Run: 2026-03-03-01KJTZD1GR7B1ZAANCJQ4WCAAC

Run Details

Duration:
3m 51s
Cost:
$0.004190
Provider:
Seed

Model input

System
You are an expert and award-winning novel writer in the dark Literary Fiction genre. Your readers are hooked on your stories and can't wait to read the book you have in store. <important> - MUST: Start each chapter in medias res (in the middle of action). AVOID talking about the weather, time of day, the position of the sun, or other boring stuff. - The instructions/summary are just a that, a summary. Feel free to add details, stretch sections and add interesting transitions/descriptions/fillers. - When called for it, have fast-paced action, but otherwise take things slow. This is an experience, and not for people with short attention spans. Enjoy the wine, not slurp Red Bull. - Add descriptions when transitioning places/times/etc, or when coming by new places (e.g. a corner shop, a cafe, etc.). But remember: NOT at the start or end of a chapter. - MUST: AVOID ending in internal monologue, reminiscing or waiting for the next day. A good chapter end is when we're ending right when shit hits the fan. We want to have the reader be excited for what comes next. So no reminiscing, contemplating or summarizing the day. It's popcorn time! </important>
User/Human
Take into account the following glossary of characters/locations/items/lore... when writing your response: <codex> <character id="4412" name="Aurora Carter" aliases="Rory, Laila, Aurora, Carter, Malphora" pronouns="she/her" species="Human" storyRole="Protagonist"> <eyeColor>bright blue</eyeColor> <hair>straight shoulder-length black</hair> <height>5'6"</height> <age>25</age> <scar>small crescent-shaped scar on her left wrist from a childhood accident</scar> <description>Aurora, referred to by her friends as Rory, is cool-headed, intelligent, and known for quick out-of-the-box thinking.</description> <backstory>Born in Cardiff to an Irish barrister father (Brendan Carter) and Welsh teacher mother (Jennifer Carter née Ellis), Rory reluctantly pursued Pre-Law at Cardiff University. She fled to London at the behest of her childhood friend Eva after leaving an abusive ex named Evan. By day, Rory works part-time as a delivery person for Yu-Fei Cheung's Golden Empress restaurant. She lives in a flat above Silas' bar.</backstory> </character> <character id="4413" name="Silas Blackwood" aliases="Silas, Si, the Spymaster" pronouns="he/him" species="Human" storyRole="Mentor"> <eyeColor>hazel</eyeColor> <hair>grey-streaked auburn</hair> <height>6'1"</height> <age>58</age> <beard>neatly trimmed, matching his grey-streaked auburn hair</beard> <limp>slight limp in his left leg from an old knee injury</limp> <signetRing>silver signet ring, always worn on his right hand</signetRing> <description>Silas is a retired intelligence operative turned bar owner. He carries himself with quiet authority.</description> <backstory>Former MI6 field agent who retired after a botched operation in Prague left him with a permanent knee injury. He opened "The Raven's Nest" bar in Soho as a front for his network of contacts.</backstory> </character> <location id="854" name="The Raven's Nest" aliases="the Nest, Raven, Silas' bar" realm="Earth"> <signColor>distinctive green neon sign above the entrance</signColor> <secretRoom>hidden back room accessible through a bookshelf, used for clandestine meetings</secretRoom> <description>A dimly lit bar in Soho, London. The walls are covered with old maps and black-and-white photographs.</description> </location> </codex> <proseGuidelines> <styleGuide> - Write in past tense and use British English spelling and grammar - Keep a Flesch reading ease score of 60 - Respect the the Royal Order of Adjectives: The order is: opinion, size, age, shape, color, origin, material, purpose, followed by the noun itself (e.g., "a lovely little old rectangular green French silver whittling knife") - Respect the ablaut reduplication rule (e.g. tick-tock, flip-flop) - Write in active voice - Passive voice: <bad>The book was read by Sarah.</bad> - Active voice: <good>Sarah read the book.</good> - Reduce the use of passive verbs - <bad>For a moment, I was tempted to throw in the towel.</bad> - <good>For a moment, I felt tempted to throw in the towel.</good> - Avoid misplaced modifiers that can cause confusion when starting with "-ing" words: - <bad>Considering going to the store, the empty fridge reflected in Betty's eyes.</bad> - <good>Betty stared into the empty fridge. It was time to go to the store.</good> - Avoid redundant adverbs that state the obvious meaning already contained in the verb: - <bad>She whispered quietly to her mom.</bad> - <good>She whispered to her mom.</good> - Use stronger, more descriptive verbs over weak ones: - <bad>Daniel drove quickly to his mother's house.</bad> - <good>Daniel raced to his mother's house.</good> - Omit adverbs that don't add solid meaning like "extremely", "definitely", "truly", "very", "really": - <bad>The movie was extremely boring.