Run: 2026-07-09-01KX40PKWXP3Z4HN5FJ3ER3QW5

Run Details

Duration:
36.2s
Cost:
$0.051022
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 touch the glass.” Aurora froze with two fingers hooked around the rim of a half-finished stout. The woman across the bar had spoken without turning round. Her black hair fell to her shoulders in a clean blunt line. A pale hand rested beside an untouched whisky, a thin scar curving across the left wrist like a crescent moon caught under skin. “Rory?” The woman shut her eyes. That small movement hurt more than any answer could have done. Silas Blackwood watched from the far end of the counter, polishing the same tumbler with a white cloth. His hazel eyes moved from Aurora to the stranger, then to the front door beneath the green neon raven. He did not interfere. Not yet. Aurora turned. “Eva.” The name came out flat, scraped bare by the years between them. Eva Mercer looked older than Aurora remembered, though that did not explain it. They had both grown older. Everyone did. Eva had once dressed as if colour might protect her, yellow coats, red boots, scarves with green parrots on them. Now she wore a charcoal suit beneath a black wool coat, its collar open at the throat. Her face had sharpened. Her mouth had learned to hold itself still. “You recognised me,” Eva said. “You haven’t changed that much.” A lie. An immediate, cowardly lie. Eva’s mouth twitched, not quite a smile. “You always did think the first lie should be a kind one.” Aurora drew her hand away from the stout. Her palm had left a wet print on the dark wood. The Raven’s Nest held its usual low murmur, old conversations poured into old walls. Yellowed maps crowded the panelling. Black-and-white photographs watched from crooked frames: men in overcoats outside embassies, women with cigarettes, a bridge in Prague with no names beneath it. Somebody had fed coins into the battered jukebox near the loos, but it only clicked and sighed. Silas placed a clean glass before Aurora. “Water,” he said. “I’m fine.” “You’ve had one drink and stopped listening to the room. Water.” Eva glanced at him. “Still collecting strays, Mr Blackwood?” Silas’s cloth paused. “Still making yourself difficult to find, Ms Mercer?” The old name landed with a dull thud. Aurora looked at Eva’s face and saw, for a second, the girl who had climbed through her bedroom window in Cardiff with a bottle of cheap cider tucked under one arm. Eva had always knocked first. She had always known when a locked door meant leave her alone and when it meant please do not leave. Aurora had not seen her since the station. Not a message. Not a call. Nothing after the last one, which Aurora had read until the screen dimmed and died. I’m here. I’ll wait until you answer. Then, after three days: Fine. Be gone, then. Aurora took the water. “What are you doing in Soho?” Eva looked at the whisky. She had not touched it. “What are you doing in a bar owned by a retired spy?” “Living above it.” “That tracks.” “What does?” “You found a man who knows how to lock doors.” Silas set the cloth down. “Mind your manners.” “I brought manners.” Eva lifted one hand. “They searched me at the door.” “No one searched you.” “Then your reputation has gone soft.” A man near the far wall laughed too loudly at something his companion said. Glass clinked. The door opened, spilling street noise and the sour smell of rain-soaked pavement into the room. A courier stepped inside, shook out a black umbrella, and left again after seeing every stool filled. Aurora studied Eva’s hands. No chipped nail varnish. No silver rings shaped like animals. No ink smudged over the side of her thumb from the pens she chewed while cramming for exams. “You work in law now?” Aurora asked. Eva’s gaze lifted. “Why?” “The suit. The voice.” “The voice?” “You used to sound like you had five thoughts fighting to get out at once.” “That was before I learned people listen harder when you make them wait.” Silas reached beneath the counter and brought out a bottle of whisky. He poured a measure into Eva’s empty glass, then capped it before she could object. “On the house,” he said. “I don’t drink.” “I didn’t ask.” Eva stared at the amber liquid. Aurora’s eyes caught the line of her wrist again. The scar. The old scar. Her own, not Eva’s. She pulled her sleeve down over it. “What happened to you?” Aurora asked. Silas looked up sharply. Eva let out a breath through her nose. “Straight to it, then.” “You vanished.” “So did you.” “I left Cardiff.” “You left your phone in a bin at the coach station.” “You knew why.” “I knew what you told me.” The whisky