Run: 2026-04-24-01KQ0NP40JEAM9ME8PRH5HJZ47

Run Details

Duration:
1m 34s
Cost:
$0.111645
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 around yet.” Aurora froze with a crate of empty bottles against her hip, one hand inside the glass bin, fingers slick with beer foam and old lime. The voice came from the far end of the bar, low and familiar enough to make her body recognise it before her mind allowed the name. She turned anyway. The woman sitting beneath the black-and-white photograph of Prague had once worn purple eyeliner to chapel and forged absence notes in three different teachers’ handwriting. She had once slept beside Aurora on a bedroom floor in Cardiff, both of them thirteen and furious at the adult world, eating dry cereal from the box while rain worried the window. She had once called at midnight and said, Come to London, Rory. Pack one bag. Don’t tell him. Eva Morgan lifted her glass in a small salute. “Still terrible at following instructions.” Aurora’s grip tightened on the crate. A brown bottle rolled, struck another, and rang like a cracked bell. Eva looked wrong in a way that expensive clothes could not hide. Her hair, once a wild copper cloud, lay cropped close to her skull and dyed a hard, glossy black. A thin white scar crossed her upper lip, pulling her smile into something sharper than memory allowed. She wore a tailored navy coat with the collar turned up, despite the heat that always clung to the Raven’s Nest after ten, and her left hand stayed gloved around the stem of her glass. “Eva.” “Rory.” “Nobody calls me that here.” “Then they don’t know you.” Behind the bar, The Raven’s Nest carried on with its usual low animal hum. Glasses knocked wood. A man in a wrinkled linen suit laughed too hard near the door under the distinctive green neon sign, trying to convince a woman half his age that his sadness counted as charm. Old maps covered the walls in pale continents and bruised seas. The photographs, Silas’ photographs, watched from their frames like witnesses who had signed nothing and remembered everything. Aurora set the crate down. “You disappeared.” Eva’s smile thinned. “You changed your number.” “You knew where I lived.” “You lived with him.” The words landed between them, small and filthy. Aurora reached for a cloth and wiped her hands longer than needed. The old instinct came first, conceal the wrist, hide the mark, give the room nothing. The small crescent-shaped scar on her left wrist flashed under the bar light before she tugged her sleeve down. Eva saw it. Of course she did. “Still got that.” “Childhood accidents have a way of sticking.” “Some accidents wear shoes.” Aurora looked at her then, properly. Not at the coat or the haircut or the hard line of Eva’s jaw, but at the hollows beneath her cheekbones, the careful way she sat with her back to the wall, the untouched bowl of salted nuts near her elbow. Eva had always devoured free snacks like a moral duty. She had never sat with her back exposed, never checked the mirror behind the spirits shelf for reflections, never smiled with only one side of her mouth. “What happened to you?” Eva gave a soft laugh with no air in it. “London. You?” “London.” “Liar. London doesn’t teach you to look at exits before faces.” Aurora folded the cloth into a square. Folded it again. “Neither did Cardiff.” A shadow moved in the mirror. Silas Blackwood emerged from the narrow corridor leading to the cellar, a crate of tonic water balanced against his ribs. He walked with his slight limp, smooth enough that most people missed it, but Aurora never did. He wore his usual white shirt with sleeves rolled to the forearms, silver signet ring catching the bar light as he set the crate down. His hazel eyes took in Eva, Aurora, the gloved hand, the untouched nuts, the space between them. “Friend of yours?” Eva turned on the stool. “Depends on the year.” Silas wiped his hands on a towel. “Ah. One of those.” “Silas, this is Eva Morgan.” A flicker passed over his face, subtle as a match struck in another room. “The Eva.” Eva’s gaze slid to Aurora. “You kept me as a definite article. Touching.” “You saved my life.” “No. I answered the phone.” “You sent money.” “Stolen money.” “You bought the train ticket.” “With stolen money.” “You stayed on the line.” Eva looked down into her drink. The glass held gin, probably, clear and cold and barely touched. “That part cost nothing.” Silas placed a coaster in front of her, though she already had one. It bore the Raven’s Nest logo, black