Run: 2026-02-19-01KHTXW1DXRF4TQ88M58JXA24V

Run Details

Duration:
35.3s
Cost:
$0.038241
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
The damp cloth slid over the dark wood of the bar top, smearing a faint ring of condensation into nothing. Only two patrons remained, hunched over their respective glasses at opposite ends of the room, lost in the amber glow. Each scrape of the bar stool, each low murmur, was amplified in the quiet of the closing hour. The stale scent of beer and roasted peanuts hung heavy in the air, a familiar perfume. Aurora dragged the cloth through a final wet streak, her movements practiced and economical. One more table to wipe, then she could escape to the quiet solitude of her flat upstairs. The heavy oak door groaned open, spilling the garish, flickering lights of Soho into the bar’s dim sanctuary. A silhouette stood framed in the doorway, a man in a well-tailored suit that looked out of place amongst the worn leather and yellowed maps. He paused, letting his eyes adjust, his posture radiating a confidence that grated. She kept her head down, hoping he would take a seat and spare her the effort of pleasantries. “No way.” The voice was sharp with disbelief, cutting through the low thrum of the bar. “Rory? Aurora Carter, is that you?” Her hand froze on the sticky surface of a table. The name, her full name, felt like a relic from another life, a dress she had long since outgrown. She turned slowly, her face a carefully constructed mask of neutrality. The man took a step forward, his expensive shoes clicking on the floorboards. His face was sharper than she remembered, the boyish charm from university chiselled into a man's handsome certainty, but the eyes were the same. The same bright, earnest blue. Leo. “Leo Davies,” she said, her voice flat. It wasn't a question. He grinned, a wide, brilliant thing that seemed to mock the shadows in the room. He closed the distance between them, stopping just short of the bar. He smelled of rain and expensive cologne. “I can’t believe it. Of all the gin joints in all the towns. What are you doing here?” She dropped the cloth into a bucket of murky water. “Working.” “Right.” He looked around, taking in the dusty photographs and the faded maps pinned to the walls. His gaze lingered on the green neon sign of The Raven’s Nest, its reflection warped in the window. “Bit of a change from the barrister track, isn’t it?” A small muscle twitched in her jaw. She picked up a stray glass, polishing its rim with a clean towel, the friction a small, private anchor. “People change.” “I’ll say.” He leaned against the bar, his suit jacket pulling tight across his shoulders. “You look… different.” He didn’t say good, or bad. Just different. It was worse. It was honest. “I’m in town for a case. Big one. Corporate mergers. Drier than sandpaper but it pays the bills.” He chuckled, a sound that she remembered echoing through the university library. It sounded hollow now. “Saw your dad last month, actually. At a fundraiser. Still telling that awful story about the confused juror.” The glass in her hand felt suddenly fragile. “Is he well?” “He’s fine. Asked after you, of course. Your mum too.” He paused, his smile faltering for the first time. “They don’t hear from you much, do they?” “I’m busy.” The lie was thin, pathetic. Leo had the decency to pretend to believe it. He picked at a non-existent piece of lint on his sleeve. “Look, Rory, it’s good to see you. It really is. I’ve wondered… you know. After everything.” Everything. The word hung between them, swollen and ugly. It meant Evan. It meant the frantic phone call to Eva in the dead of night, the packed bag, the train to London with nothing but a few hundred quid and a constellation of purple bruises hidden under her coat. It meant the life she had torched to the ground to escape one man. “I heard you made partner at Jenkins & Croft,” she said, steering the conversation onto safer ground. “Youngest in the firm’s history.” He brightened, puffing up slightly. “News travels, eh? It’s been a slog, but worth it. The life we always talked about, right? Burning the midnight oil, drowning in precedents.” He gestured with his hand, a silver signet ring flashing on his finger. It wasn’t a bar owner’s ring, not like Silas’s worn band. It was a mark of belonging to a world she had been