</bad> - <good>The movie was dull.</good> - Use adverbs to replace clunky phrasing when they increase clarity: - <bad>He threw the bags into the corner in a rough manner.</bad> - <good>He threw the bags into the corner roughly.</good> - Avoid making simple thoughts needlessly complex: - <bad>After I woke up in the morning the other day, I went downstairs, turned on the stove, and made myself a very good omelet.</bad> - <good>I cooked a delicious omelet for breakfast yesterday morning.</good> - Never backload sentences by putting the main idea at the end: - <bad>I decided not to wear too many layers because it's really hot outside.</bad> - <good>It's sweltering outside today, so I dressed light.</good> - Omit nonessential details that don't contribute to the core meaning: - <bad>It doesn't matter what kind of coffee I buy, where it's from, or if it's organic or not—I need to have cream because I really don't like how the bitterness makes me feel.</bad> - <good>I add cream to my coffee because the bitter taste makes me feel unwell.</good> - Always follow the "show, don't tell" principle. For instance: - Telling: <bad>Michael was terribly afraid of the dark.</bad> - Showing: <good>Michael tensed as his mother switched off the light and left the room.</good>- Telling: <bad>I walked through the forest. It was already Fall, and I was getting cold.</bad> - Showing: <good>Dry orange leaves crunched under my feet. I pulled my coat's collar up and rubbed my hands together.</good>- Add sensory details (sight, smell, taste, sound, touch) to support the "showing" (but keep an active voice) - <bad>The room was filled with the scent of copper.</bad> - <good>Copper stung my nostrils. Blood. Recent.</good> - Use descriptive language more sporadically. While vivid descriptions are engaging, human writers often use them in bursts rather than consistently throughout a piece. When adding them, make them count! Like when we transition from one location to the next, or someone is reminiscing their past, or explaining a concept/their dream... - Avoid adverbs and clichés and overused/commonly used phrases. Aim for fresh and original descriptions. - Avoid writing all sentences in the typical subject, verb, object structure. Mix short, punchy sentences with long, descriptive ones. Drop fill words to add variety. Like so: <good>Locked. Seems like someone doesn't want his secrets exposed. I can work with that.</good> - Convey events and story through dialogue. It is important to keep a unique voice for every character and make it consistent. - Write dialogue that reveals characters' personalities, motivations, emotions, and attitudes in an interesting and compelling manner - Leave dialogue unattributed. If needed, only use "he/she said" dialogue tags and convey people's actions or face expressions through their speech. Dialogue always is standalone, never part of a paragraph. Like so: - <bad>"I don't know," Helena said nonchalantly, shrugging her shoulders</bad> - <good>"No idea" "Why not? It was your responsibility"</good> - Avoid boring and mushy dialog and descriptions, have dialogue always continue the action, never stall or include unnecessary fluff. Vary the descriptions to not repeat yourself. Avoid conversations that are just "Let's go" "yes, let's" or "Are you ready?" "Yes I'm ready". Those are not interesting. Think hard about every situtation and word of text before writing dialogue. If it doesn't serve a purpose and it's just people talking about their day, leave it. No one wants to have a normal dinner scene, something needs to happen for it to be in the story. Words are expensive to print, so make sure they count! - Put dialogue on its own paragraph to separate scene and action. - Use body language to reveal hidden feelings and implied accusations- Imply feelings and thoughts, never state them directly - NEVER use indicators of uncertainty like "trying" or "maybe" - NEVER use em-dashes, use commas for asides instead </styleGuide> <voiceGuide> Each character in the story needs to have distinct speech patterns: - Word choice preferences - Sentence length tendencies - Cultural/educational influences - Verbal tics and catchphrases Learn how each person talks and continue in their style, and use their Codex entries as reference. <examples> - <bad>"We need to go now." "Yes, we should leave." "I agree."</bad> <good>"Time's up." "Indeed, our departure is rather overdue." "Whatever, let's bounce."