Run: 2026-07-09-01KX40J2VNQ97F310JK5WPGJDZ

Run Details

Duration:
31.2s
Cost:
$0.038569
Provider:
OpenAI

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
“Don’t turn round.” Aurora’s hand stopped halfway to the gin bottle. The tumbler on the shelf caught her face in fragments, black hair tucked behind one ear, bright blue eyes narrowed at the mirror. “People only say that when they want you to turn round.” “Then you’ve learned something in London.” The voice carried Cardiff in it, softened at the edges and sharpened elsewhere. Aurora set the bottle down. Behind her, the Raven’s Nest breathed its usual smoke-stained breath, old wood, spilled stout, fried onions from the kitchen, damp wool steamed from coats. Green neon from the sign outside stained the bottles along the back bar. Silas had filled the walls with maps and dead men in photographs, all those fixed faces watching living people make the same mistakes. Aurora turned. Eva Morgan stood by the end of the bar with both hands around a glass of water. For a moment, Rory saw her as she had been at seventeen, hair hacked short with kitchen scissors, a school tie painted black, grin wide enough to drag anybody into trouble. Then the old image folded away. Eva wore a charcoal coat that reached her calves and a narrow cream blouse beneath it. Her blond hair had grown long and hung in a smooth sheet over one shoulder. A small gold watch clung to her wrist. Her mouth held no smile. Fine lines bracketed it, not from laughter. “You look expensive,” Aurora said. “You look employed.” “I am employed.” “That’s a relief. Last I heard, you delivered chow mein on a bicycle.” “Still do. General Tso’s chicken has covered more rent than your father’s lectures on fiscal discipline.” Eva’s fingers tightened around the glass. Silas looked up from polishing a pint glass at the far end of the counter. His hazel eyes moved from Eva to Aurora, then to the door. He gave Aurora nothing else, which meant he had given her plenty. “You’re not going to hug me?” Eva asked. “You’ve been gone six years.” “Five.” “Five years, ten months. I keep a ledger.” “That sounds like you.” Aurora came round the bar. Her left wrist brushed the counter, and the small crescent scar flashed pale beneath her sleeve. She stopped an arm’s length from Eva. “You vanished.” “I moved.” “People move their furniture. You vanished.” Eva looked past her, towards the old photograph above the fireplace. It showed a young Silas in a dark suit beside a black car, before the limp and the grey in his beard, before the bar gave him a place to hide in plain sight. “I wrote to you.” “You wrote one letter. No return address. Two sentences.” “I didn’t know what else to say.” “You knew where I was.” “You changed your number.” “After Evan put it on a bathroom wall in Cathays.” The name slipped into the room and altered its shape. Silas stopped polishing the glass. Eva lowered her eyes to the water. “I heard.” “No. You heard a version. I sent you photographs.” “I know.” “Then why didn’t you call?” A man at the corner table laughed at something his companion said. The noise sounded misplaced, like a party held in a hospital corridor. Eva took a breath through her nose, slow and measured. “Because I was a coward.” “That’s clean of you.” “It’s not meant to be.” Aurora leaned against the bar. She had imagined this scene in less generous forms. Eva crying. Eva furious. Eva still wearing her battered boots, arriving with a cheap bottle of wine and a story that stitched the gap closed. Instead, this woman stood in silk and gold, her careful face built like a locked door. “Where have you been?” Aurora asked. “Working.” “At what?” “A firm.” “You always said suits made people look embalmed.” “They do. The salary helps.” “What firm?” Eva hesitated. Aurora saw it in the small shift of her jaw, the glance towards the green light on the front window. “Hargrave, Bell and Wren.” Aurora knew the name. Everybody with half an eye on London’s legal pages knew it. They handled corporate fraud, political damage, rich men caught with poor morals. Her father had once called them sharks with chamber memberships. “You got into Hargrave?” “I made partner last spring.” Aurora barked out a laugh before she could stop it. “You failed constitutional law twice.” “I passed it on the third go.” “You called the Magna Carta ‘a medieval customer charter’.” “I was drunk.” “You were always drunk.” Eva’s mouth twitched. The expression died before it became a smile. “Yes,” she said. “I was.” Silas placed a fresh