Run: 2026-04-24-01KQ0NHEKPPG8H9AH1JY7C6JXD

Run Details

Duration:
1m 51s
Cost:
$0.142515
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
Aurora caught the bottle before it broke, fingers closing around the wet neck, and looked straight into the face of the girl who had taught her how to disappear. Gin ran over her knuckles. The smell rose sharp and clean, a lie of medicine. Across the bar, the woman in the dark coat watched her with an expression polished so smooth it gave nothing back. “Rory Carter.” Aurora set the bottle upright. Her thumb found the small crescent scar on her left wrist, rubbed once, stopped. “Eva.” A man at the far end of the counter laughed too loudly at nothing. Silas Blackwood glanced from him to the woman, then to Aurora. His silver signet ring tapped once against the till. One beat. Warning or question, with Silas it often meant both. Eva Llewellyn had once worn cheap hoop earrings that turned her skin green. She had once kept loose coins in her bra because her father searched her pockets. She had once stood outside Aurora’s room in Cardiff with a bin bag full of clothes and said, Pack ugly things first, men always remember the red dress. This woman wore no earrings. Her hair, once a copper-brown riot, sat blunt at her jaw, black as ink except for a white seam above her left temple. A thin scar cut through one eyebrow. Her mouth held its old shape, wide and quick, but the warmth had gone from it. She looked expensive in a way that did not suggest money so much as consequence. “Still quick with your hands.” “Still walking into places like you own the fire exits.” Eva’s gaze flicked to the mirror behind the bottles, then to the front door, then to the small black dome of the camera above the old map of Prague. “Habit.” “Drink?” “Water. No ice.” “London changed you.” “Cardiff didn’t?” Aurora took a glass from the shelf. The Raven’s Nest breathed around them, low voices, clink of ice, the soft rasp of an old record Silas kept playing because he hated silence more than bad music. Black-and-white photographs lined the walls, men in wool coats, women with severe hair, streets that looked like wounds. The green neon sign outside bled through the front window and laid a sickly stripe across Eva’s cheek. Aurora filled the glass from the tap. “You’re not in for a hen do, then.” Eva took the water and did not drink. “You always did open with an insult when you wanted to hug someone.” “I grew out of hugs.” “Did you?” Behind them, Silas moved with his slight limp, clearing two empty tumblers from a table no one had sat at for ten minutes. He did not waste movements. He had the rare gift of making attention look like housekeeping. Eva watched him in the mirror. “So that’s him.” Aurora kept her face still. “That’s the man who owns the bar.” “Right.” “The pint-puller. The one who complains about licensing inspections and refuses to stock raspberry gin.” “Sounds wholesome.” “Eva.” The name landed badly. The woman’s fingers tightened round the glass until her knuckles paled. “People call me Eve now.” “People call me a lot of things. I don’t answer to the ones that lie.” A smile appeared, brief and ugly. “There she is.” Aurora wiped the counter where the gin had spilled. She pressed the cloth hard enough to leave her wrist aching. Years had made a room between them, and the room had no windows. She had not known whether Eva had married, left Wales, died, or become one of those women seen in passing on a station platform, familiar until the doors closed. “You look well.” “That’s kind of you.” “It wasn’t kindness.” “No. You never spent much on that.” Aurora dropped the cloth into the sink. “You vanished.” Eva stared at the water in her glass as if something small had drowned in it. “So did you.” “I ran.” “I packed the bag.” “You stopped answering.” “You stopped calling.” “I called twelve times.” “Thirteen. You forgot Christmas.” Aurora’s lips parted. Eva drank at last, a shallow sip. “Your number still ended in 0427. You used to say it sounded like a prison code.” Aurora looked past her, towards the door, because the sudden force of memory made the room seem too small. Cardiff University library. Rain on bike racks. Eva smoking under the No Smoking sign, saying law students looked like undertakers for money. A train ticket folded into Aurora’s palm. The metallic taste of panic while Evan pounded on the bathroom door. Silas placed a bowl of peanuts between them. “On the house.” Eva did not look at him. “I don’t eat from open bowls.” “Wise. Neither do rats, once they learn.” Aurora shot him a warning glance. Silas smiled without showing teeth. “Ms