sat between them, glowing under the bar lights. Eva reached for it at last, though her hand stopped before the glass. “You told me Evan hit you,” she said. “You told me you were scared. You told me you needed to get out. I got you out.” “You did.” “Then I got a text from you saying not to contact you again.” Aurora said nothing. “That did not sound like you,” Eva continued. “It sounded like a solicitor’s letter. No swearing. No bad spelling. Not even one of those ridiculous little skulls you used to send when you were angry.” “I didn’t send it.” Eva’s face did not move. Aurora felt Silas watching now, not with curiosity but with the weary attention of someone who had seen old damage open under a clean shirt. “I never sent it,” Aurora said. “I lost my phone at the station.” “You lost it.” “Yes.” “And Evan had your number.” “Yes.” “And he knew about me.” Aurora tightened her fingers around the water glass. Condensation slicked her skin. “He knew everything. He read my messages. He knew where you worked. He knew your mum’s name. He knew your little brother had asthma. He made a list, Eva.” Eva blinked once. “A list.” “He wanted me to know he could reach you.” The Raven’s Nest seemed to shrink. The map behind the bar, a faded spread of Europe, hung in its frame like flayed skin. Eva looked away first. “I went to your parents,” she said. Aurora’s throat tightened. “They said you had gone to London.” “My dad told you?” “Your father opened the door and spoke to me as though I was selling roof insulation.” “That sounds like him.” “Your mother cried in the kitchen.” Aurora gripped the edge of the bar. “She cried?” “She did not know where you were. Brendan did. I could see it on him. He had that barrister face, all polished stone and legal phrasing. He said you were safe. He said your choices were your own.” Aurora gave a short laugh without humour. “Safe was his favourite word. He liked it because it meant he had done enough.” “I thought you had chosen not to come back.” “I did.” “You did not choose not to come back to me.” Aurora met her eyes. “No.” The answer held. No excuse could soften it. Eva had once known every corner of Aurora’s life. The hidden cigarette burns on the garden wall. The cracked tile by the Carter kitchen sink. The way Aurora’s father lowered his voice before he said something that would cut. Eva had known the bruises before Aurora admitted them. She had packed a bag in silence. She had bought a coach ticket in cash. Then Aurora had stepped off the coach in London, followed Eva through streets she did not know, and disappeared from the life that had saved her. “I was afraid,” Aurora said. Eva’s laugh broke out clean and bitter. “Of me?” “Of him. Of what he would do if I replied. Of what he had already done. I got a new number. I told myself I would call when it settled down.” “And did it?” “No.” “Years pass, Rory. They do not settle. They pile up.” Silas’s signet ring clicked against the bar as he picked up a bottle. The sound cut through Aurora. She had seen that ring catch light during meetings in the hidden room beyond the bookshelf, when people entered with secrets tucked under their tongues and left lighter or ruined. Eva noticed the look. “You work for him?” “I deliver food for Golden Empress. Sometimes I help out here.” “Help out.” “He has contacts.” “Of course he does.” Eva’s gaze shifted to Silas. “You took in a young woman who had cut every thread to her old life. That must have made you feel useful.” Silas leaned both hands on the counter. “Careful.” “Why? Does she not know what this place is?” Aurora’s jaw set. “She knows enough.” “No one does,” Silas said. Eva finally picked up the whisky. She did not drink. She held the glass beneath her nose and inhaled, as if testing a chemical. “You always loved places with rules,” Eva said to Aurora. “That was the trick, was it not? Evan made rules, your father made rules, then London offered you a new set with better furniture.” “You do not know anything about my life.” “I know you stopped answering.” “I know you stopped looking.” Eva set the whisky down too hard. The glass struck wood. A few drops leapt over the rim. “I hired someone.” Aurora went still. “What?” “Two years after you vanished. I had money by then. I worked in compliance for a private bank, which means I spent my days helping rich men look surprised when their money came from places with no clean water. I paid a man to find you.” Silas’s expression changed. Only a fraction, but Aurora saw it. “And?” she asked. “He found a woman named Laila working deliveries out of a Chinese restaurant in London. Same