tumbler in front of Aurora and poured gin without asking. He did not pour one for Eva. “Water’s the right choice,” he said. Eva looked at him. “Mr Blackwood.” “Mrs Morgan.” “Ms.” “Of course.” Aurora picked up her drink but left it untouched. “You got married.” Eva’s hand went to the gold watch. “Briefly.” “To whom?” “Does it matter?” “It matters if he taught you to sit like that.” Eva’s gaze snapped up. “Like what?” “Like you’re waiting for a headmaster to tell you off.” The old Eva would have fired back. She would have thrown a coaster, stolen the gin, made a filthy joke about headmasters. This Eva looked at Aurora with a tiredness that had no business on somebody’s face at twenty-five. “You don’t know anything about my life,” she said. “No. That’s the bloody point.” Silas moved down the bar to serve a couple near the till. His left leg dragged a fraction as he walked. He kept his body turned towards them, yet Aurora knew he listened. Silas did not own a bar because he loved hospitality. He owned it because secrets came thirsty. Eva placed a folded envelope on the counter. “There’s a reason I came.” “Of course there is.” “I did want to see you.” “But you also brought paperwork.” “It concerns Evan.” Aurora’s fingers closed around the tumbler. The glass gave a faint squeak against the bar. “Don’t.” “He contacted the firm.” “Then contact the police.” “He has lawyers.” “Everyone has lawyers. I hear one became you.” Eva flinched. Small. Real. “He lodged a complaint against you.” Aurora laughed again, though no humour reached it. “For what?” “Harassment. Defamation. Theft.” “Christ.” “He says you stole documents from his flat before you left Cardiff. He says you threatened him. He says you have continued to pursue him through false accounts.” “I deleted my Facebook.” “He knows.” “How?” Eva looked down. Aurora felt the answer arrive before the words did. “You told him.” “No.” “You told him where I was.” “I told someone who told him.” “Who?” “It doesn’t matter.” “It matters enough for you to cross the city with an envelope.” Eva pressed her lips together. “My husband worked with Evan.” The gin tasted of juniper and rust. Aurora set it down. “What did you say?” “He invested in one of Daniel’s companies. Nothing dramatic. A property scheme. Evan knew I knew you. He knew we were friends.” “Were.” “Don’t do that.” “Don’t do what?” “Make it sound simple.” Aurora stared at her. “You handed him my address.” “I gave Daniel the address. He said Evan wanted to apologise.” “And you believed him.” “I believed Daniel.” “Why?” Eva’s fingertips found the faint mark beneath her collar, half-hidden by the blouse. A purple shadow, old enough to have turned yellow at the edges. Aurora said nothing. “Daniel told me he needed it,” Eva said. “That was the sort of sentence I obeyed then.” “Then?” “He’s dead.” The bar noise seemed to recede. Aurora heard the refrigerator motor kick in. Somewhere in the back room, pipes clicked inside the walls. “How?” “He drove into a bridge support.” “That happened when?” “Four months ago.” “And you came here now because Evan found a new use for you.” Eva’s eyes shone, but she did not look away. “I came because he’s worse than he was.” “You knew that six years ago.” “I knew he hurt you. I did not know what I was helping him build.” Aurora picked up the envelope. It bore the firm’s address in neat black type. Her own name sat beneath it, Aurora Carter, as if the paper had a right to know her. “What’s in it?” “His complaint. A draft injunction. Names of people he’s paid.” “Paid for what?” “To watch you.” Silas reached beneath the counter. His hand vanished, then returned empty. Aurora had seen the movement before. He had a button under there, and another thing nobody discussed. Eva leaned closer. “He knows about this place. He knows you live upstairs.” Aurora’s eyes went to the front window. A taxi rolled past, its roof light smearing across the wet pavement. Beyond it, Soho churned with bodies and bright signs and all the hungry little businesses that survived by refusing to look too hard at their customers. “Why warn me?” Aurora asked. Eva’s face broke then, not with tears but with anger. “Because I am tired of watching men turn damage into a profession.” The front door opened. Evan stepped beneath the green neon, older than Aurora remembered, broader through the shoulders, his smile polished into something patient. Two men entered behind him and shut the door. Silas’s hand went beneath the bar again. Evan looked straight at Aurora. “There you are,” he said.