Llewellyn, I presume.” Eva’s stillness changed. It did not break. It sharpened. “You know me?” “I know most people who come in carrying trouble under a tailored coat.” “Then your reputation has manners it doesn’t deserve.” “My reputation has gout and a passport in another name. Sit down before you make my regulars curious.” The loud man at the end of the bar had stopped laughing. He stared at Eva’s coat, or at the bulge beneath it. Aurora saw it then, the wrong line near her ribs. Not a gun. Too flat. A packet, taped under the wool. Eva noticed the shift in Aurora’s eyes. “Don’t.” “Don’t what?” “Count exits. You get that little line between your eyebrows.” “You have something strapped to you.” “I have several disappointments strapped to me. Be specific.” Aurora came out from behind the bar. The floorboards of The Raven’s Nest gave soft complaints under her boots. The place had always felt like an old confession box, all dark wood and stale citrus, walls crowded with old maps whose borders had failed to save anyone. Silas kept a shelf of books near the back, heavy volumes nobody read. One of them, a cracked atlas with a red spine, opened the hidden room when pulled from its place. Aurora had found out by accident during her second week above the bar. Silas had called it curiosity. She had called it bad shelving. Eva slid into a booth beneath a photograph of a woman lighting a cigarette outside a bombed-out building. Aurora sat opposite her. For a moment neither of them spoke. Not a tender silence. A hard one, the kind used in interviews and hospital corridors. “Why here?” “I needed a place where men with clean hands lie for a living.” “Half of Soho, then.” “I needed him.” Eva’s gaze cut towards Silas. Aurora leaned back. “You came for Silas.” “I didn’t know you worked here.” “You expect me to believe that?” “I expected you to have left London by now.” “Back to Cardiff?” “Somewhere kinder.” Aurora laughed once. It sounded scraped out. “You sent me to London with forty quid, two jumpers, and a name written on a takeaway menu. Kindness wasn’t in the itinerary.” Eva’s face changed at the mention of the menu. There, for one small second, Aurora saw the old girl, the one with chipped nail varnish and fury bright enough to light a stairwell. “You still remember that?” “I lived on that memory for a month.” “You hated noodles.” “I delivered them for a living.” Eva looked at her hands. The nails sat short, clean, unpainted. A burn scar crossed the base of her thumb. Newer than the scar on her eyebrow. “Golden Empress?” Aurora’s eyes narrowed. “You have been looking.” “I listen. Different sin.” “Yu-Fei would throw you out for saying that with your shoes on the seat.” Eva took her boot off the booth edge at once, and that, more than any apology, struck Aurora in the ribs. Some manners survived war. Some girls still heard other women’s mothers. “You left me with Evan.” The words came before Aurora could dress them. Eva’s head lifted. “No.” “You did.” “No.” “He came to the flat in Cathays after I missed his calls. He broke the letterbox. He told my neighbour I had stolen his grandmother’s ring.” “You were already on the coach.” “And you were still there.” Eva’s mouth hardened. “Yes.” Aurora felt the booth press into her spine. “What happened?” “Nothing worth polishing.” “Eva.” The old name again. This time it hurt both of them. Aurora saw it land. Eva set the glass down. Her hand shook once, then stilled under the table. “He came with two friends. One had a dog chain round his fist. Evan always did like props. He cried first, you know. Made a whole little theatre of it. Said you’d ruined him. Said I’d filled your head.” “He said that to me too.” “I know.” “How?” “Because men like him write one script and tour it.” Aurora swallowed. The bar noise thinned to a hush, though no one had lowered their voice. “I thought you were angry with me.” “I was.” “For leaving?” “For not leaving sooner.” The words cut because Aurora had sharpened them herself for years. Eva looked towards the bar. Silas now spoke to the loud man with such calm that the man had gone pale. A ten-pound note lay untouched beside his pint. “I paid him.” Aurora gripped the edge of the table. “What?” “Evan. I paid him to stay away.” “With what money?” Eva smiled, a poor imitation of mischief. “You remember my rich aunt?” “You didn’t have a rich aunt.” “No. But I had a talent for making men think they’d underestimated me in the pleasant direction.” “Eva.” “I lifted from the wrong pocket.” The record clicked. No one moved to turn it over. Aurora saw the clean coat, the white seam in the hair, the scar. She saw, too late, the