bird, green circle, a little too elegant for the sort of people who came in to drown themselves by instalments. “First drink’s on the house for ghosts.” “I’m not dead.” “Then you can pay for the second.” Eva gave him a quick, appraising glance. “You always this hospitable?” “Only to people who enter through the front door and watch the mirror.” Aurora caught the shift. Eva’s fingers tightened on the glass stem. Silas’ right hand rested near the shelf beneath the till, where he kept nothing legal and several things useful. “Silas.” He did not look away from Eva. “She came in alone?” “Everyone comes in alone.” “That’s philosophy. I asked a practical question.” Eva drank at last. The gin barely wet her lips. “You MI5?” “Retired landlord.” “Retired men don’t stand like that.” “Women who visit old friends don’t keep gloves on indoors.” Aurora reached across the bar and put her palm flat on the wood. “Enough.” For a second all three of them listened to the bar breathe. A stool scraped. Ice cracked in a glass. Somewhere, someone fed coins into the old jukebox and got Nina Simone for their trouble. Her voice rose smoky and wounded, filling the gaps people left in themselves. Eva turned back to Aurora. “He knows about Evan?” Aurora’s mouth dried. “He knows enough.” “Does anyone ever know enough about a man like that?” “Don’t say his name here.” “Names don’t summon them.” Aurora gave a short laugh. “That’s new. You used to cross yourself when Mrs Price mentioned exams.” “I used to believe in things with rules.” Eva’s glove creaked as she flexed her hand. The sound drew Aurora’s eye. Eva noticed and held the hand still. “What’s under it?” “Skin.” “Eva.” “Less than before.” The old Eva would have made a joke broad enough to hide behind. This woman watched the exit while saying the sort of thing that left blood under the tongue. Aurora came around the end of the bar. Silas stepped aside but did not leave. He understood certain rooms, how two people could sit in them and still require witnesses. He understood danger in the shape of old affection. The stool beside Eva stood empty. Aurora did not take it. Sitting would make this social. This did not feel social. It felt like finding a sealed letter inside a wall. “Why are you here?” Eva traced the rim of her glass with her gloved thumb. “I wanted to see if you were all right.” “After four years?” “Five.” “Four and a half.” “Trust the future barrister to negotiate the sentence.” “I left uni.” “I heard.” “You heard?” Eva’s face closed. “People talk.” “What people?” “The kind you don’t invite to weddings.” Aurora leaned closer. “I didn’t have a wedding.” “No. You had a funeral and called it a relationship.” Silas made a small sound, not quite a cough. A warning, perhaps. Or sympathy, which from him often wore the same coat. Aurora felt the old anger stir, hot and clean at first, then dirtied by memory. Eva had always spoken like that, blade first, apology never. At sixteen, Aurora had loved it. At twenty, she had needed it. At twenty-five, it cut differently. “You don’t get to vanish and return with commentary.” “No.” “You don’t get to sit there with your spy gloves and your expensive coat and talk about my life as if you kept a seat in it.” “No.” “You don’t get to know things about me from people who aren’t me.” Eva nodded once. “No.” The agreement stripped the fight of its rails. Aurora had prepared for deflection, a smirk, some trick of old friendship. Not this. Silas took two glasses from the shelf and poured water into both. He set one near Aurora, one near Eva. “Nina’s on. Bad time for a duel.” Eva glanced at him. “You run a bar or a confessional?” “In Soho, the distinction lacks commercial value.” Aurora ignored the water. “Where did you go?” Eva looked towards the photograph above the end of the bar, a narrow street in Prague, black cobbles shining under a blurred lamp. Silas watched her recognise it, and something in his posture changed. “Europe.” “That’s not an answer.” “It’s a continent. Plenty of people make do.” “Eva.” The name cracked a little. Aurora hated that. Eva removed her right glove, slowly. Her hand looked thin, nails bitten short, knuckles split in old places. The left glove remained. “I went where the money went.” “What money?” “The money I stole for your train ticket.” Aurora frowned. “That was two hundred pounds.” “Three hundred. Don’t diminish my crimes.” “You said it came from your savings.” “I was twenty. My savings were a Boots loyalty card and a jar of coppers.” Silas’ gaze sharpened. “Whose money?” Eva’s mouth twisted. “A man who thought girls crying in office toilets made easy prey.” Aurora remembered then, not clearly, because that night had blurred around its edges. Evan asleep in the next room, or pretending to be. The bathroom light. Her own breath doing strange mechanical things. Eva on the phone, brisk and bright and ruthless. Listen to me, Rory. Shoes first. Not the red bag, he knows the red bag. Take the black one. There’s cash at Paddington. Platform three if he follows you, platform nine if he doesn’t. “You never told me.” “You had enough fear to carry.” “So you carried the rest?” Eva’s laugh came dry. “I carried it badly.” The front door opened. Green neon washed over two men in dark coats. Neither looked around like a customer searching for friends. They paused just inside, letting the door shut behind them, and both glanced at the mirror behind the bar. Silas saw them. Aurora saw Silas seeing them. Eva did not turn. Her shoulders went still. Silas picked up a tray of clean glasses and shifted towards the till. “Rory, fetch the Glenfarclas from the back.” “No one orders that.” “Someone’s about to.” Eva’s jaw moved once, teeth pressing together. “Don’t go to the back.” Aurora kept her face angled towards Eva. “Why?” “Because I used the front door.” Silas set the tray down without a sound. “One practical answer at last.” The two men moved to a corner table beneath an old map of the Balkans. One sat facing the room. The other stayed standing long enough to study the ceiling corners, the bar, the corridor to the toilets, the shelves of bottles with their amber, green, and clear throats. Customers glanced up, then away. London had trained them in selective blindness. Trouble belonged to whoever acknowledged it first. Aurora stepped nearer to Eva. “Who are they?” “Debt collectors.” “You owe money?” “Not money.” Silas’ signet ring tapped once on the bar. Tick-tock. “Names.” “The tall one calls himself Mercer. The other one doesn’t speak unless there’s bone involved.” Aurora looked at the seated man. He had a pleasant, blank face and hands folded on the table like a priest waiting for a bride. “What did you take?” Eva swallowed. For the first time since Aurora had turned, she looked young. Not younger. Young, as in unfinished. As if some part of her had stayed at twenty, stuck at the moment she had chosen theft over safety and then discovered the price kept adding itself up. “A ledger.” Silas’ eyes narrowed. “Whose ledger?” Eva met his gaze in the mirror. “Yours, I think.” The bar seemed to tilt half an inch. Silas did not move. That made it worse. “I keep accounts digitally.” “Not bar accounts.” Aurora looked between them. “What does that mean?” Eva reached inside her coat. Silas’ hand dropped under the bar in a blur. “Slowly.” Eva drew out a small black oilcloth packet and placed it beside her glass. The packet bore a dark stain along one corner, rust-brown, finger-shaped. “I didn’t know it was connected to you until I saw the sign outside.” “The sign?” “The green raven. It’s stamped inside the cover.” Silas stared at the packet as if it had crawled from a grave and remembered his address. “Where did you get this?” “From a dead man’s oven in Kilburn.” “Dead how?” “With enthusiasm.” Aurora’s skin prickled. Eva pushed the packet towards her rather than Silas. “That’s why I came. Not for forgiveness. Not for a drink. I thought if anyone near you still had a clean way out, it would be Rory.” Silas gave a humourless smile. “You overestimate innocence.” “No. I overestimate luck.” The man called Mercer rose from the corner table. He did not hurry. He adjusted his cuff, crossed the room, and stopped two stools away, close enough for his cologne to reach them, cedar, mint, something medicinal beneath. “Evangeline.” Eva’s eyes closed for one heartbeat. “Mercer.” “You cut your hair.” “You grew a conscience?” “Still theatrical. Cardiff did that to you?” Aurora felt the name like a hand at the back of her neck. Mercer turned to her. His face warmed with a polite smile that never reached his eyes. “And this must be Aurora Carter.” Silas stepped forward. “Private conversation.” Mercer glanced at the old maps, the photographs, the bottles, the exits. He looked amused by the fiction of privacy. “Mr Blackwood. Prague was unkind to you, I hear.” Silas’ expression did not change, but the air around him hardened. “Prague was unkind to several people.” “Fewer than deserved it.” Eva’s left hand trembled