age. Same build. Black hair. The address led to a flat above this bar.” Aurora felt the blood leave her face. “You knew.” “I stood across the road.” “Two years ago?” “Yes.” “You watched me?” “I watched you carry cartons of food into a building with a green bird over the door. You looked…” Eva stopped. Her thumb circled the glass rim. “You looked like someone had taught you how not to be seen.” “And you left.” “You had walked away from me once already.” “I did not walk away from you.” “You did not come back.” Aurora swallowed. Words crowded behind her teeth, useless and late. She pictured Eva across the street, anonymous beneath passing faces, seeing her without being seen. It felt intimate in the worst way. It felt like finding a photograph taken through a window. “Why now?” Aurora asked. Eva looked at her for a long moment. “Because Evan Price is dead.” The jukebox clicked again. This time it began to play, a warped piano tune that limped through the opening notes. Aurora stared at Eva. “What?” “He died three weeks ago.” “No.” “He did.” “No.” Her voice rose. “That is not funny.” “I did not come here to make you laugh.” “How?” Eva’s lips pressed together. “Someone found him in a rented flat in Newport. He had been using another name. There was no funeral worth attending. His sister collected the body.” Aurora’s hand moved to her wrist beneath the sleeve. Her thumb found the crescent scar, then stopped. Not that mark. Another memory sat beneath it, bruised knuckles, a locked bathroom, Evan’s voice outside the door. She pulled her hand away. “You knew,” she said. “I found out through work. A report crossed my desk.” “You came all this way to tell me he’s dead?” “I came because the police found a folder in his flat.” Silas straightened. Eva reached inside her coat and drew out a brown document envelope. It had softened at the corners from being carried too long. She placed it on the bar between the whisky and the water. Aurora did not touch it. “What is that?” “Photographs. Addresses. Notes.” Eva’s eyes held hers. “Names of women.” Silas’s ring tapped once against the counter. “Police should have that,” he said. “They have copies.” Eva looked at him. “They do not have all of it.” “That is a dangerous distinction.” “One of the names is mine,” Aurora said. Eva nodded. “And yours?” Another nod. Aurora looked at the envelope. The neat black writing on its face made her stomach turn. AURORA CARTER EVA MERCER Under the names, in a hand Aurora recognised with sick certainty, Evan had written: LONDON. RAVEN’S NEST. The front door slammed open. A man stood beneath the green neon spill, rainwater shining on his dark coat. He held a mobile phone to his ear and stared straight at Aurora. Then he smiled.
created_at"2026-07-09T18:02:08.678Z" 7/9/2026, 6:02:08 PM
model"openai/gpt-5.6-terra-20260709"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency570
moderation_latency(null)
generation_time36136
tokens_prompt4618
tokens_completion3522
native_tokens_prompt4131
native_tokens_completion2713
native_tokens_completion_images0
native_tokens_reasoning0
native_tokens_cached0
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"
usage0.0510225
router(null)
provider_responses
0
endpoint_id"3cc89000-ae34-4dde-9c7d-5ce009c8af0b"
id"resp_065a3bae1c665660016a4fe220c3d48195aa00712861dd6237"
is_byokfalse
latency255
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-1783620128-hoEV2NJXZ53uKn7b209b"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1783620128-1H3rKobEA84WAFGYbXy1"
upstream_id"resp_065a3bae1c665660016a4fe220c3d48195aa00712861dd6237"
total_cost0.0510225
cache_discount(null)
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
totalTags22
adverbTagCount0
adverbTags(empty)
dialogueSentences130
tagDensity0.169
leniency0.338
rawRatio0
effectiveRatio0
97.65% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount2131
totalAiIsmAdverbs1
found
0
adverb"sharply"
count1
highlights
0"sharply"
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)
95.31% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount2131
totalAiIsms2
found
0
word"silence"
count1
1
word"stomach"
count1
highlights
0"silence"
1"stomach"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"let out a breath"
count1
highlights
0"let out a breath"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences165
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount2
narrationSentences165
filterMatches(empty)
hedgeMatches
0"seemed to"
1"began to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences272
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen46
