Run: 2026-07-09-01KX40DG41FT4MM4K9F4TJCDDT

Run Details

Duration:
28.0s
Cost:
$0.043182
Provider:
OpenAI

Model input

System
You are an expert and award-winning novel writer in the dark Mystery 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="4416" name="Detective Harlow Quinn" aliases="Quinn, Detective Quinn, Harlow" pronouns="she/her" species="Human" storyRole="Antagonist"> <eyeColor>brown</eyeColor> <hair>closely cropped salt-and-pepper</hair> <height>5'9"</height> <age>41</age> <jawline>sharp jaw</jawline> <watch>worn leather watch on her left wrist</watch> <bearing>military precision</bearing> <description>A Metropolitan Police detective with 18 years of decorated service who suspects the clique is involved in criminal activity.</description> <backstory>She lost her partner, DS Morris, during a case three years ago under unexplained circumstances that had supernatural origins she doesn't yet understand.</backstory> </character> <character id="4414" name="Eva Kowalski" aliases="Eva, Evie" pronouns="she/her" species="Human" storyRole="Best Friend"> <eyeColor>green</eyeColor> <hair>curly red</hair> <height>5'4"</height> <age>26</age> <glasses>round glasses</glasses> <satchel>worn leather satchel full of books</satchel> <freckles>freckled complexion</freckles> <nervousHabit>tucking hair behind her left ear</nervousHabit> <description>Aurora's childhood friend and an occult researcher.</description> <backstory>Moved to London two years before Aurora and works as a research assistant at the British Museum's restricted archives. She holds a master's degree in Ancient History from Oxford.</backstory> </character> <location id="856" name="The Veil Market" aliases="Veil Market, the Market, underground market" realm="Earth"> <currentLocation>abandoned Tube station beneath Camden</currentLocation> <entryRequirement>bone token</entryRequirement> <schedule>moves locations every full moon</schedule> <description>A hidden supernatural black market that sells enchanted goods, banned alchemical substances, and information.</description> </location> <item id="2004" name="Veil Compass" aliases="the Compass, shadow compass" type="Tool" origin="The Veil Market"> <casingMaterial>small brass compass</casingMaterial> <faceMarkings>face etched with protective sigils</faceMarkings> <needle>points toward the nearest supernatural rift or portal</needle> <patina>casing has a patina of verdigris</patina> <creator>crafted by a Shade artisan</creator> <description>A compass attuned to supernatural energy.</description> </item> </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 mystery genre. A detective arrives at a crime scene in an unusual location. Something is wrong — the evidence doesn't add up. A colleague is present, offering a different interpretation. Through careful observation and deduction, the detective begins to see what others have missed. 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 circle.” Detective Harlow Quinn caught the young constable’s wrist before his boot crossed the yellow-and-black tape on the tiles. He stared at her hand, then at the chalk-white ring broken across the platform floor. “It’s evidence, ma’am.” “It’s a trap pretending to be evidence.” Quinn let go. Her leather watch had bitten into her wrist. The second hand moved with its usual stubborn tick, though the abandoned station had swallowed every other sound. The old Tube platform lay beneath Camden, stripped of signs and staff but not of purpose. Someone had torn the advertising boards from the walls. Their pale rectangles remained, ghost frames around damp brick. Rusted rails vanished into the black mouths of twin tunnels. The air tasted of iron filings, wet plaster, and a sweetness Quinn recognised from old crime scenes. Blood. Not much. Enough. Forensics had set portable lamps along the platform. Their hard white glare turned the circle into a crude drawing, all symbols and loops and sharp little hooks. The marks had been made with powdered bone, or something close enough that Quinn did not care to test it herself. At its centre lay a man in an expensive charcoal suit. He had