</good> - Power Dynamic Example: <bad> "We need to discuss the contract." "Yes, let's talk about it." "I have concerns." </bad> <good> "A word about the contract." "Of course, Mr. Blackwood. Whatever you need." "The terms seem..." A manicured nail tapped the desk. "Inadequate." "I can explain every-" "Can you?" </good> </examples> </voiceGuide> <dialogueFlow> When writing dialogue, consider that it usually has a goal in mind, which gives it a certain flow. Make dialogue sections also quite snappy in the back and forth, and don't spread the lines out as much. It's good to have details before, after, or as a chunk in-between, but we don't want to have a trail of "dialogue breadcrumbs" spread throughout a conversation. <examples> - Pattern 1 - Question/Deflection/Revelation: <good> "Where were you last night?" "Work. The usual." "Lipstick's an interesting shade for spreadsheets." </good> - Pattern 2 - Statement/Contradiction/Escalation: <good> "Your brother's clean." "Tommy doesn't touch drugs." "I'm holding his tox screen." </good> - Pattern 3 - Observation/Denial/Truth: <good> "That's a new watch." "Birthday gift." "We both know what birthdays mean in this business." </good> - Example - A Simple Coffee Order: <bad> "I'll have a coffee." "What size?" "Large, please." </bad> <good> "Black coffee.""Size?""Large. Been a long night." "That bodega shooting?" "You watch too much news." "My brother owns that store." </good> This short exchange: - Advances plot (reveals connection to crime) - Shows character (cop working late) - Creates tension (unexpected connection) - Sets up future conflict (personal stake) - Example - Dinner Scene: <bad> "Pass the salt." "Here you go." "Thanks." </bad> <good> "Salt?" "Perfect as is. Mother's recipe." "Mother always did prefer... bland things." "Unlike your first wife?" </good> - Example - Office Small Talk: <bad> "Nice weather today." "Yes, very nice." "Good for golf." </bad> <good> "Perfect golf weather." "Shame about your membership." "Temporary suspension. Board meets next week." "I know. I called the vote." </good> </examples> </dialogueFlow> <subtextGuide> - Layer dialogue with hidden meaning: <bad>"I hate you!" she yelled angrily.</bad> <good>"I made your favorite dinner." The burnt pot sat accusingly on the stove.</good> - Create tension through indirect communication: <bad>"Are you cheating on me?"</bad> <good>"Late meeting again?" The lipstick stain on his collar caught the light.</good> <examples> - Example 1 - Unspoken Betrayal: <bad> "Did you tell them about our plans?" "No, I would never betray you." "I don't believe you." </bad> <good> "Funny. Johnson mentioned our expansion plans today." "The market's full of rumors." "Mentioned the exact numbers, actually." The pen in his hand snapped. </good> - Example 2 - Failed Marriage: <bad> "You're never home anymore." "I have to work late." "I miss you." </bad> <good> "Your dinner's in the microwave. Again." "Meetings ran long." "They always do." She folded the same shirt for the third time. </good> - Example 3 - Power Struggle: <bad> "You can't fire me." "I'm the boss." "I'll fight this." </bad> <good> "That's my father's nameplate you're sitting behind." "Was." "The board meeting's on Thursday." </good> </examples> </subtextGuide> <sceneDetail> While writing dialogue makes things more fun, sometimes we need to add detail to not have it be a full on theatre piece. <examples> - Example A (Power Dynamic Scene) <good> "Where's my money?" The ledger snapped shut. "I need more time." "Interesting." He pulled out a familiar gold pocket watch. My mother's. "Time is exactly what you bargained with last month." "That was different-" "Was it?" The watch dangled between us. "Four generations of O'Reillys have wound this every night. Your mother. Your grandmother. Your great-grandmother.Shall we see who winds it next?" </good> - Example B (Action Chase) It's much better to be in the head of the character experiencing it, showing a bit of their though-process, mannerisms and personality: <good> Three rules for surviving a goblin chase in Covent Garden: Don't run straight. Don't look back. Don't let them herd you underground. I broke the first rule at Drury Lane. Rookie mistake. The fruit cart I dodged sailed into the wall behind me. Glass shattered. Someone screamed about insurance. *Tourist season's getting rough*, the scream seemed to say. Londoners adapt fast. "Oi! Market's closed!" The goblin's accent was pure East End. They're evolving. Learning. I spotted the Warren Street tube station sign ahead. *Shit.* There went rule three. </good> - Example C (Crime Scene Investigation) <good> "Greek." Davies snapped photos of the symbols. "No, wait. Reverse Greek." "Someone's been watching too many horror films." I picked up a receipt from the floor. Occult supply shop in Camden. Paid by credit card. *Amateur hour*. "Could be dangerous though," Davies said. "Remember Bristol?" "Bristol was Sanskrit. And actual cultists." I pointed to the nearest symbol. "This genius wrote 'darkness' backwards but used a Sigma instead of an S. It's summoning Instagram followers at best." "Speaking of followers..." Davies pointed to heavy foot traffic in the dust. Multiple sets. All new trainers. *Ah.