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords2131
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions32
unquotedAttributions0
matches(empty)
0.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions108
wordCount1240
uniqueNames14
maxNameDensity3.39
worstName"Aurora"
maxWindowNameDensity6.5
worstWindowName"Aurora"
discoveredNames
Blackwood1
Aurora42
Mercer1
Raven2
Nest2
Prague1
Eva38
Cardiff1
Fine1
Silas14
Europe1
Carter1
London1
Evan2
persons
0"Blackwood"
1"Aurora"
2"Mercer"
3"Raven"
4"Nest"
5"Eva"
6"Silas"
7"Carter"
8"Evan"
places
0"Prague"
1"Cardiff"
2"Europe"
3"London"
globalScore0
windowScore0
55.06% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences79
glossingSentenceCount3
matches
0"not quite a smile"
1"as if testing a chemical"
2"felt like finding a photograph taken th"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches1
per1kWords0.469
wordCount2131
matches
0"not with curiosity but with the weary attention of someone who had seen old damage"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences272
matches
0"seen that ring"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs194
mean10.98
std13.75
cv1.252
sampleLengths
04
158
21
35
411
543
62
71
812
969
105
115
126
137
1412
1578
167
173
182
1911
204
215
223
238
2464
258
2621
277
284
294
304
316
3210
3312
343
352
362
3710
385
393
4013
414
426
4349
4432
457
463
471
484
492
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences165
matches
0"being seen"
1"being carried"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs221
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences272
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1244
adjectiveStacks0
stackExamples(empty)
adverbCount32
adverbRatio0.02572347266881029
lyAdverbCount6
lyAdverbRatio0.00482315112540193
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences272
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences272
mean7.83
std6.85
cv0.874
sampleLengths
04
113
210
312
423
51
65
711
818
919
104
112
122
131
1412
1513
165
172
1820
1917
204
218
225
235
242
254
267
2712
288
2911
3014
315
3223
3317
347
353
362
3711
384
395
403
418
428
4331
445
4520
468
473
483
4915
41.18% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats24
diversityRatio0.22794117647058823
totalSentences272
uniqueOpeners62
99.50% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount4
totalSentences134
matches
0"Then, after three days:"
1"Then Aurora had stepped off"
2"Only a fraction, but Aurora"
3"Then he smiled."
ratio0.03
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount28
totalSentences134
matches
0"Her black hair fell to"
1"His hazel eyes moved from"
2"He did not interfere."
3"They had both grown older."
4"Her face had sharpened."
5"Her mouth had learned to"
6"Her palm had left a"
7"She had always known when"
8"I’ll wait until you answer."
9"She had not touched it."
10"He poured a measure into"
11"Her own, not Eva’s."
12"She pulled her sleeve down"
13"She had packed a bag"
14"She had bought a coach"
15"She had seen that ring"
16"She did not drink."
17"She held the glass beneath"
18"Her thumb circled the glass"
19"She pictured Eva across the"
ratio0.209
19.70% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount118
totalSentences134
matches
0"Aurora froze with two fingers"
1"The woman across the bar"
2"Her black hair fell to"
3"A pale hand rested beside"
4"The woman shut her eyes."
5"That small movement hurt more"
6"Silas Blackwood watched from the"
7"His hazel eyes moved from"
8"He did not interfere."
9"The name came out flat,"
10"Eva Mercer looked older than"
11"They had both grown older."
12"Eva had once dressed as"
13"Her face had sharpened."
14"Her mouth had learned to"
15"An immediate, cowardly lie."
16"Eva’s mouth twitched, not quite"
17"Aurora drew her hand away"
18"Her palm had left a"
19"The Raven’s Nest held its"
ratio0.881
37.31% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences134
matches
0"Now she wore a charcoal"
ratio0.007
94.16% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences44
technicalSentenceCount3
matches
0"Aurora felt Silas watching now, not with curiosity but with the weary attention of someone who had seen old damage open under a clean shirt."
1"The way Aurora’s father lowered his voice before he said something that would cut."
2"She held the glass beneath her nose and inhaled, as if testing a chemical."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags22
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags17
fancyCount1
fancyTags
0"Eva continued (continue)"
dialogueSentences130
tagDensity0.131
leniency0.262
rawRatio0.059
effectiveRatio0.015
87.9958%