Run: 2026-07-09-01KX41BKMBZEN2G60SNJK47WH3

Run Details

Duration:
26.9s
Cost:
$0.033941
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
Detective Harlow Quinn caught the constable’s wrist before he could step over the chalk line. “Lift your foot.” The young man froze, boot hovering above the platform tiles. “Look down.” He did. His face tightened. A grey smear ran across the toe of his boot, no wider than a thumbprint. It glimmered in the weak emergency lights. “Sorry, ma’am. I thought it was dust.” “Dust doesn’t crawl uphill.” The smear crept along the leather grain, a thread of ash moving against gravity. Quinn took a sample tube from her coat, scraped it free with a penknife, and sealed it. Her worn leather watch pressed against the cuff of her sleeve as she wrote the time on the label. Behind her, the disused station breathed through cracked tunnels. Camden had buried this place beneath newer lines and locked doors. Yet someone had opened the old entrance, cleared the rubble from the stairwell, and hung bare bulbs along the tiled passage. Their cables drooped like black veins. The old advertisements had peeled away in long strips, exposing mouldy plaster and rusted frames. A faded roundel still clung to one wall. MORNINGTON CRESCENT, it read. No trains had stopped here for decades. No one had mentioned a body. DS Anwar Bell stood by the yellow evidence tent at the platform’s far end. He held a paper cup in one hand and a clear property bag in the other. His tie had loosened. His sleeves carried the grey grit that coated every surface. “Thought you were on leave,” Bell said. “Thought you knew how to secure a scene.” “I did secure it.” Quinn glanced at the crouching constable. Bell grimaced. “Mostly.” He held out the bag. Inside lay a small brass compass, greened at the hinge and worn smooth at the edges. Protective markings covered its face, cramped sigils cut around a needle that had spun itself into a blur. “We found that in the victim’s hand. Or what’s left of it.” Quinn did not touch it. “Who called it in?” “Anonymous. Phone box on Chalk Farm Road. Voice muffled. They gave the location, said there’d been a murder, then ended the call.” “And the body?” Bell tilted his head towards the evidence tent. “Depends how strict you feel about the word.” Quinn walked down the platform. Her shoes clicked against white tiles, then sank into a thin carpet of black dust. The sound died before it reached the tunnel mouth. The platform should have carried an echo. Stations did. They trapped every cough, every dropped coin, every curse from the far end of the line. This one swallowed sound whole. Bell followed her, his shoes making no noise at all. “Control ran the fingerprints,” he said. “Nothing in the system. Male, late thirties or early forties, if the teeth tell the truth. No wallet. No phone. No clothes.” “No clothes?” “Not a stitch. No burns on the skin either.” Quinn stopped beside the tent. The victim lay on his back on a plastic sheet. He had no wounds that she could see. His chest remained unmarked. His limbs lay straight, his hands placed by his sides with care. Someone had washed the grime from his face. His skin had the waxy pale tone of a drowned man, though no water pooled anywhere near him. Fine black cracks webbed across his throat and cheeks. The fissures looked less like injuries than dried riverbeds. His mouth gaped open. Grey ash packed it to the gums. Bell sipped his coffee. “Overdose, my first thought. Some new synthetic thing. Dealers cut rubbish with all sorts.” “Your dealer brought him to an abandoned Underground station, stripped him, washed him, arranged him, and filled his mouth with ash.” “You’d be surprised what people do after a bad night.” “I am rarely surprised by people.” “That sounds healthy.” Quinn crouched by the dead man’s head. The metallic stink of old blood sat beneath the dust, sharp enough to sting. She slipped on nitrile gloves and leaned closer. The ash did not sit loose in the mouth. It formed a solid plug, dense and grey-white. The same material filled each nostril. It had entered under pressure. Not sprinkled in later. Forced in. She reached for the torch clipped to her belt and swept its beam across the man’s face. The black cracks on his skin deepened around the eyes. Fine grains lay trapped in the lashes. “He inhaled it,” she said. Bell lowered his cup. “He inhaled ash?” “Enough to fill his lungs.” “That would kill him.” “Yes.” “So we agree.” “No. He inhaled it after his heart stopped.” Bell frowned. “How do you know?” “His lips are dry. His gums aren’t torn. No defensive damage around the mouth, no bruising on the jaw. If someone held him down and pumped this into him, we’d see something. We don’t.” “You said it was under pressure.” “It was.” Bell looked over the body, then towards the black tunnel. “Ventilation shaft?” “Blocked years