once under the glove. Aurora noticed. So did Mercer. His smile deepened. “Hand still aches?” Eva lifted her glass with the right hand. “Only when tedious men enter rooms.” Mercer leaned closer. “You took property.” “I returned it to circulation.” “You opened it.” “I’m curious.” “You read names you lack the discipline to forget.” Silas spoke then, soft and exact. “If you conduct business in my bar, buy a drink.” Mercer looked at him. “I’ll have what she’s having.” “No, you won’t.” The second man at the corner table stood. Conversations faltered nearby. The jukebox crooned on, indifferent and cruel. Aurora slid the oilcloth packet off the bar and tucked it behind the waistband of her jeans beneath her loose black shirt. Mercer’s eyes tracked the movement. “That belongs to my employer.” Aurora picked up a tray of dirty glasses. “Then your employer should label things more clearly.” “Rory.” Silas’ voice carried warning, but also something else. Calculation. Mercer smiled at Aurora as if she had performed well in a test designed to kill her. “Your father taught law, didn’t he? No, barrister. Brendan Carter. Irish. Fond of procedure. Your mother, Jennifer, Welsh, schoolteacher. Respectable people. Respectable people bruise so beautifully when disappointed.” The tray felt suddenly heavy. Eva rose from the stool. “Leave them out of it.” “There she is.” Mercer’s tone brightened. “There’s the girl from the office toilet. I wondered if London had eaten her whole.” Aurora saw it then, the old story beneath the new one. Not just stolen money. Not just a ledger. Eva had stepped into something years ago, and the door had closed behind her with Aurora’s name still in her mouth. Silas reached beneath the bar. Mercer lifted one finger. The second man opened his coat. Nobody screamed at first. The Raven’s Nest entered that strange silence before violence, when every glass on every table seemed to hold its breath. Then the front window burst inward. Green neon shattered into the room in bright, singing fragments. Customers dropped. Someone cried out. The man by the door folded with a red hole blooming through his white shirt, and Mercer seized Aurora by the wrist, his fingers closing over the crescent scar as if he had come for that exact piece of her.
created_at"2026-04-24T21:17:43.837Z" 4/24/2026, 9:17:43 PM
model"openai/gpt-5.5-20260423"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency6462
moderation_latency(null)
generation_time92969
tokens_prompt4618
tokens_completion4779
native_tokens_prompt4131
native_tokens_completion3609
native_tokens_completion_images0
native_tokens_reasoning70
native_tokens_cached3840
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"
usage0.111645
router(null)
provider_responses
0
endpoint_id"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id"resp_03b1cf6b2d1735c70169ebddf7ee4881949b2f14d13501e117"
is_byokfalse
latency258
model_permaslug"openai/gpt-5.5-20260423"
provider_name"OpenAI"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer(null)
request_id"req-1777065463-FijAIvNqOoaPpXbslZEZ"
session_id(null)
api_type"completions"
id"gen-1777065463-WJEM2p9d2qOfjtV1zrTZ"
upstream_id"resp_03b1cf6b2d1735c70169ebddf7ee4881949b2f14d13501e117"
total_cost0.111645
cache_discount0.01728
upstream_inference_cost0
provider_name"OpenAI"
response_cache_source_id(null)

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags2
adverbTagCount1
adverbTags
0"Prague had once [once]"
dialogueSentences156
tagDensity0.013
leniency0.026
rawRatio0.5
effectiveRatio0.013
94.49% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount2724
totalAiIsmAdverbs3
found
0
adverb"slowly"
count2
1
adverb"suddenly"
count1
highlights
0"slowly"
1"suddenly"
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)
81.64% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount2724
totalAiIsms10
found
0
word"familiar"
count1
1
word"charm"
count1
2
word"flicker"
count1
3
word"affection"
count1
4
word"traced"
count1
5
word"mechanical"
count1
6
word"grave"
count1
7
word"trembled"
count1
8
word"silence"
count1
9
word"shattered"
count1
highlights
0"familiar"
1"charm"
2"flicker"
3"affection"
4"traced"
5"mechanical"
6"grave"
7"trembled"
8"silence"
9"shattered"
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
emotionTells0
narrationSentences199
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount2
narrationSentences199
filterMatches(empty)
hedgeMatches
0"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences361
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen41