fallen face-up, arms spread wide. His shoes shone. His shirt cuffs showed silver links. The left side of his throat carried a thin black line, as neat as a garrotte mark, but no wire lay near him. His eyes had clouded into a dull grey. DS Patel crouched by the body with a camera tablet in one hand and a mask hanging under his chin. He was good at his job, decent under pressure, and still young enough to trust a clean answer. “Victim’s name was Adrian Wren,” he said. “Forty-eight. Financial consultant. No record beyond parking tickets. Wallet says he lived in Hampstead. Uniform found his car in a loading bay near the canal.” “Who found him?” “Night security for the construction site above. He reported a noise from the sealed stairwell. Came down with a torch, saw this, threw up on the tracks.” “Wise man.” Patel gestured at the circle. “Looks ritualistic. We found a goat’s skull in the tunnel, candles in bottles, all the usual theatre. There’s a group online, calls itself the Ashen Gate. They favour old symbols, robes, the lot.” Quinn studied the powder at her feet. “Do they favour station closures too?” “Ma’am?” “This place hasn’t been on a public map for thirty years. How did your Ashen Gate get in?” Patel pointed towards a service door at the end of the platform. It stood ajar under a faded red sign that read STAFF ONLY. A modern padlock hung from the hasp, cut clean through. “Through there. We found bolt-cutter marks. Straightforward break-in.” “Straightforward.” Quinn looked at him. Patel had the good sense to glance away. A forensic technician, Davies, rose from the edge of the circle. Her gloves gleamed blue under the lamps. “No prints on the victim’s phone,” Davies said. “Wiped. No prints on the wallet either, except his own. We’ve got a partial boot impression near the service door, size nine or ten. Heavy sole. Could belong to anyone.” “Anything beneath the body?” Davies’s mouth tightened. “Nothing.” “No transfer? No dust compression?” “Body left an impression. No pooled blood. No fibres that aren’t from his own clothes. He died here, or someone cleaned a murder scene with more care than the Savoy polishes a spoon.” Quinn walked the platform’s edge, keeping outside the taped path. The rails below held brown water. Old rubbish floated in it, bottle caps, a crushed packet of crisps, a child’s plastic dinosaur with one chewed leg. The tunnel breathed cold air against her face. She stopped beside the nearest lamp. “His watch?” Patel checked the evidence log. “Still on him. A Patek Philippe. Stopped at 11:17.” “Battery?” “Mechanical. It shouldn’t stop.” Quinn crouched, feeling the ache in her knees. She did not touch the dead man. Instead she examined his hands. No defensive cuts. No bruising on the knuckles. His nails were clean, but fine white grit packed beneath the left thumbnail. Not the same as the circle. That powder looked coarse, with tiny dark flakes through it. “Bag that scraping,” she said. Davies nodded and reached for a swab. Patel moved closer. “You think he fought someone?” “I think someone held his hand against something.” “He has no restraint marks.” “Not on his wrists.” Quinn leaned over the body, careful of the evidence markers. Adrian Wren’s left sleeve had slipped back by an inch. A faint band, pale and raised, circled his upper arm. Patel saw it. “Tourniquet?” “Could be.” “Drug overdose?” “Then explain the throat.” “Ligature strangulation. Someone staged the rest.” “Then explain the lack of a ligature. Explain why he has no petechial haemorrhaging. Explain why his tongue isn’t swollen. Explain why his blood has decided it no longer wants to act like blood.” Patel looked at the line on Wren’s throat. Up close, it did not look like a cut. It looked like a shadow had settled under his skin. “Pathologist will tell us,” he said. “The pathologist will tell us what the body permits.” A dry scrape came from the tunnel. Every officer on the platform froze. Quinn looked towards the black arch. Nothing moved. The lamps reached only a few yards into the darkness, then failed. A single drop struck the rail. Another followed. Patel lifted his