Run: 2026-02-19-01KHTZ0RKTVPYHJSSMJ3X2BD26

Run Details

Duration:
37.1s
Cost:
$0.041520
Provider:
Amazon Bedrock

Model input

System
You are an expert and award-winning novel writer in the dark Thriller 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="4417" name="Tomás Herrera" aliases="Tommy, Tomás, Herrera" pronouns="he/him" species="Human" storyRole="Support"> <eyeColor>warm brown</eyeColor> <hair>short curly dark brown</hair> <height>5'10"</height> <age>29</age> <skinTone>olive skin</skinTone> <scar>scar running along his left forearm from a knife attack</scar> <medallion>Saint Christopher medallion around his neck</medallion> <birthplace>Seville, Spain</birthplace> <description>A former paramedic who provides off-the-books medical care for the clique.</description> <backstory>Born in Seville, Spain. He moved to London to work for the NHS but lost his license after administering unauthorized treatments to supernatural patients.</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> <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> </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 thriller genre. A detective is pursuing a suspect through rain-soaked city streets at night. The chase takes them from the street level down into an underground market. The detective must decide whether to follow the suspect into unfamiliar and potentially dangerous territory. 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 suspect's leather jacket disappeared around the corner of Berwick Street before Harlow could close the gap. Rain hammered the pavement between them, turning the cobblestones into treacherous mirrors reflecting sodium streetlights. She'd been tailing him for three blocks now, ever since he'd bolted from The Raven's Nest. Tomás bloody Herrera, the paramedic who shouldn't exist according to NHS records. The one who kept showing up in witness statements, always just out of frame. "Stop! Police!" He didn't stop. They never did. Harlow's boots slapped through puddles as she rounded the corner. Soho's narrow streets gave her an advantage, civilian foot traffic thinning out this late on a Tuesday. Her worn leather watch caught on her jacket sleeve as she pumped her arms. Quarter past eleven. The Tube would be shutting down soon. Herrera cut left towards Shaftesbury Avenue. Wrong direction for going to ground. He was heading somewhere specific. A taxi horn blared. Harlow vaulted over its bonnet, her palm leaving a print on the wet metal. The driver's curse followed her into the maze of backstreets behind the theatres. Her lungs burned. Eighteen years of service and she still couldn't outrun a man ten years younger. But she could think faster. Harlow hooked right at the next junction, gambling on him following the old delivery routes. The shortcut brought her parallel to his position, one street over. She caught a glimpse of him through a gap between buildings. Still running. Still heading north. Camden. Her radio crackled. She ignored it. Whatever was happening back at the station could wait. She'd been chasing leads on this lot for six months, ever since that business with the missing artefact from the British Museum. Every thread led back to that dim little bar in Soho and its collection of people who shouldn't know each other. People like Herrera, who'd lost his medical licence but still somehow treated patients off the books. The rain intensified, sheeting down in waves that turned the world into watercolour. Harlow's salt-and-pepper hair plastered itself to her skull. She'd left her umbrella in the car. Priorities. Herrera's silhouette emerged on Camden High Street. He didn't look back, just kept that steady pace. Not quite sprinting. Conserving energy. He'd done this before. Harlow hung back, letting two groups of drunk students pass between them. No need to spook him if he thought he'd lost her. The street was busier here despite the rain, London's nocturnal ecosystem in full flow. Kebab shops leaked steam and the smell of charred meat. A busker packed up his guitar, protecting it under his coat like a child. Herrera turned into an alley. Dead end. She'd checked these streets a dozen times during the investigation. That particular alley terminated at a brick wall behind a shuttered chemist. Harlow slowed. Her hand went to the ASP baton on her belt. The military precision of the gesture would've made her old sergeant proud. Check your six. Assess the terrain. Never corner what you can't control. The alley swallowed sound. Rain drummed on industrial