* "Anyone check local uni paranormal societies?" </good> - Example D (Dialogue-heavy) <good> "Found your card in her wallet." The detective slid it across the table. Worn edges. Folded corner. Three years old at least. "Standard practice. I work missing persons." "Funny thing about missing persons.Eventually they stop being missing. Turn up in the Thames. Under motorways. In pieces." "I don't-" "You found four last year. All breathing." She opened a file. "This would've been your first dead one. If we hadn't found her first." The card felt heavier somehow. </good> </examples> </sceneDetail> <sceneOpenings> KEY RULE: Never open with more than one paragraph of description, no matter how beautiful. Description should be earned through action and dialogue. Instead of opening with setting description, open with: - A character doing something specific - A line of dialogue that raises questions - An unexpected observation - A moment of tension or conflict - Start with a hook that's 1-2 sentences maximum - Follow with a smaller paragraph that provides immediate context - Vary paragraph size from the start to create visual interest </sceneOpenings> </proseGuidelines> Write a chapter based on the following instructions: <instructions> Write a fully fleshed out scene of at least 1000 words in the literary fiction genre. Two old friends who haven't seen each other in years run into each other unexpectedly at a bar. One of them has changed significantly. Through their conversation and the tension between who they were and who they've become, reveal the weight of time and unspoken regret. Use the codex entries above as your world reference for characters and setting. Only include the prose of the scene without any markdown or commentary. </instructions>

Model response

AI
The plastic delivery bag crinkled as I slung it over the back of the stool, rainwater dripping from the folded umbrella tucked under my arm. I’d just dropped off a tray of har gow and siu mai to a Soho townhouse where the owner’d tipped me with a packet of salted peanuts, and my calves ached from the hour’s walk back from Golden Empress. The bar smelled like roasted hazelnuts and burnt bourbon, the same mix it had since I moved into the flat upstairs six months prior. The walls were lined with yellowed maps and black-and-white photos of Soho street corners, just like Silas had explained when he handed me the lease. I pushed the half-empty ginger ale across the oak counter, and Silas didn’t look up from polishing a set of rock glasses at first. His left knee creaked when he leaned over to grab the soda tap, a faint tell everyone who rented from him knew meant he was running low on patience for slow shifts. When he did look up, his hazel eyes flicked to the scar snaking along my left wrist, the crescent-shaped mark from the bike crash we’d shared at 12, and he nodded once, like he was acknowledging both the scar and the long day I’d just finished. His silver signet ring caught the green neon glow filtering through the front window, glinting sharp against his grey-streaked auburn beard. The bell above the door jingled loud enough to cut through the slow jazz trickling from the jukebox in the corner. I looked up, expecting a group of tourists spilling in after a West End show, or a pair of accountants from the nearby building society grabbing a quick pint before their trains home. Instead, a woman stood in the doorway, shaking rain off a tailored charcoal wool coat, her sleeve catching on the door frame so hard the fabric pulled tight across her shoulder. She didn’t look like the girl I’d shared a dorm room with for three years at Cardiff University. The curly waist-length blonde hair I’d spent hours braiding on sleepover nights was gone, replaced by a sharp blunt bob dyed a muted chestnut, cut so straight it looked like it had been measured with a ruler. Her round, freckled cheeks—once dotted with freckles that faded only in the dead of winter—were now angular, her jawline defined by a set of sleek silver hoops I’d never have picked out for her back then. She scanned the bar, and her eyes locked on mine, and for a second, her jaw tightened, like she was trying to place a face she’d not seen in six years. “Rory?” she said, and her accent was still the same soft Welsh lilt, but it was edged with something sharp, the way people talked when they spent all day in boardrooms and courtrooms. “Is that you?” I sat up straighter, my fingers brushing the crescent scar on my wrist without thinking. I’d cut my own hair three months prior, trimmed the shoulder-length black straight hair myself with a pair of kitchen scissors, after Evan had joked that long hair made me look like a lost sheep. I’d been wearing scuffed leather boots and high-waisted black jeans for the delivery shift, a far cry from the baggy Cardiff University hoodies I’d hidden in when Evan told me I looked too “attention-grabbing” in anything form-fitting. “Eva?” I said, and my voice came out quieter than I meant it to. I’d not heard her name since I packed the last of my boxes in the Cardiff flat, the one Evan had rented for us, the one where