torch. “Rats?” “Rats don’t drag their feet.” The scrape stopped. Quinn crossed to the far wall. A strip of flaking paint bore a station name beneath grime and vandal marks. The letters had almost vanished, but she made out the final four. …DEN. Camden had dozens of forgotten passages, disused platforms, sealed doors that led nowhere on official plans. The city built over its secrets, then charged rent to the ghosts beneath. Her phone vibrated. The name on the screen made her jaw tighten. Eva Kowalski. Quinn stepped aside and answered. “You picked a poor moment.” “You’re at the old Camden site.” It was not a question. “Are you watching police radio now?” “Only the parts your lot leave open. Harlow, listen. Did anyone draw a circle?” Quinn looked at the powder. “You know something.” “Bone ash, salt, iron filings, anything with a dark residue?” “All of that, by the look of it.” Eva drew a breath. Paper rustled at her end of the line. “Don’t let anyone disturb it. That’s not a summoning circle.” “Your distinction comforts me.” “It’s a boundary ward. An old one. Pre-Roman in root, though the symbols have been adapted. It should keep something out.” Quinn watched the dead man’s blank face. “Something got in.” “No. That’s the problem.” Eva’s voice sharpened. “If the marks are intact, it could not have crossed from outside.” Quinn’s gaze snapped to the circle. At first it seemed whole, apart from the scuffs left by forensics around its perimeter. Then she saw the break. Not near the service door, nor by the tunnel. Beneath Wren’s right shoulder, a small gap cut through the line. It had not been smudged by a shoe. The powder ended with intent on both sides, each edge crisp. Someone had opened the circle from within. “Send me photographs,” Eva said. “Close ones. Every symbol.” “No.” “Harlow.” “You’re not coming down here.” “I have a bone token.” Quinn went still. Patel had overheard enough to raise his brows. “A what?” “Nothing.” Eva spoke again, lower this time. “The old station under Camden is not simply an old station. The Veil Market used it last full moon.” Quinn’s grip tightened around the phone. “The Veil Market is a rumour.” “It sells rumours. It also sells knives that remember your name and counterfeit saints’ bones. I’ve been cataloguing accounts for two years. That platform was one of its entrances.” “The Market moves.” “Yes. But a place remembers when a door opens in it.” The scrape came again from the tunnel. Closer. Patel swung his torch towards the dark. “Who’s on the line?” “Research assistant at the British Museum.” “Of course.” Eva ignored him. “Look for a compass,” she said. “Small brass case. Green corrosion. Sigils on the face.” Quinn surveyed the scene again. The victim’s pockets had already been logged. Wallet, phone, keys, a hotel card, loose coins, a fountain pen. No compass. “Why?” “Because Wren bought one, if he bought the thing I think he bought. A Veil Compass points to the nearest rift.” Patel made a noise that might have been a laugh. “A rift?” “Tell your colleague to stop sneering,” Eva said. “It isn’t polite when the dead man has been emptied.” Quinn’s eyes returned to Wren. “Emptied of what?” Eva did not answer at once. Then, “People call it breath. Not lungs. The part that makes you more than meat.” The lamps flickered. Davies swore. Her camera tablet flashed white, then went dead in her hand. A sound rolled through the platform, not loud but deep enough to stir dust from the tiles. It came from underfoot. The rails trembled. Brown water shivered in bright little rings. “Everyone off the platform,” Quinn said. Patel stared at her. “Ma’am, we need to preserve the scene.” “Move.” Her command cut through the station. Officers seized equipment. Davies grabbed her kits, then hesitated over the victim. “Leave him,” Quinn said. “No chance.” “Davies.” The technician’s face had drained of colour behind her mask. She reached for Wren’s shoulder. His hand closed around her wrist. Davies screamed. Wren’s eyes opened. They were no longer grey. They were black, slick and depthless, and something behind them pressed its face against the skin of the world.