cast out of. “Remember Professor Albright’s class? You, me, and Eva, plotting to take over the Old Bailey. You were going to be the fiercest prosecutor they’d ever seen.” She offered a tight, bloodless smile. “Plans change.” “I saw Evan, you know,” he said, his voice dropping. “At a wedding in the spring. He asked about you.” The crescent-shaped scar on her wrist burned, a phantom pain that was more memory than sensation. She placed the glass down on the counter with a sharp click that made him flinch. She met his eyes, her own bright blue ones turning to ice. “And what did you tell him?” “Nothing. Just that I hadn’t seen you.” He looked uncomfortable, shifting his weight. “He looks the same. Still has that same easy smile.” Her breath caught in her throat. She knew that smile. It was the smile he wore before the mask dropped, before the doors were locked, before his hands found her. Before Leo could say more, a shadow fell over them. Silas emerged from the back room, his limp more pronounced than usual. He moved with a quiet purpose that silenced the air around him. His hazel eyes, sharp and assessing, were fixed on Aurora. He paid Leo no more mind than he would a piece of furniture. He slid a small, black object onto the bar between them. It was a simple memory stick, devoid of any markings. “The Nightingale is compromised,” Silas said, his voice a low gravelly hum that carried an undeniable weight of command. “We move tonight.” Leo stared, bewildered, from the memory stick to Silas, then back to Aurora. “Nightingale? Rory, what’s he talking about?” Aurora ignored him. The girl he knew, the bright law student from Cardiff, vanished. In her place was someone colder, impossibly still. Her entire being seemed to sharpen, her focus narrowing to the old man and the object on the bar. She picked up the memory stick, its plastic cool against her skin. Her hand was rock-steady. “The meet?” Silas finally flickered his gaze to Leo, a brief, dismissive inspection. It was the look of a man cataloguing a threat and finding it wanting. “Your friend needs to leave.” It was not a request. It was an order.
created_at"2026-02-19T12:26:50.693Z" 2/19/2026, 12:26:50 PM
model"google/gemini-2.5-pro"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency3265
moderation_latency(null)
generation_time35304
tokens_prompt4618
tokens_completion2572
native_tokens_prompt4497
native_tokens_completion3262
native_tokens_completion_images0
native_tokens_reasoning1780
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"
usage0.03824125
router(null)
provider_responses
0
endpoint_id"b261d15b-95ce-4c8c-8bce-00eb0dc1ff77"
is_byokfalse
latency3265
model_permaslug"google/gemini-2.5-pro"
provider_name"Google AI Studio"
status200
api_type"completions"
id"gen-1771504010-n6jEIX4AWw2qPtJ6lVnB"
upstream_id(null)
total_cost0.03824125
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
totalTags12
adverbTagCount1
adverbTags
0"He looked around [around]"
dialogueSentences32
tagDensity0.375
leniency0.75
rawRatio0.083
effectiveRatio0.063
77.82% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1127
totalAiIsmAdverbs5
found
0
adverb"slowly"
count1
1
adverb"carefully"
count1
2
adverb"suddenly"
count1
3
adverb"really"
count1
4
adverb"slightly"
count1
highlights
0"slowly"
1"carefully"
2"suddenly"
3"really"
4"slightly"
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)
64.51% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1127
totalAiIsms8
found
0
word"familiar"
count1
1
word"sanctuary"
count1
2
word"constructed"
count1
3
word"charm"
count1
4
word"echoing"
count1
5
word"weight"
count2
6
word"flickered"
count1
highlights
0"familiar"
1"sanctuary"
2"constructed"
3"charm"
4"echoing"
5"weight"
6"flickered"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"hung in the air"
count1
highlights
0"hung heavy in the air"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells2
narrationSentences78
matches
0"p with disbelief"
1"looked uncomfortable"
87.91% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount3
narrationSentences78
filterMatches(empty)
hedgeMatches
0"seemed to"
1"tend to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences97
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen37
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1123
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions11