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords2724
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions14
unquotedAttributions0
matches(empty)
0.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions138
wordCount1846
uniqueNames17
maxNameDensity2.44
worstName"Eva"
maxWindowNameDensity5
worstWindowName"Eva"
discoveredNames
Prague2
Aurora42
Cardiff1
Come1
London2
Rory2
Morgan1
Raven4
Nest4
Eva45
Blackwood1
Nina1
Simone1
Paddington1
Silas18
Balkans1
Mercer11
persons
0"Aurora"
1"Rory"
2"Morgan"
3"Raven"
4"Nest"
5"Eva"
6"Blackwood"
7"Nina"
8"Simone"
9"Silas"
10"Mercer"
places
0"Prague"
1"Cardiff"
2"London"
3"Paddington"
globalScore0.281
windowScore0
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences118
glossingSentenceCount2
matches
0"felt like finding a sealed letter insid"
1"not quite a cough"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches1
per1kWords0.367
wordCount2724
matches
0"Not at the coat or the haircut or the hard line of Eva’s jaw, but at the hollows beneath her cheekbones, the careful way she s"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences361
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs258
mean10.56
std14.75
cv1.397
sampleLengths
04
151
23
376
49
55
618
783
81
91
105
115
1278
135
142
153
164
175
184
198
2046
217
223
237
244
2584
264
2710
282
291
3011
3110
323
3368
3417
353
365
374
387
394
405
4114
422
435
448
454
465
473
482
495
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences199
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs304
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences361
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount584
adjectiveStacks0
stackExamples(empty)
adverbCount9
adverbRatio0.015410958904109588
lyAdverbCount1
lyAdverbRatio0.0017123287671232876
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences361
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences361
mean7.55
std6.64
cv0.88
sampleLengths
04
125
226
33
425
533
612
73
83
99
105
116
1212
1312
1419
1517
1635
171
181
195
205
2114
223
2333
2411
2517
265
272
283
294
305
314
328
3312
3415
3519
363
374
383
397
404
416
4241
4310
4427
454
4610
472
481
4911
44.74% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats19
diversityRatio0.28254847645429365
totalSentences361
uniqueOpeners102
52.91% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount3
totalSentences189
matches
0"Of course she did."
1"Somewhere, someone fed coins into"
2"Then the front window burst"
ratio0.016
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount26
totalSentences189
matches
0"She turned anyway."
1"She had once slept beside"
2"She had once called at"
3"Her hair, once a wild"
4"She wore a tailored navy"
5"She had never sat with"
6"He walked with his slight"
7"He wore his usual white"
8"His hazel eyes took in"
9"It bore the Raven’s Nest"
10"He did not look away"
11"Her voice rose smoky and"
12"He understood certain rooms, how"
13"He understood danger in the"
14"It felt like finding a"
15"He set one near Aurora,"
16"Her hand looked thin, nails"
17"Her own breath doing strange"
18"They paused just inside, letting"
19"Her shoulders went still."
ratio0.138
31.43% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount162
totalSentences189
matches
0"Aurora froze with a crate"
1"The voice came from the"
2"She turned anyway."
3"The woman sitting beneath the"
4"She had once slept beside"
5"She had once called at"
6"Eva Morgan lifted her glass"
7"Aurora’s grip tightened on the"
8"A brown bottle rolled, struck"
9"Eva looked wrong in a"
10"Her hair, once a wild"
11"A thin white scar crossed"
12"She wore a tailored navy"
13"Glasses knocked wood."
14"A man in a wrinkled"
15"Aurora set the crate down."
16"Eva’s smile thinned."
17"The words landed between them,"
18"Aurora reached for a cloth"
19"The old instinct came first,"
ratio0.857
26.46% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences189
matches
0"As if some part of"
ratio0.005
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences68
technicalSentenceCount2
matches
0"It bore the Raven’s Nest logo, black bird, green circle, a little too elegant for the sort of people who came in to drown themselves by instalments."
1"The man by the door folded with a red hole blooming through his white shirt, and Mercer seized Aurora by the wrist, his fingers closing over the crescent scar a…"
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags2
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags0
87.7223%