ago. Your scene officers checked.” “Could have been a collapse.” “Then why is the ash inside him and not over him?” Bell’s mouth opened, then closed. Quinn moved to the victim’s left hand. The fingers curled around empty air. A pale circle marked the palm where the brass compass had rested. The mark had not come from pressure. It had burned itself into the skin, a perfect ring of tiny symbols. She had seen the same kind of mark once, three years ago, on DS Morris’s notebook. Quinn straightened before the memory could settle its teeth. “Where was the compass found, exactly?” Bell pointed. “Right there. His hand had it clenched like a child with sweets. Forensics prised it out.” “Who bagged it?” “DC Marsh.” “Get him.” Bell gave the nearest uniform a nod. The officer moved off at once. Quinn scanned the platform. A rusted bench stood beneath an enamel sign. The wall behind it bore dark streaks, thick at the floor and thin near the ceiling. At first glance, they looked like soot from an old fire. At second glance, they formed handprints. Dozens of them. Some faced upwards. Some dragged across the tiles. One sat at shoulder height, fingers spread wide, as if someone had pressed against the wall from the other side. Quinn walked over. Bell trailed behind her. “Don’t touch those,” she said. “I wasn’t going to.” “You were lifting your hand.” “I gesture when I think.” “Think with your hands in your pockets.” He shoved both hands into his trouser pockets. The prints did not match one person. Some looked small, child-sized. Others stretched long, with too many joints in the fingers. The ash did not coat the tile surface. It lay beneath the glaze. Quinn ran her torch along the wall. The light caught the smooth ceramic, then vanished where it passed over the handprints. “They’re under the tiles,” she said. Bell looked at the wall. “That’s not possible.” “No.” “You keep saying that like it helps.” “It helps me narrow the field.” A policeman approached with DC Marsh. Marsh was broad-shouldered and pink-faced, his hair flattened by a cheap wool cap. He carried a second property bag. “Detective,” he said. “You wanted me?” “Tell me about the compass.” Marsh held the bag up. “Found it in the victim’s left hand. Brass, old-looking. Might be some antique dealer’s trinket.” “Was it open?” “Closed.” “Was the needle moving?” He blinked. “Can’t say I noticed.” “You bagged it. You noticed enough.” “It rattled about a bit.” “Show me.” Marsh’s eyes flicked to Bell. Bell sighed. “Show her.” Marsh unsealed the bag with clumsy fingers. The compass lay within it, lid shut. Quinn watched him lift it by the edge. “Open it.” He flipped the lid. The needle whipped round, struck north, then swung hard towards the tunnel beside the platform. It trembled there, pinned against the glass. Nobody spoke. Marsh swallowed. “That’s a powerful magnet.” “There are no magnets in the tunnel,” Quinn said. “Old electrical works?” “Dead line. Dead power. Dead rails.” Bell reached out. “Give it here.” Quinn caught his hand. “Gloves.” He stared at her. “I am wearing gloves.” “Not the same ones you wore beside the body.” Bell looked down. Grey dust mottled the fingertips. For the first time since she had arrived, the humour dropped from his face. Quinn took a fresh pair from the kit at her belt and handed them over. Bell put them on. Marsh passed him the compass. The needle spun once, twice, then pointed past Bell’s shoulder. At Quinn. She kept still. The needle shook. It dragged itself a fraction to the right, towards the tiled wall with its buried handprints. Bell held the compass away from them, then closer. The needle followed the movement, always seeking the same patch of tiles. “What is that thing?” he asked. “Evidence,” Quinn said. “That isn’t an answer.” “No. It’s a category.” A crack snapped through the station. The sound came from behind the wall. Every officer on the platform turned. The enamel tiles bulged outwards beneath the spread handprint. A line opened between them, thin as a paper cut. Black dust leaked through it and fell in a soft stream onto the platform. Marsh stepped back. “What the hell is that?” Quinn took the compass from Bell. Its brass casing felt cold enough to ache through her gloves. The needle vibrated so fast it hummed. She looked at the body. At the grey plug in the dead man’s mouth. At the scorched circle on his palm. “He didn’t come here to die,” she said. Bell’s eyes stayed on the widening crack. “Then why was he here?” “He came to close something.” The wall convulsed. Tiles burst across the platform. One struck Marsh’s cheek and opened it to the bone. He dropped with both hands clamped over his face. Officers shouted. A torch clattered away, its beam spinning across the ceiling. From the hole behind the tiles, a hand pushed through. It had six fingers. Its nails were packed with the same grey ash.