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions22
wordCount877
uniqueNames10
maxNameDensity0.68
worstName"Leo"
maxWindowNameDensity2
worstWindowName"Silas"
discoveredNames
Soho1
Raven1
Nest1
Evan1
Eva1
London1
Silas5
Leo6
Aurora4
Cardiff1
persons
0"Raven"
1"Evan"
2"Eva"
3"Silas"
4"Leo"
5"Aurora"
places
0"Soho"
1"London"
2"Cardiff"
globalScore1
windowScore1
66.67% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences60
glossingSentenceCount2
matches
0"felt like a relic from another life, a"
1"thing that seemed to mock the shadows in the room"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1123
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences97
matches
0"knew that smile"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs28
mean40.11
std29.01
cv0.723
sampleLengths
0105
174
222
383
411
552
611
745
828
984
1011
1127
122
1341
1463
1522
1694
178
1820
1950
2023
2130
2278
2322
2419
2557
262
2739
87.27% Passive voice overuse
Target: ≤2% passive sentences
passiveCount4
totalSentences78
matches
0"was amplified"
1"were locked"
2"were fixed"
3"being seemed"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs142
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences97
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount881
adjectiveStacks0
stackExamples(empty)
adverbCount20
adverbRatio0.022701475595913734
lyAdverbCount9
lyAdverbRatio0.01021566401816118
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences97
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences97
mean11.58
std7.3
cv0.63
sampleLengths
020
120
218
316
414
517
618
725
813
918
1016
116
1210
1319
1411
1513
1624
175
181
197
204
2115
2212
237
2418
2510
261
2717
2818
2910
307
3119
322
3315
349
352
363
373
3830
394
4018
418
423
4319
448
452
465
479
4811
4916
57.73% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats9
diversityRatio0.4020618556701031
totalSentences97
uniqueOpeners39
44.44% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences75
matches
0"Only two patrons remained, hunched"
ratio0.013
0.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount49
totalSentences75
matches
0"He paused, letting his eyes"
1"She kept her head down,"
2"Her hand froze on the"
3"She turned slowly, her face"
4"His face was sharper than"
5"she said, her voice flat"
6"It wasn't a question."
7"He grinned, a wide, brilliant"
8"He closed the distance between"
9"He smelled of rain and"
10"She dropped the cloth into"
11"He looked around, taking in"
12"His gaze lingered on the"
13"She picked up a stray"
14"He leaned against the bar,"
15"He didn’t say good, or"
16"It was worse."
17"It was honest."
18"He chuckled, a sound that"
19"It sounded hollow now."
ratio0.653
0.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount71
totalSentences75
matches
0"The damp cloth slid over"
1"Each scrape of the bar"
2"The stale scent of beer"
3"Aurora dragged the cloth through"
4"The heavy oak door groaned"
5"A silhouette stood framed in"
6"He paused, letting his eyes"
7"She kept her head down,"
8"The voice was sharp with"
9"Her hand froze on the"
10"The name, her full name,"
11"She turned slowly, her face"
12"The man took a step"
13"His face was sharper than"
14"The same bright, earnest blue."
15"she said, her voice flat"
16"It wasn't a question."
17"He grinned, a wide, brilliant"
18"He closed the distance between"
19"He smelled of rain and"
ratio0.947
66.67% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences75
matches
0"Before Leo could say more,"
ratio0.013
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences42
technicalSentenceCount2
matches
0"He paused, letting his eyes adjust, his posture radiating a confidence that grated."
1"The crescent-shaped scar on her wrist burned, a phantom pain that was more memory than sensation."
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags12
uselessAdditionCount5
matches
0"she said, her voice flat"
1"He leaned, his suit jacket pulling tight across his shoulders"
2"He chuckled, a sound that she remembered echoing through the university library"
3"He paused, his smile faltering for the first time"
4"he said, his voice dropping"
87.50% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags6
fancyCount2
fancyTags
0"He didn’t (do)"
1"He chuckled (chuckle)"
dialogueSentences32
tagDensity0.188
leniency0.375
rawRatio0.333
effectiveRatio0.125
81.3505%