Run: 2026-02-20-01KHYB1H7FCRXZCVNX89PF68AG

Run Details

Duration:
35.5s
Cost:
$0.000382
Provider:
DeepInfra

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 whisky’s gone flat,” Silas observed, polishing a glass with a practiced flick of his wrist. Not a complaint, merely a statement of fact. A barman’s assessment of his domain. The bell above the door chimed, a discordant clang against the muted jazz spilling from the speakers. I barely registered it before a voice, familiar yet warped, cut through the low hum of conversation. “Well, well, look what the cat dragged in.” I turned, slower this time, as if wading through treacle. Eva. But not the Eva I remembered. The girl with the riotous red curls and eyes that danced with mischief was… gone. Her hair was cropped close to her scalp, dyed a severe shade of charcoal. The vibrant floral dresses had been replaced by tailored black trousers and a crisp white shirt. A single, thin silver chain hung around her neck, the only concession to adornment. She looked… hard. Like a sculpture carved from granite. “Eva,” I managed, the name tasting foreign on my tongue. “I… I didn’t know you were back.” She offered a strained smile, the corners of her lips barely curving upward. “London’s always been home, Rory. Just… been doing a bit of traveling. A lot of traveling.” She gestured to the stool beside me. “Mind if I join you?” I shook my head, feeling a peculiar lump forming in my throat. It had been nearly eight years. Eight years since she’d practically dragged me from Cardiff, promising adventure and escape from Evan. Eight years since I’d last seen her laugh, truly laugh, the kind that crumpled her face and made her eyes sparkle. “You look… good,” I said, lamely. It was the first thing that came to mind, a desperately inadequate assessment of the woman sitting beside me. “Trying to,” she replied, her gaze flicking around the room, avoiding mine. “You too, Rory. Still delivering Thai, I see.” I winced, the reference to my part-time job a sharp jab. “It pays the bills.” Silas slid a glass of amber liquid towards her without a word. “Single malt. Good for what ails ya.” He gave me a knowing look, a silent acknowledgment of the awkwardness hanging in the air. Eva took a slow sip, her eyes finally meeting mine. They were colder now, lacking the warmth I remembered. "Remember that trip to Barcelona? Before everything went sideways?" The memory surfaced unbidden: scorching sunshine, sangria-soaked afternoons, and endless laughter echoing through the narrow, cobbled streets. Before the arguments, before Evan's creeping possessiveness, before I'd fled Cardiff with nothing but a suitcase and a broken heart. “Of course,” I said, a ghost of a smile playing on my lips. “We almost got arrested for climbing the Sagrada Familia.” Eva’s lips tightened. "Good times." She paused, then added, a hint of steel in her voice, "We were young. Reckless. We thought we were invincible.” “We were,” I countered, wanting to recapture the feeling, to rewind the clock even for a fleeting moment. "Appearances," she said softly, turning the glass between her fingers. "They can be deceiving. Things change, Rory. People change.” "I see that." The words felt flat, inadequate. The easy camaraderie we’d once shared seemed a million miles away. “What are you doing now, really?” she asked, her gaze intense. "Beyond delivering Pad Thai to students and grumpy pensioners." I hesitated. “Working. Living. Trying to… rebuild.” The rebuilding felt like a constant, Sisyphean task. Evan’s shadow still lingered, a cold dread that coiled in my stomach whenever I thought about him. "And you? What have you been up to all these years?" She took another sip of her whisky, the silence stretching between us. "I trade in