shape of the years. Not absence. Debt. “Who?” “A man who thought girls from Splott came with handles.” “And now?” “Now I carry things for people who carry people.” The packet under her coat seemed to swell between them. Aurora stood so fast the booth jolted. “You brought that here?” “I didn’t know you were here.” “That’s your defence?” “That’s my crime.” Silas appeared at the table with the quiet speed he used when violence started considering its options. “Ladies.” Aurora did not look away from Eva. “What is it?” Eva’s tongue touched the inside of her cheek. “Names.” Silas’s expression altered. Only a fraction, but Aurora knew him well enough to feel the drop in the room. “Whose?” “Yours is on the second page.” Silas’s hand closed round the back of a chair. The silver signet ring caught the green neon and flashed like a fish turning in dark water. “You opened it?” “I’m alive, aren’t I?” “Not an answer.” “No. A habit.” Aurora looked between them. “What second page?” Silas ignored her. “Who sent you?” Eva tapped the glass with one finger. Tick-tock. The sound made Aurora’s teeth ache. “Do you remember a man called Malden?” Silas did not blink. “Many men have names.” “This one lost an eye in Prague.” The old map above the bar seemed to lean closer. Aurora had never asked about Prague. Silas had never invited the question. His limp told one version. His silences told worse. Silas pulled the chair out and sat. That frightened Aurora more than if he had cursed. “Malden died.” “People keep saying that about men who don’t.” “Where is the package?” Eva reached inside her coat. Aurora caught her wrist. For one breath, they became girls again in a kitchen with peeling yellow paint, fighting over a stolen bottle of vodka, not knowing how close girlhood stood to the edge of a grave. Eva’s pulse jumped beneath Aurora’s fingers. Fast. Human. Terribly human. “Show me your other hand.” Eva’s eyes met hers. “You always notice the wrong miracle.” “Other hand.” Slowly, Eva placed her left hand on the table. Empty. Silas took the packet from under her coat. Brown paper. Grey tape. No postmark. No neat spycraft, just the ugly care of people who sent warnings wrapped like butcher’s meat. He opened it with a small knife from his waistcoat. Inside lay a stack of photographs and a cheap black phone. Aurora saw the top photograph and sat down without meaning to. Her own face stared back from it. Not recent. Cardiff. Nineteen, thinner, hair longer, eyes fixed somewhere beyond the frame. She stood outside the law building with a folder held to her chest. Evan’s hand rested on the back of her neck, fingers spread in ownership. Eva stood half in shot, blurred, mouth open as if she had just shouted. Aurora reached for it. Silas covered the photograph with his palm. “Don’t touch.” “That’s mine.” “No, Rory. That’s bait.” Eva’s throat worked. “There are more.” Silas lifted the next with the knife tip. Aurora above the Golden Empress, carrying a delivery bag. Aurora entering The Raven’s Nest. Aurora leaning from the upstairs window, cigarette she never lit between two fingers. Aurora asleep on the late bus, bright blue eyes closed, black hair against the glass. The last showed Brendan Carter outside Cardiff Crown Court, older, shoulders stooped beneath his barrister’s coat. Aurora’s chair scraped back. “Who took these?” The black phone lit before anyone touched it. A single line of text filled the screen. SHE WAS NEVER YOURS TO HIDE. Eva closed her eyes. Silas picked up the phone with a napkin and read the message once. “Out the back. Now.” Aurora turned on Eva. “You knew.” “I knew they had a file. I didn’t know it was you.” “You said names.” “And one of them was Laila.” The alias slid across the table like a blade from childhood. Laila, the false name Eva had used on the coach ticket. Laila, the name Aurora had signed on the first room she rented in London. Laila, the person invented to survive what Aurora could not. A glass shattered near the bar. The loud man at the counter had risen. His pint lay in amber pieces around his shoes. He stared at the front window, mouth slack. Silas moved first, his limp gone under purpose. “Down.” The green neon sign outside flickered. A shape stood beyond it, blurred by glass and reflected bottles. Tall. Broad through the shoulders. One hand pressed flat against the window, fingers splayed. Aurora knew that hand before she saw the face. Eva whispered one word, and for the first time all night she sounded twenty again. “Run.” The front door opened. Evan stepped into The Raven’s Nest with blood on his shirt and a gun hanging loose at his side. “Hello, Laila.”