created_at"2026-07-09T18:13:36.532Z" 7/9/2026, 6:13:36 PM
model"openai/gpt-5.6-terra-20260709"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency559
moderation_latency(null)
generation_time26793
tokens_prompt4671
tokens_completion2830
native_tokens_prompt4157
native_tokens_completion2193
native_tokens_completion_images0
native_tokens_reasoning0
native_tokens_cached4154
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"
usage0.033941
router(null)
provider_responses
0
endpoint_id"3cc89000-ae34-4dde-9c7d-5ce009c8af0b"
id"resp_0446565bfacd70b2016a4fe4d09cf08190aede79ba0862447d"
is_byokfalse
latency259
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-1783620816-OnTZSfR2Q5uHnwh9BBoL"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1783620816-rlIfYnNFg66LagC2o0LI"
upstream_id"resp_0446565bfacd70b2016a4fe4d09cf08190aede79ba0862447d"
total_cost0.033941
cache_discount0.0093465
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
totalTags10
adverbTagCount0
adverbTags(empty)
dialogueSentences81
tagDensity0.123
leniency0.247
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1676
totalAiIsmAdverbs0
found(empty)
highlights(empty)
100.00% AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions(empty)
found(empty)
100.00% AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions(empty)
found(empty)
79.12% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1676
totalAiIsms7
found
0
word"echo"
count1
1
word"synthetic"
count1
2
word"perfect"
count1
3
word"scanned"
count1
4
word"flicked"
count1
5
word"trembled"
count1
6
word"vibrated"
count1
highlights
0"echo"
1"synthetic"
2"perfect"
3"scanned"
4"flicked"
5"trembled"
6"vibrated"
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
narrationSentences159
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences159
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences230
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen35
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1676
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
totalMentions54
wordCount1206
uniqueNames6
maxNameDensity1.91
worstName"Bell"
maxWindowNameDensity4
worstWindowName"Bell"
discoveredNames
Harlow1
Quinn19
Anwar1
Bell23
Morris1
Marsh9
persons
0"Harlow"
1"Quinn"
2"Anwar"
3"Bell"
4"Morris"
5"Marsh"
places(empty)
globalScore0.546
windowScore0.333
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences96
glossingSentenceCount1
matches
0"looked like soot from an old fire"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1676
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences230
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs163
mean10.28
std11.53
cv1.122
sampleLengths
015
13
210
32
45
522
67
74
850
99
1061
114
127
136
1444
157
168
174
186
192
201
2139
2212
235
244
2522
263
278
288
295
3049
315
3210
3328
342
359
365
3742
3836
394
407
414
4214
4321
4410
456
463
4729
4828
494
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences159
matches
0"were packed"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs213
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences230
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1210
adjectiveStacks0
stackExamples(empty)
adverbCount29
adverbRatio0.023966942148760332
lyAdverbCount0
lyAdverbRatio0
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences230
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences230
mean7.29
std4.9
cv0.673
sampleLengths
015
13
210
32
42
53
615
77
87
94
1014
1117
1219
139
1411
1521
166
1715
188
194
207
216
2214
2316
244
2510
267
278
284
296
302
311
325
3316
3418
3512
365
374
3822
393
408
418
425
4315
449
457
462
4716
485
4910
59.57% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats8
diversityRatio0.3782608695652174
totalSentences230
uniqueOpeners87
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences137
matches(empty)
ratio0
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount34
totalSentences137
matches
0"His face tightened."
1"It glimmered in the weak"
2"Her worn leather watch pressed"
3"Their cables drooped like black"
4"He held a paper cup"
5"His tie had loosened."
6"His sleeves carried the grey"
7"He held out the bag."
8"Her shoes clicked against white"
9"They trapped every cough, every"
10"He had no wounds that"
11"His chest remained unmarked."
12"His limbs lay straight, his"
13"His skin had the waxy"
14"His mouth gaped open."
15"She slipped on nitrile gloves"
16"It formed a solid plug,"
17"It had entered under pressure."
18"She reached for the torch"
19"It had burned itself into"
ratio0.248
32.99% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount117
totalSentences137
matches
0"Detective Harlow Quinn caught the"
1"The young man froze, boot"
2"His face tightened."
3"A grey smear ran across"
4"It glimmered in the weak"
5"The smear crept along the"
6"Quinn took a sample tube"
7"Her worn leather watch pressed"
8"Camden had buried this place"
9"Their cables drooped like black"
10"The old advertisements had peeled"
11"A faded roundel still clung"
12"MORNINGTON CRESCENT, it read."
13"DS Anwar Bell stood by"
14"He held a paper cup"
15"His tie had loosened."
16"His sleeves carried the grey"
17"Quinn glanced at the crouching"
18"He held out the bag."
19"Quinn did not touch it."
ratio0.854
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences137
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences45
technicalSentenceCount0
matches(empty)
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags10
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags10
fancyCount0
fancyTags(empty)
dialogueSentences81
tagDensity0.123
leniency0.247
rawRatio0
effectiveRatio0
86.8336%