bins and fire escapes but created a strange muffled quality, like walking into cotton wool. Water sluiced down the walls, carrying the day's grime into the gutters. Herrera stood at the far end. Waiting. "Bit late for a walk, Detective." His voice carried that warm Seville lilt she'd noted from witness descriptions. The Saint Christopher medallion at his throat caught what little light penetrated the alley. His olive skin looked grey in the darkness. "Tomás Herrera. We need to talk about your activities." "Do we?" He wasn't breathing hard. Hadn't even broken a sweat despite the run. Wrong. Something was wrong. "You left The Raven's Nest in a hurry. Guilty conscience?" "Or perhaps I simply don't enjoy being followed." He touched something on the wall beside him. A brick, unremarkable except for the way his fingers found it without looking. "You should go back, Detective Quinn. This isn't your jurisdiction." "Last I checked, all of London was my jurisdiction." "London, yes." His fingers pressed. The brick depressed with a soft click. "But not everywhere in London." The wall opened. Not a door. The wall itself, a section of brickwork swinging inward on hidden hinges. Beyond it, stairs descended into darkness. Not the clean darkness of a basement, but something older. Stone steps worn smooth by centuries of feet. Air wafted up carrying scents that had no business existing together: incense and copper, aged paper and something sharp she couldn't identify. Voices drifted up. Multiple conversations in languages she didn't recognise. "What the hell is this?" "A choice." Herrera started down the stairs. "Follow me and see what you're not supposed to see. Or go back to your life where things make sense." The wall began to close. Harlow's radio crackled again. Dispatch asking for her location. Standard check-in. The normal world wanting her back. She thought of Morris. Her partner, three years gone. The official report said cardiac arrest during a pursuit. But Morris had been thirty-two and ran marathons. And there'd been marks on his body, burns in patterns that the coroner couldn't explain. Burns the Home Office had classified the photos of, then made the file disappear. Burns she'd seen similar patterns of in crime scene photos from six other cases over the past year. Cases that got quietly closed. Cases involving people connected to The Raven's Nest. The gap in the wall narrowed to two feet. Eighteen inches. Harlow lunged through. The brick sealed behind her with a sound like a tomb closing. The stairwell was lit by intermittent electric bulbs strung along the ceiling, their light flickering and uncertain. The stone walls wept moisture. Someone had carved symbols into them at irregular intervals. Not graffiti. Too precise. Too old. Herrera waited three turns down, his expression unreadable. "Welcome to the Veil Market, Detective." He held up something between his thumb and forefinger. Small. White. It took her a moment to recognise it as a carved bone token. "Hope you brought an entry fee." "I don't—" "Need one?" A smile without warmth. "No. You're with me. They'll assume you're livestock or a client." "Excuse me?" But he was already descending, and the sounds from below were growing louder. Music with too many rhythms layered together. Laughter that didn't sound quite human. The clink of glass and metal and things scraping against things. Harlow's hand found her baton again. Morris had probably made a choice like this. Probably stood at a threshold and decided to step through despite every instinct screaming at him to call for backup. She followed Herrera down into the dark. The stairs opened into an impossible space. The abandoned Tube station shouldn't exist here, not according to any map she'd studied. But the curved walls and vintage tile work were unmistakable. Someone had strung fairy lights along the tracks, illuminating stalls and vendor carts that sprawled across what should have been the platform. Dozens of people moved through the market. Hundreds, maybe. Browsing. Bartering. She caught snatches of conversation in English, Spanish, what might have been Arabic or Hebrew. A woman in an immaculate suit examined bottles filled with luminescent liquid. Two men argued over a leather-bound book, its pages moving of their own accord. A vendor called out, offering "Fresh wards, top quality, none of that Camden Town rubbish." This wasn't happening. Couldn't be happening. Herrera turned back, his expression almost pitying. "Still think this is your jurisdiction, Detective?"