I’d stopped calling my friends because he’d said they “didn’t understand the kind of life we were building.” Eva pushed off the doorframe, her tailored wool coat swishing slightly as she walked over to the bar. Silas grabbed a glass for whiskey, poured neat bourbon, and slid it across the counter without a word, his limp more pronounced as he turned back to polishing the rest of the glasses. He didn’t need to say anything; we both knew this was a conversation he didn’t need to be part of. “I didn’t think I’d find you here,” Eva said, staring at the glass in front of her. She picked at the rim with her thumb, a nervous tic I remembered from when she’d have to present her art portfolios to university lecturers. “I asked Mia—you remember Mia, from the art studio? She moved to London last year. She said you were living above a bar named after a bird. I thought she was winding me up.” I laughed, a short, dry sound. “It’s the Raven’s Nest. Silas owns it. I’ve been renting the flat upstairs since May.” “You look… put-together,” Eva said, and her eyes flicked to my leather jacket, the one I’d bought with the first delivery shift wages, the one that fit me properly, not the oversized blazer Evan had made me wear to avoid “unwanted attention.” “Back in Cardiff, you used to hide behind your textbooks, like the world was going to eat you if you spoke up.” “I was hiding behind more than textbooks,” I said, and the words slipped out before I could stop them. The bar grew quiet, save for the grandfather clock in the corner tick-tocking off the minutes, and I watched Eva’s throat tighten, like she’d been waiting six years to hear those words. “I didn’t know,” she said, and her voice broke. She wiped at her eyes with the sleeve of her coat, a frayed cashmere cuff that looked nothing like the paint-stained hoodies she used to wear. “When you left, you just vanished. You didn’t answer my calls, you didn’t leave a note. I thought you’d finally listened to Evan, that you’d decided I was just a nuisance you didn’t need anymore.” I reached across the bar, and my hand hovered over hers for a second before I pulled back, afraid I’d cross a line she wasn’t ready to cross. “I was ashamed,” I said. “I stayed too long. I let him make me think you’d be better off without me, that I was just a mess he had to clean up. I called you twice, after I left Cardiff. But you didn’t answer.” Eva’s eyes widened, and she shook her head. “My phone got stolen the week you left. I changed the number, but you didn’t text me your new one. I spent six months looking for you, asking everyone in Cardiff if they’d seen you. I thought you hated me.” “I didn’t hate you,” I said, and this time, I reached out and took her hand. Her nails were neat, filed to a soft square, no chipped polish from painting murals on the side of the student union building, no dried paint under her fingernails from the stray cats she’d brought home to the dorm. “I just thought you’d be mad at me for staying so late. For letting him hurt me.” She squeezed my hand, and for a second, I could feel the same teenage girl I’d sat next to in art history, the one who’d snuck me into the campus bar to drink cheap cider when we were 19, the one who’d helped me cut my hair for the first time when Evan had told me I looked “too pretty” for my own good. “I would never have been mad at you,” she said. “I would have helped you. I would have left with you, if you’d asked.” We sat in silence for a minute, listening to the clock tick-tock, watching the rain streak down the fogged windows. Eva took a sip of her bourbon, and her posture relaxed, just a little, like the weight of six years of looking for me had finally lifted off her shoulders. “I took the bar exam last year,” she said, and her voice was steady now, no more cracks. “Passed on the first try. Moved to London to work for a firm that specializes in employment law—helps people leave abusive partners, Rory. That’s what I do now.” I stared at her, shocked. Back in Cardiff, she’d told me law was “just for rich pricks who wanted to push poor people around.” She’d rather paint murals on street corners than work a 9-to-5 office job. “You?” I said. “You’re a lawyer?” She laughed, a warm, familiar sound, and she nodded. “I found out what happened to you, after I moved to London. Mia told me about Evan, about how you left. I wanted to find you then, but I didn’t know where you were. I’ve been looking for you, on and off, for two years.” I pulled my hand away, and I reached into my delivery bag, pulled out the crumpled receipt from the townhouse, and folded it into my jacket pocket. My phone buzzed in another pocket, a text from the restaurant’s group chat saying they needed me for a Saturday double shift, but I ignored it. Eva pulled a business card out of her briefcase, slid it across the bar to me. The front had her name: EVANOR “EVA” MORGAN, SOLICITOR, HOLBORN LAW FIRM. The back had her mobile number, scrawled in