created_at"2026-04-24T21:15:10.849Z" 4/24/2026, 9:15:10 PM
model"openai/gpt-5.5-20260423"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency33797
moderation_latency(null)
generation_time110510
tokens_prompt4618
tokens_completion4107
native_tokens_prompt4131
native_tokens_completion4638
native_tokens_completion_images0
native_tokens_reasoning1478
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"
usage0.142515
router(null)
provider_responses
0
endpoint_id"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id"resp_0f409b60b9eafcd00169ebdd5eedd081948ee1cf38e1286864"
is_byokfalse
latency307
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-1777065310-eHM7sFTc9pcDQcery8ll"
session_id(null)
api_type"completions"
id"gen-1777065310-qbVoZoLkUvwXYr5J8fLI"
upstream_id"resp_0f409b60b9eafcd00169ebdd5eedd081948ee1cf38e1286864"
total_cost0.142515
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
totalTags0
97.96% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount2445
totalAiIsmAdverbs1
found
0
adverb"slowly"
count1
highlights
0"slowly"
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)
77.51% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount2445
totalAiIsms11
found
0
word"eyebrow"
count2
1
word"warmth"
count1
2
word"flicked"
count1
3
word"silence"
count2
4
word"familiar"
count1
5
word"grave"
count1
6
word"pulse"
count1
7
word"shattered"
count1
8
word"flickered"
count1
highlights
0"eyebrow"
1"warmth"
2"flicked"
3"silence"
4"familiar"
5"grave"
6"pulse"
7"shattered"
8"flickered"
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
narrationSentences193
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount3
narrationSentences193
filterMatches
0"look"
hedgeMatches
0"seem to"
1"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences330
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen39
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords2445
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions17
unquotedAttributions0
matches(empty)
0.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions144
wordCount1735
uniqueNames23
maxNameDensity2.88
worstName"Aurora"
maxWindowNameDensity5
worstWindowName"Aurora"
discoveredNames
Blackwood1
Aurora50
Silas22
Llewellyn1
Cardiff4
Pack1
Prague2
Raven4
Nest4
Eva36
Wales1
University1
Smoking1
Evan3
Golden1
Empress1
Brendan1
Carter1
Crown1
Court1
London1
One3
Laila3
persons
0"Blackwood"
1"Aurora"
2"Silas"
3"Llewellyn"
4"Raven"
5"Nest"
6"Eva"
7"Evan"
8"Empress"
9"Brendan"
10"Carter"
11"One"
12"Laila"
places
0"Cardiff"
1"Prague"
2"Wales"
3"University"
4"London"
globalScore0.059
windowScore0
72.48% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences129
glossingSentenceCount4
matches
0"looked like wounds"
1"appeared, brief and ugly"
2"looked like undertakers for money"
3"felt like an old confession box, all da"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount2445
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount2
totalSentences330
matches
0"calm that the"
1"knew that hand"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs234
mean10.45
std13.69
cv1.311
sampleLengths
029
136
22
319
41
545
656
766
85
910
1029
111
121
133
143
152
1672
177
188
198
2013
215
222
2339
246
253
265
277
281
2915
302
311
3215
335
3415
356
363
3762
383
394
403
417
427
432
4416
453
462
474
483
493
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences193
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs273
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences330
ratio0
matches(empty)
94.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1741
adjectiveStacks1
stackExamples
0"lay untouched beside his"
adverbCount58
adverbRatio0.03331418724870764
lyAdverbCount9
lyAdverbRatio0.005169442848937392
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences330
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences330
mean7.41
std6.16
cv0.832
sampleLengths
029
15
210
321
42
55
614
71
814
911
109
112
129
1313
1415
1528
165
1723
187
1916
2015
215
2210
2329
241
251
263
273
282
297
3029
3118
3218
337
348
358
3613
375
382
3923
405
4111
426
433
445
457
461
4715
482
491
43.03% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats23
diversityRatio0.2878787878787879
totalSentences330
uniqueOpeners95
37.88% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences176
matches
0"Only a fraction, but Aurora"
1"Slowly, Eva placed her left"
ratio0.011
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount25
totalSentences176
matches
0"Her thumb found the small"
1"His silver signet ring tapped"
2"She had once kept loose"
3"She had once stood outside"
4"Her hair, once a copper-brown"
5"Her mouth held its old"
6"She looked expensive in a"
7"He did not waste movements."
8"He had the rare gift"
9"She pressed the cloth hard"
10"She had not known whether"
11"It did not break."
12"He stared at Eva’s coat,"
13"She had called it bad"
14"It sounded scraped out."
15"Her hand shook once, then"
16"She saw, too late, the"
17"His limp told one version."
18"His silences told worse."
19"He opened it with a"
ratio0.142
13.98% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount157
totalSentences176
matches
0"Aurora caught the bottle before"
1"Gin ran over her knuckles."
2"The smell rose sharp and"
3"Aurora set the bottle upright."
4"Her thumb found the small"
5"A man at the far"
6"Silas Blackwood glanced from him"
7"His silver signet ring tapped"
8"Eva Llewellyn had once worn"
9"She had once kept loose"
10"She had once stood outside"
11"This woman wore no earrings."
12"Her hair, once a copper-brown"
13"A thin scar cut through"
14"Her mouth held its old"
15"She looked expensive in a"
16"Eva’s gaze flicked to the"
17"Aurora took a glass from"
18"The Raven’s Nest breathed around"
19"The green neon sign outside"
ratio0.892
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences176
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences67
technicalSentenceCount3
matches
0"Aurora caught the bottle before it broke, fingers closing around the wet neck, and looked straight into the face of the girl who had taught her how to disappear…"
1"Eva Llewellyn had once worn cheap hoop earrings that turned her skin green."
2"Black-and-white photographs lined the walls, men in wool coats, women with severe hair, streets that looked like wounds."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags0
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags0
84.5609%