information," she said finally, her voice low and precise. “Data. Assets. Intelligence.” I blinked. "Intelligence? Like... spy stuff?" The image of Eva, the wild-haired, impulsive youth, engaging in espionage felt ludicrous. She didn’t flinch. “Something like that. It’s a living.” She shrugged, a gesture that seemed calculated, devoid of any casualness. "It pays considerably better than waiting tables." “You always were ambitious,” I murmured, remembering her relentless drive, her desire to escape the small-town confines of Cardiff. “Ambition’s a survival skill, Rory," she said, her eyes hard. "You learn that quickly enough when you're playing this game." The game. What game was she playing? And how had she become such a different person? “It makes you… ruthless,” I said, the words leaving my mouth before I could stop them. Her gaze sharpened. “Ruthless? Or efficient? There's a difference.” “Is there?” I challenged, instantly regretting it. "What happened to the girl who would sneak into concerts and steal packets of crisps?” A flicker of something—pain, perhaps—crossed her face, quickly masked by a carefully constructed neutrality. "She grew up,” she said, her voice clipped. “The world has a way of doing that to you.” I studied her face, searching for a trace of the girl I’d known, the girl who’d shared my hopes and fears, my dreams and disappointments. I found nothing but a polished facade, a wall of impenetrable resolve. “Do you ever… miss it?” I asked, the question a desperate plea for a connection, any connection, to the past. "The… lightness? The freedom?” She laughed, a short, brittle sound that didn’t reach her eyes. “Freedom is an illusion, Rory. A pleasant fantasy for those who haven’t seen the dark side of things.” Silas cleared his throat, breaking the tense silence. “Another whisky, ladies?” Eva shook her head. "No, thank you." She stood up, smoothing down her trousers. "It was… good to see you, Rory. Really." "You too, Eva." Though I wasn't sure, truly, that I meant that. She hesitated for a moment, her hand resting on the back of her chair. “Be careful, Rory.” “Careful of what?” She didn’t answer. Instead, she turned and walked towards the door, disappearing into the London night. The bell chimed again as she left. I watched her go, a profound sense of loss settling over me. It wasn't just the loss of a friend. It was the loss of a shared history, a vanished possibility. The realization that the past was irretrievable, that the people we thought we knew could be irrevocably transformed by the weight of time, a world away from the bright glow of neon signs and refuge in smoky bars. Silas placed a hand on my shoulder. “Rough seeing old friends, eh?” I shook my head, unable to articulate the complicated tangle of emotions churning within me. "She's different", I managed. "Everyone is”, Silas replied, his gaze drifting across the room. “The question is... do you like who they’ve become?”
created_at"2026-02-20T20:14:45.513Z" 2/20/2026, 8:14:45 PM
model"google/gemma-3-12b-it"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency342
moderation_latency(null)
generation_time35263
tokens_prompt4642
tokens_completion1793
native_tokens_prompt4505
native_tokens_completion1555
native_tokens_completion_images(null)
native_tokens_reasoning0
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
usage0.00038235
router(null)
provider_responses
0
endpoint_id"eb06dc92-5a16-47ec-a776-6ef956457c47"
id"chatcmpl-RHWBQZ7YNXdlLnyAG7MEUzbh"
is_byokfalse
latency49
model_permaslug"google/gemma-3-12b-it"
provider_name"DeepInfra"
status200
api_type"completions"
id"gen-1771618485-hv07VVQm80iArqEMOBUC"
upstream_id"chatcmpl-RHWBQZ7YNXdlLnyAG7MEUzbh"
total_cost0.00038235
cache_discount(null)
upstream_inference_cost0
provider_name"DeepInfra"