messy handwriting that was exactly the same as the notes she’d left on my dorm room fridge back in Cardiff. “Call me,” she said. “Anytime. I don’t keep strict office hours anymore. I can meet you anywhere. Dim sum, if you want. My treat.” I picked up the card, running my thumb over the inked number. “I will,” I said. “Soon.” Eva stood up, grabbed her coat, and shook the rain off it one more time. The bell jingled as she stepped out into the Soho rain, and I watched her walk down the street, her bob bobbing slightly as she turned the corner. I sat there for a minute, staring at the business card, when Silas slid a crumpled piece of paper across the bar. It was a missing person flyer. The top read MISSING: LEAH MARLOWE, 26, LAST SEEN IN CARDIFF, OCTOBER 2021. The photo showed a girl with shoulder-length brown hair and a crescent-shaped scar snaking along her left wrist, identical to mine. Below the photo, it read CONTACT SOUTH WALES POLICE IF YOU HAVE ANY INFORMATION. The grandfather clock tick-tocked, and the neon green glow of the Raven’s Nest sign flickered outside. Silas leaned against the bar, his left knee creaking, and his hazel eyes locked on mine. “Leah Marlowe was staying with Evan when he disappeared,” he said.
created_at"2026-03-03T23:09:18.261Z" 3/3/2026, 11:09:18 PM
model"bytedance-seed/seed-2.0-mini-20260224"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1043
moderation_latency(null)
generation_time230985
tokens_prompt4618
tokens_completion9974
native_tokens_prompt4522
native_tokens_completion9344
native_tokens_completion_images(null)
native_tokens_reasoning7045
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
usage0.0041898
router(null)
provider_responses
0
endpoint_id"9265aa87-9657-4d40-b9d7-2a70318e57d9"
id"02177257935837995691c8304a8e23a54dc26928986fec3feb4cc"
is_byokfalse
latency1043
model_permaslug"bytedance-seed/seed-2.0-mini-20260224"
provider_name"Seed"
status200
api_type"completions"
id"gen-1772579358-74PhMEgbCxCIk8cgPjBL"
upstream_id"02177257935837995691c8304a8e23a54dc26928986fec3feb4cc"
total_cost0.0041898
cache_discount(null)
upstream_inference_cost0
provider_name"Seed"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags19
adverbTagCount0
adverbTags(empty)
dialogueSentences32
tagDensity0.594
leniency1
rawRatio0
effectiveRatio0
94.34% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1767
totalAiIsmAdverbs2
found
0
adverb"slightly"
count2
highlights
0"slightly"
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)
68.87% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1767
totalAiIsms11
found
0
word"flicked"
count2
1
word"glinting"
count1
2
word"measured"
count1
3
word"scanned"
count1
4
word"lilt"
count1
5
word"could feel"
count1
6
word"silence"
count1
7
word"weight"
count1
8
word"familiar"
count1
9
word"flickered"
count1
highlights
0"flicked"
1"glinting"
2"measured"
3"scanned"
4"lilt"
5"could feel"
6"silence"
7"weight"
8"familiar"
9"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 widened"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences64
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences64
filterMatches
0"look"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences77
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen65
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1763
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions28
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions36
wordCount1363
uniqueNames14
maxNameDensity0.59
worstName"Eva"
maxWindowNameDensity2
worstWindowName"Eva"
discoveredNames
Soho3
Golden1
Empress1
Silas5
West1
End1
Cardiff5
University2
Welsh1
Evan5
Eva8
Saturday1
Raven1
Nest1
persons
0"Silas"
1"Evan"
2"Eva"
3"Raven"
places
0"Soho"
1"Golden"
2"West"
3"End"
4"Cardiff"
5"University"
globalScore1
windowScore1
62.28% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences57
glossingSentenceCount2
matches
0"smelled like roasted hazelnuts and burnt b"
1"looked like it had been measured with a r"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1763
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences77
matches(empty)
91.67% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs27
mean65.3
std30.74
cv0.471
sampleLengths
0113
1123
285
3122
436
587
659
771
876
921
1064
1151
1270
1372
1448
1572
1688
1796
1843
1954
20109
2124
2217
2365
2454
2532
2611
88.82% Passive voice overuse
Target: ≤2% passive sentences
passiveCount3
totalSentences64
matches
0"were lined"
1"was gone"
2"been measured"
3"was edged"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount3
totalVerbs241
matches
0"was running"
1"was acknowledging"
2"was trying"
68.65% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount2
semicolonCount1
flaggedSentences2
totalSentences77
ratio0.026
matches
0"Her round, freckled cheeks—once dotted with freckles that faded only in the dead of winter—were now angular, her jawline defined by a set of sleek silver hoops I’d never have picked out for her back then."