created_at"2026-07-09T17:59:40.162Z" 7/9/2026, 5:59:40 PM
model"openai/gpt-5.6-terra-20260709"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency6335
moderation_latency(null)
generation_time31014
tokens_prompt4618
tokens_completion2711
native_tokens_prompt4131
native_tokens_completion2502
native_tokens_completion_images0
native_tokens_reasoning485
native_tokens_cached4128
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
num_fetches(null)
web_search_engine(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"completed"
service_tier"default"
usage0.0385695
router(null)
provider_responses
0
endpoint_id"3cc89000-ae34-4dde-9c7d-5ce009c8af0b"
id"resp_0d965f8eda4cc363016a4fe18c3f648196b6a52d756546898f"
is_byokfalse
latency232
model_permaslug"openai/gpt-5.6-terra-20260709"
provider_name"OpenAI"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer(null)
request_id"req-1783619980-vlqEkVPyUMJwG51YjsZ5"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1783619980-RIdrNYujDvuElzfQ6SYT"
upstream_id"resp_0d965f8eda4cc363016a4fe18c3f648196b6a52d756546898f"
total_cost0.0385695
cache_discount0.009288
upstream_inference_cost0
provider_name"OpenAI"
response_cache_source_id(null)
data_region"global"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags9
adverbTagCount0
adverbTags(empty)
dialogueSentences117
tagDensity0.077
leniency0.154
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1560
totalAiIsmAdverbs0
found(empty)
highlights(empty)
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)
90.38% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1560
totalAiIsms3
found
0
word"measured"
count1
1
word"silk"
count1
2
word"churned"
count1
highlights
0"measured"
1"silk"
2"churned"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"eyes widened/narrowed"
count1
highlights
0"eyes narrowed"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells1
narrationSentences106
matches
0"t with anger"
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount1
narrationSentences106
filterMatches(empty)
hedgeMatches
0"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences214
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen34
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1560
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions21
unquotedAttributions0
matches(empty)
0.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions76
wordCount967
uniqueNames11
maxNameDensity3.1
worstName"Aurora"
maxWindowNameDensity5.5
worstWindowName"Eva"
discoveredNames
Cardiff1
Raven1
Nest1
Morgan1
Rory1
Eva29
Aurora30
Silas9
London1
Carter1
Soho1
persons
0"Raven"
1"Nest"
2"Morgan"
3"Rory"
4"Eva"
5"Aurora"
6"Silas"
7"Carter"
places
0"Cardiff"
1"London"
2"Soho"
globalScore0
windowScore0
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences71
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches1
per1kWords0.641
wordCount1560
matches
0"not with tears but with anger"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences214
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs156
mean10
std12.33
cv1.233
sampleLengths
03
131
211
36
478
52
617
737
851
95
103
113
1213
1316
146
1539
168
175
181
198
204
2128
222
232
246
2545
264
279
287
295
304
3110
3210
335
349
359
362
375
3834
395
404
415
4255
436
441
452
462
478
485
492
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences106
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs168
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences214
ratio0
matches(empty)
94.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount970
adjectiveStacks1
stackExamples
0"usual smoke-stained breath,"
adverbCount24
adverbRatio0.024742268041237112
lyAdverbCount0
lyAdverbRatio0
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences214
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences214
mean7.29
std5.74
cv0.787
sampleLengths
03
18
223
311
46
513
65
724
813
923
102
1117
1231
136
1416
1515
168
175
187
195
203
213
2213
2316
246
2515
2612
2712
288
295
301
318
324
335
3416
357
362
372
386
3911
4034
414
429
437
445
454
4610
4710
485
497
46.42% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats9
diversityRatio0.3037383177570093
totalSentences214
uniqueOpeners65
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount3
totalSentences90
matches
0"Then the old image folded"
1"Instead, this woman stood in"
2"Somewhere in the back room,"
ratio0.033
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount19
totalSentences90
matches
0"Her blond hair had grown"
1"Her mouth held no smile."
2"His hazel eyes moved from"
3"He gave Aurora nothing else,"
4"Her left wrist brushed the"
5"She stopped an arm’s length"
6"It showed a young Silas"
7"She had imagined this scene"
8"They handled corporate fraud, political"
9"Her father had once called"
10"He did not pour one"
11"She would have thrown a"
12"His left leg dragged a"
13"He kept his body turned"
14"He owned it because secrets"
15"It bore the firm’s address"
16"Her own name sat beneath"
17"His hand vanished, then returned"
18"He had a button under"
ratio0.211
10.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount81
totalSentences90
matches
0"Aurora’s hand stopped halfway to"
1"The tumbler on the shelf"
2"The voice carried Cardiff in"
3"Aurora set the bottle down."
4"Silas had filled the walls"
5"Eva Morgan stood by the"
6"Eva wore a charcoal coat"
7"Her blond hair had grown"
8"A small gold watch clung"
9"Her mouth held no smile."
10"Eva’s fingers tightened around the"
11"Silas looked up from polishing"
12"His hazel eyes moved from"
13"He gave Aurora nothing else,"
14"Aurora came round the bar."
15"Her left wrist brushed the"
16"She stopped an arm’s length"
17"Eva looked past her, towards"
18"It showed a young Silas"
19"The name slipped into the"
ratio0.9
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences90
matches(empty)
ratio0
73.17% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences41
technicalSentenceCount4
matches
0"Eva wore a charcoal coat that reached her calves and a narrow cream blouse beneath it."
1"Eva still wearing her battered boots, arriving with a cheap bottle of wine and a story that stitched the gap closed."
2"This Eva looked at Aurora with a tiredness that had no business on somebody’s face at twenty-five."
3"Beyond it, Soho churned with bodies and bright signs and all the hungry little businesses that survived by refusing to look too hard at their customers."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags9
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags9
fancyCount0
fancyTags(empty)
dialogueSentences117
tagDensity0.077
leniency0.154
rawRatio0
effectiveRatio0
87.1324%