Evaluation details

Result Evaluator Details Meta Data
46.15% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags26
adverbTagCount4
adverbTags
0"She paused then [then]"
1"she said softly [softly]"
2"The rebuilding felt like [like]"
3"she said finally [finally]"
dialogueSentences50
tagDensity0.52
leniency1
rawRatio0.154
effectiveRatio0.154
63.80% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1105
totalAiIsmAdverbs8
found
0
adverb"truly"
count2
1
adverb"softly"
count1
2
adverb"really"
count2
3
adverb"quickly"
count2
4
adverb"carefully"
count1
highlights
0"truly"
1"softly"
2"really"
3"quickly"
4"carefully"
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)
18.55% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1105
totalAiIsms18
found
0
word"familiar"
count1
1
word"warmth"
count1
2
word"echoing"
count1
3
word"fleeting"
count1
4
word"stomach"
count1
5
word"silence"
count2
6
word"calculated"
count1
7
word"desire"
count1
8
word"efficient"
count1
9
word"flicker"
count1
10
word"constructed"
count1
11
word"facade"
count1
12
word"resolve"
count1
13
word"profound"
count1
14
word"sense of"
count1
15
word"weight"
count1
16
word"churning"
count1
highlights
0"familiar"
1"warmth"
2"echoing"
3"fleeting"
4"stomach"
5"silence"
6"calculated"
7"desire"
8"efficient"
9"flicker"
10"constructed"
11"facade"
12"resolve"
13"profound"
14"sense of"
15"weight"
16"churning"
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
narrationSentences80
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences80
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences104
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen38
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1099
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions17
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions19
wordCount806
uniqueNames6
maxNameDensity0.74
worstName"Eva"
maxWindowNameDensity1.5
worstWindowName"Eva"
discoveredNames
Eva6
Cardiff3
Evan3
Sisyphean1
London1
Silas5
persons
0"Eva"
1"Evan"
2"Silas"
places
0"Cardiff"
1"London"
globalScore1
windowScore1
25.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences60
glossingSentenceCount3
matches
0"as if wading through treacle"
1"felt like a constant, Sisyphean task"
2"seemed calculated devoid of any casualness"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1099
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences104
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs44
mean24.98
std15.27
cv0.611
sampleLengths
030
134
28
385
417
541
654
725
820
915
1035
1128
1237
1322
1425
1518
1619
1719
1820
1943
2027
2119
2227
2319
2420
2516
2616
279
2822
2932
3037
3124
3229
3311
3422
3512
3617
373
3816
397
4069
4112
4219
4319
96.49% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences80
matches
0"was cropped"
1"been replaced"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs145
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount2
semicolonCount0
flaggedSentences1
totalSentences104
ratio0.01
matches
0"A flicker of something—pain, perhaps—crossed her face, quickly masked by a carefully constructed neutrality."
90.50% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount812
adjectiveStacks1
stackExamples
0"single, thin silver chain"
adverbCount35
adverbRatio0.04310344827586207
lyAdverbCount17
lyAdverbRatio0.020935960591133004
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences104
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences104
mean10.57
std6.19
cv0.586
sampleLengths
016
18
26
317
417
58
610
71
86
914
101
1114
1216
1314
142
151
166
1710
187
1913
2023
215
2212
236
2415
2521
266
2719
2812
298
3011
314
3212
3323
3410
359
369
3717
3820
3913
409
413
4222
4318
4410
459
468
4711
4811
499
72.44% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats3
diversityRatio0.4519230769230769
totalSentences104
uniqueOpeners47
46.30% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences72
matches
0"Instead, she turned and walked"
ratio0.014
0.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount40
totalSentences72
matches
0"I barely registered it before"
1"I turned, slower this time,"
2"Her hair was cropped close"
3"I managed, the name tasting"
4"She offered a strained smile,"
5"She gestured to the stool"
6"I shook my head, feeling"
7"It had been nearly eight"
8"I said, lamely"
9"It was the first thing"
10"she replied, her gaze flicking"
11"I winced, the reference to"
12"He gave me a knowing"
13"They were colder now, lacking"
14"I said, a ghost of"
15"She paused, then added, a"
16"I countered, wanting to recapture"
17"she said softly, turning the"
18"she asked, her gaze intense"
19"She took another sip of"
ratio0.556
29.44% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount62
totalSentences72
matches
0"Silas observed, polishing a glass"
1"A barman’s assessment of his"
2"The bell above the door"
3"I barely registered it before"
4"I turned, slower this time,"
5"The girl with the riotous"
6"Her hair was cropped close"
7"The vibrant floral dresses had"
8"A single, thin silver chain"
9"I managed, the name tasting"
10"She offered a strained smile,"
11"She gestured to the stool"
12"I shook my head, feeling"
13"It had been nearly eight"
14"I said, lamely"
15"It was the first thing"
16"she replied, her gaze flicking"
17"I winced, the reference to"
18"Silas slid a glass of"
19"He gave me a knowing"
ratio0.861
100.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount2
totalSentences72
matches
0"Before the arguments, before Evan's"
1"Though I wasn't sure, truly,"
ratio0.028
23.81% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences30
technicalSentenceCount5
matches
0"I shook my head, feeling a peculiar lump forming in my throat."
1"Eight years since I’d last seen her laugh, truly laugh, the kind that crumpled her face and made her eyes sparkle."
2"It was the first thing that came to mind, a desperately inadequate assessment of the woman sitting beside me."
3"I studied her face, searching for a trace of the girl I’d known, the girl who’d shared my hopes and fears, my dreams and disappointments."
4"She laughed, a short, brittle sound that didn’t reach her eyes."
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags26
uselessAdditionCount11
matches
0"I managed, the name tasting foreign on my tongue"
1"I said, lamely"
2"she replied, her gaze flicking around the room, avoiding mine"
3"I said, a ghost of a smile playing on my lips"
4"The words felt flat, inadequate"
5"she asked, her gaze intense"
6"she said finally, her voice low and precise"
7"she said, her eyes hard"
8"I said, the words leaving my mouth before I could stop them"
9"she said, her voice clipped"
10"Silas replied, his gaze drifting across the room"
90.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags14
fancyCount3
fancyTags
0"Silas observed (observe)"
1"I murmured (murmur)"
2"I challenged (challenge)"
dialogueSentences50
tagDensity0.28
leniency0.56
rawRatio0.214
effectiveRatio0.12
76.7496%