1"He didn’t need to say anything; we both knew this was a conversation he didn’t need to be part of."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1380
adjectiveStacks0
stackExamples(empty)
adverbCount29
adverbRatio0.021014492753623187
lyAdverbCount7
lyAdverbRatio0.005072463768115942
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences77
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences77
mean22.9
std13.24
cv0.578
sampleLengths
025
139
224
325
424
532
646
721
821
933
1031
1118
1237
1336
1431
1533
163
1715
1835
1937
2014
2145
2218
2333
2420
2517
2625
2734
286
2915
3064
3119
3232
339
3426
3535
3628
375
3839
398
4040
4116
4239
4317
4464
4510
4614
4720
4830
4918
34.42% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats12
diversityRatio0.2987012987012987
totalSentences77
uniqueOpeners23
57.47% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences58
matches
0"Instead, a woman stood in"
ratio0.017
0.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount33
totalSentences58
matches
0"I’d just dropped off a"
1"I pushed the half-empty ginger"
2"His left knee creaked when"
3"His silver signet ring caught"
4"I looked up, expecting a"
5"She didn’t look like the"
6"Her round, freckled cheeks—once dotted"
7"She scanned the bar, and"
8"she said, and her accent"
9"I sat up straighter, my"
10"I’d cut my own hair"
11"I’d been wearing scuffed leather"
12"I said, and my voice"
13"I’d not heard her name"
14"He didn’t need to say"
15"She picked at the rim"
16"I laughed, a short, dry"
17"I said, and the words"
18"she said, and her voice"
19"She wiped at her eyes"
ratio0.569
0.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount54
totalSentences58
matches
0"The plastic delivery bag crinkled"
1"I’d just dropped off a"
2"The bar smelled like roasted"
3"The walls were lined with"
4"I pushed the half-empty ginger"
5"His left knee creaked when"
6"His silver signet ring caught"
7"The bell above the door"
8"I looked up, expecting a"
9"She didn’t look like the"
10"The curly waist-length blonde hair"
11"Her round, freckled cheeks—once dotted"
12"She scanned the bar, and"
13"she said, and her accent"
14"I sat up straighter, my"
15"I’d cut my own hair"
16"I’d been wearing scuffed leather"
17"I said, and my voice"
18"I’d not heard her name"
19"Eva pushed off the doorframe,"
ratio0.931
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences58
matches(empty)
ratio0
53.57% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences40
technicalSentenceCount5
matches
0"His left knee creaked when he leaned over to grab the soda tap, a faint tell everyone who rented from him knew meant he was running low on patience for slow shi…"
1"Instead, a woman stood in the doorway, shaking rain off a tailored charcoal wool coat, her sleeve catching on the door frame so hard the fabric pulled tight acr…"
2"I sat up straighter, my fingers brushing the crescent scar on my wrist without thinking."
3"She wiped at her eyes with the sleeve of her coat, a frayed cashmere cuff that looked nothing like the paint-stained hoodies she used to wear."
4"The back had her mobile number, scrawled in messy handwriting that was exactly the same as the notes she’d left on my dorm room fridge back in Cardiff."
46.05% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags19
uselessAdditionCount3
matches
0"she said, and her accent was still the same soft Welsh lilt, but it was edged with something sharp, the way people talked when they spent all day in boardrooms and courtrooms"
1"I said, and the words slipped out before I could stop them"
2"she said, and her voice was steady now, no more cracks"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags14
fancyCount0
fancyTags(empty)
dialogueSentences32
tagDensity0.438
leniency0.875
rawRatio0
effectiveRatio0
78.8711%