created_at"2026-07-09T17:57:09.9Z" 7/9/2026, 5:57:09 PM
model"openai/gpt-5.6-terra-20260709"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency623
moderation_latency(null)
generation_time27892
tokens_prompt4671
tokens_completion2779
native_tokens_prompt4157
native_tokens_completion2186
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"
usage0.0431825
router(null)
provider_responses
0
endpoint_id"3cc89000-ae34-4dde-9c7d-5ce009c8af0b"
id"resp_0f5ce0ff913d179a016a4fe0f5f7588195b84c875a1ec2639b"
is_byokfalse
latency279
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-1783619829-VDoQbqF7xjpM43N6ZnJx"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1783619829-yLRQ9x0CIzH2Z46kQsVf"
upstream_id"resp_0f5ce0ff913d179a016a4fe0f5f7588195b84c875a1ec2639b"
total_cost0.0431825
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
totalTags11
adverbTagCount0
adverbTags(empty)
dialogueSentences83
tagDensity0.133
leniency0.265
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1616
totalAiIsmAdverbs0
found(empty)
highlights(empty)
80.00% AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions(empty)
found
0"Patel"
100.00% AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions(empty)
found(empty)
84.53% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1616
totalAiIsms5
found
0
word"mechanical"
count1
1
word"charged"
count1
2
word"vibrated"
count1
3
word"flickered"
count1
4
word"trembled"
count1
highlights
0"mechanical"
1"charged"
2"vibrated"
3"flickered"
4"trembled"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches0
maxInWindow0
found(empty)
highlights(empty)
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences133
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences133
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences204
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen34
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1616
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions18
unquotedAttributions0
matches(empty)
33.33% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions60
wordCount990
uniqueNames9
maxNameDensity2.12
worstName"Quinn"
maxWindowNameDensity4
worstWindowName"Quinn"
discoveredNames
Harlow1
Quinn21
Tube1
Camden2
Patel13
Davies7
Wren6
Kowalski1
Eva8
persons
0"Harlow"
1"Quinn"
2"Camden"
3"Patel"
4"Davies"
5"Wren"
6"Kowalski"
7"Eva"
places(empty)
globalScore0.439
windowScore0.333
87.50% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences80
glossingSentenceCount2
matches
0"looked like a shadow had settled under hi"
1"seemed whole apart from the scuffs left by forensics around its perimeter"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches1
per1kWords0.619
wordCount1616
matches
0"not loud but deep enough to stir dust from the tiles"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences204
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs145
mean11.14
std11.81
cv1.059
sampleLengths
04
118
215
33
47
529
661
74
848
911
1047
1138
1232
133
1427
152
165
1733
187
196
201
2118
2234
238
245
258
2618
2738
284
293
301
315
3233
3344
346
352
365
379
381
394
4020
4137
425
437
443
455
468
475
484
4930
97.35% Passive voice overuse
Target: ≤2% passive sentences
passiveCount3
totalSentences133
matches
0"been made"
1"been smudged"
2"been logged"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs168
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences204
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount994
adjectiveStacks0
stackExamples(empty)
adverbCount33
adverbRatio0.03319919517102616
lyAdverbCount2
lyAdverbRatio0.002012072434607646
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences204
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences204
mean7.92
std6.39
cv0.807
sampleLengths
04
118
215
33
47
53
68
718
816
99
109
1110
1217
131
142
151
168
1719
1821
1911
207
213
226
2323
248
2520
2618
277
2825
293
3027
312
325
3333
347
356
361
3718
3812
3912
4010
418
425
438
4411
457
468
4730
484
493
70.10% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats7
diversityRatio0.4411764705882353
totalSentences204
uniqueOpeners90
59.52% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences112
matches
0"Instead she examined his hands."
1"Then she saw the break."
ratio0.018
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount25
totalSentences112
matches
0"He stared at her hand,"
1"Her leather watch had bitten"
2"Their pale rectangles remained, ghost"
3"Their hard white glare turned"
4"He had fallen face-up, arms"
5"His shoes shone."
6"His shirt cuffs showed silver"
7"His eyes had clouded into"
8"He was good at his"
9"It stood ajar under a"
10"Her gloves gleamed blue under"
11"She stopped beside the nearest"
12"She did not touch the"
13"His nails were clean, but"
14"It looked like a shadow"
15"Her phone vibrated."
16"It was not a question."
17"It had not been smudged"
18"Her camera tablet flashed white,"
19"It came from underfoot."
ratio0.223
13.57% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount100
totalSentences112
matches
0"Detective Harlow Quinn caught the"
1"He stared at her hand,"
2"Quinn let go."
3"Her leather watch had bitten"
4"The second hand moved with"
5"The old Tube platform lay"
6"Someone had torn the advertising"
7"Their pale rectangles remained, ghost"
8"The air tasted of iron"
9"Forensics had set portable lamps"
10"Their hard white glare turned"
11"The marks had been made"
12"He had fallen face-up, arms"
13"His shoes shone."
14"His shirt cuffs showed silver"
15"The left side of his"
16"His eyes had clouded into"
17"DS Patel crouched by the"
18"He was good at his"
19"Patel gestured at the circle."
ratio0.893
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences112
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences38
technicalSentenceCount0
matches(empty)
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags11
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags9
fancyCount0
fancyTags(empty)
dialogueSentences83
tagDensity0.108
leniency0.217
rawRatio0
effectiveRatio0
87.5302%