026-02-19T19:36:44.121Z" 2/19/2026, 7:36:44 PM
model"google/gemini-3.1-pro-preview-20260219"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency3061
moderation_latency(null)
generation_time146981
tokens_prompt4618
tokens_completion7242
native_tokens_prompt4497
native_tokens_completion14329
native_tokens_completion_images0
native_tokens_reasoning12618
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"
usage0.180942
router(null)
provider_responses
0
endpoint_id"2abf5677-0826-45d9-8470-3d62c31d54a1"
is_byokfalse
latency3061
model_permaslug"google/gemini-3.1-pro-preview-20260219"
provider_name"Google AI Studio"
status200
api_type"completions"
id"gen-1771529804-Jov1ovQYHTEEgFQ7Q4hb"
upstream_id(null)
total_cost0.180942
cache_discount(null)
upstream_inference_cost0
provider_name"Google AI Studio"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags24
adverbTagCount0
adverbTags(empty)
dialogueSentences65
tagDensity0.369
leniency0.738
rawRatio0
effectiveRatio0
88.41% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1294
totalAiIsmAdverbs3
found
0
adverb"carefully"
count1
1
adverb"slightly"
count1
2
adverb"completely"
count1
highlights
0"carefully"
1"slightly"
2"completely"
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)
42.04% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1294
totalAiIsms15
found
0
word"tracing"
count1
1
word"navigated"
count1
2
word"weight"
count2
3
word"traced"
count1
4
word"facade"
count2
5
word"clandestine"
count1
6
word"firmly"
count1
7
word"calculated"
count1
8
word"vibrated"
count1
9
word"echoed"
count1
10
word"shattered"
count1
11
word"sanctuary"
count1
12
word"familiar"
count1
highlights
0"tracing"
1"navigated"
2"weight"
3"traced"
4"facade"
5"clandestine"
6"firmly"
7"calculated"
8"vibrated"
9"echoed"
10"shattered"
11"sanctuary"
12"familiar"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"knuckles turned white"
count1
highlights
0"knuckles turned white"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences84
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences84
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences125
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen28
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1279
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions20
unquotedAttributions0
matches(empty)
50.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions39
wordCount834
uniqueNames18
maxNameDensity1.44
worstName"Eva"
maxWindowNameDensity3.5
worstWindowName"Eva"
discoveredNames
Soho2
Cheung1
Golden1
Empress1
Raven1
Nest1
London2
Heat1
Rainwater1
Victorian1
Silas9
Irish1
Prague1
Eva12
German1
French1
Russian1
Evan1
persons
0"Cheung"
1"Raven"
2"Heat"
3"Rainwater"
4"Silas"
5"Eva"
6"French"
7"Evan"
places
0"Soho"
1"London"
2"Prague"
globalScore0.781
windowScore0.5
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences64
glossingSentenceCount1
matches
0"tasted like copper and cold rain"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1279
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences125
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs72
mean17.76
std16.81
cv0.946
sampleLengths
068
121
245
335
47
531
65
75
84
928
102
1128
121
1360
1439
156
163
1710
1817
1920
2022
217
2216
2328
247
2520
2662
2711
285
2915
3011
3130
3218
337
3475
357
366
373
3829
392
4012
4122
428
4331
444
4519
4611
4741
484
494
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences84
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs129
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences125
ratio0
matches(empty)
82.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount845
adjectiveStacks3
stackExamples
0"small crescent-shaped scar"
1"ugly heavy old square"
2"beautiful large long old black Russian"
adverbCount14
adverbRatio0.016568047337278107
lyAdverbCount13
lyAdverbRatio0.015384615384615385
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences125
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences125
mean10.23
std5.93
cv0.579
sampleLengths
015
121
214
34
414
55
616
727
818
99
1026
117
1217
139
145
155
165
172
182
198
209
2111
222
237
2421
251
265
2717
287
2917
3014
3112
3215
3312
346
353
3610
3717
389
398
403
4119
423
437
4416
4517
4611
477
4820
494
53.07% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats7
diversityRatio0.352
totalSentences125
uniqueOpeners44
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences75
matches(empty)
ratio0
49.33% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount32
totalSentences75
matches
0"I threw the motorcycle onto"
1"I sprinted across the slick"
2"I pushed through the entrance."
3"I slammed the grease-stained brown"
4"He wore a jagged scar"
5"I unclipped my helmet and"
6"It anchored my heavy boots"
7"I abandoned the cash arrangement."
8"My left thumb instinctively jumped"
9"I navigated past the wobbly"
10"I felt their forgotten historical"
11"She wore a tailored charcoal"
12"She belonged in a prestigious"
13"I slid into the opposite"
14"I crossed my arms over"
15"He carried a heavy glass"
16"He stepped carefully, his left"
17"He set the glass down"
18"His neatly trimmed grey-streaked auburn"
19"He retreated to the far"
ratio0.427
0.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount72
totalSentences75
matches
0"I threw the motorcycle onto"
1"Yu-Fei Cheung runs the Golden"
2"Lateness means docked wages."
3"I sprinted across the slick"
4"I pushed through the entrance."
5"The low rhythm of an"
6"I slammed the grease-stained brown"
7"Heat radiated through the damp"
8"Silas polished the counter with"
9"He wore a jagged scar"
10"I unclipped my helmet and"
11"Rainwater dripped from my jacket"
12"Silas reached into his pockets."
13"The voice originated from the"
14"It anchored my heavy boots"
15"The stale pub air instantly"
16"A woman sat deep in"
17"The distinctive green neon sign"
18"I abandoned the cash arrangement."
19"My left thumb instinctively jumped"
ratio0.96
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences75
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences34
technicalSentenceCount1
matches
0"He wore a jagged scar across his chin and a permanent scowl, souvenirs from a previous life serving a government agency that did not technically exist."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags24
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags10
fancyCount3
fancyTags
0"I ordered (order)"
1"Eva refused (refuse)"
2"Silas barked (bark)"
dialogueSentences65
tagDensity0.154
leniency0.308
rawRatio0.3
effectiveRatio0.092
82.1616%