created_at"2026-02-19T12:46:54.085Z" 2/19/2026, 12:46:54 PM
model"anthropic/claude-4.5-sonnet-20250929"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1808
moderation_latency162
generation_time36808
tokens_prompt4663
tokens_completion2012
native_tokens_prompt4720
native_tokens_completion1824
native_tokens_completion_images(null)
native_tokens_reasoning0
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"
usage0.04152
router(null)
provider_responses
0
endpoint_id"d8bee848-f020-454a-b2be-4a7ce868f99f"
id"c6d9807f-8d06-4c47-ab4f-fda939c3888d"
is_byokfalse
latency1808
model_permaslug"anthropic/claude-4.5-sonnet-20250929"
provider_name"Amazon Bedrock"
status200
api_type"completions"
id"gen-1771505214-baaMYtwLsw12ZEc1arwc"
upstream_id"c6d9807f-8d06-4c47-ab4f-fda939c3888d"
total_cost0.04152
cache_discount(null)
upstream_inference_cost0
provider_name"Amazon Bedrock"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags5
adverbTagCount0
adverbTags(empty)
dialogueSentences21
tagDensity0.238
leniency0.476
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1249
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)
75.98% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1249
totalAiIsms6
found
0
word"treacherous"
count1
1
word"lilt"
count1
2
word"standard"
count1
3
word"electric"
count1
4
word"unreadable"
count1
5
word"warmth"
count1
highlights
0"treacherous"
1"lilt"
2"standard"
3"electric"
4"unreadable"
5"warmth"
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
narrationSentences136
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount1
narrationSentences136
filterMatches
0"watch"
hedgeMatches
0"began to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences151
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen22
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1244
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions5
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions53
wordCount1108
uniqueNames27
maxNameDensity0.9
worstName"Harlow"
maxWindowNameDensity2
worstWindowName"Harlow"
discoveredNames
Berwick1
Street2
Harlow10
Raven2
Nest2
Herrera10
Tuesday1
Tube2
Shaftesbury1
Avenue1
British1
Museum1
Soho2
Camden2
High1
London1
Seville1
Saint1
Christopher1
Morris3
Home1
Office1
Small1
English1
Spanish1
Arabic1
Hebrew1
persons
0"Harlow"
1"Herrera"
2"Tube"
3"Saint"
4"Christopher"
5"Morris"
6"Office"
places
0"Berwick"
1"Street"
2"Raven"
3"Shaftesbury"
4"Avenue"
5"British"
6"Soho"
7"Camden"
8"High"
9"London"
10"Seville"
11"English"
globalScore1
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences83
glossingSentenceCount1
matches
0"something between his thumb and forefinger"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches1
per1kWords0.804
wordCount1244
matches
0"Not the clean darkness of a basement, but something older"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences151
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs55
mean22.62
std18.44
cv0.815
sampleLengths
032
142
22
36
451
517
648
75
842
91
1058
1116
1229
1325
1461
155
1624
1736
1835
197
206
2134
229
232
2416
2510
2639
279
2817
293
3061
3110
325
3327
345
3517
3655
3731
3811
393
4049
418
4236
432
4417
452
4637
4734
487
4953
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences136
matches
0"was lit"
21.75% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount5
totalVerbs187
matches
0"was heading"
1"was happening"
2"wasn't breathing"
3"were growing"
4"wasn't happening"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences151
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1113
adjectiveStacks0
stackExamples(empty)
adverbCount31
adverbRatio0.027852650494159928
lyAdverbCount3
lyAdverbRatio0.0026954177897574125
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences151
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences151
mean8.24
std5.32
cv0.646
sampleLengths
017
115
216
312
414
52
63
73
810
917
1014
113
127
136
146
155
164
1714
1813
193
2014
215
2215
2311
2411
252
263
271
283
293
309
3122
3221
3316
3413
358
367
371
387
399
403
412
424
4312
4411
4514
4610
4714
485
492
78.15% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats7
diversityRatio0.4966887417218543
totalSentences151
uniqueOpeners75
56.50% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences118
matches
0"Still heading north."
1"Probably stood at a threshold"
ratio0.017
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount26
totalSentences118
matches
0"She'd been tailing him for"
1"He didn't stop."
2"They never did."
3"Her worn leather watch caught"
4"He was heading somewhere specific."
5"Her lungs burned."
6"She caught a glimpse of"
7"Her radio crackled."
8"She ignored it."
9"She'd been chasing leads on"
10"She'd left her umbrella in"
11"He didn't look back, just"
12"He'd done this before."
13"She'd checked these streets a"
14"Her hand went to the"
15"His voice carried that warm"
16"His olive skin looked grey"
17"He wasn't breathing hard."
18"He touched something on the"
19"His fingers pressed"
ratio0.22
57.46% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount95
totalSentences118
matches
0"The suspect's leather jacket disappeared"
1"She'd been tailing him for"
2"Tomás bloody Herrera, the paramedic"
3"The one who kept showing"
4"He didn't stop."
5"They never did."
6"Harlow's boots slapped through puddles"
7"Soho's narrow streets gave her"
8"Her worn leather watch caught"
9"Quarter past eleven."
10"The Tube would be shutting"
11"Herrera cut left towards Shaftesbury"
12"He was heading somewhere specific."
13"A taxi horn blared."
14"Harlow vaulted over its bonnet,"
15"The driver's curse followed her"
16"Her lungs burned."
17"Harlow hooked right at the"
18"The shortcut brought her parallel"
19"She caught a glimpse of"
ratio0.805
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences118
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences51
technicalSentenceCount1
matches
0"Air wafted up carrying scents that had no business existing together: incense and copper, aged paper and something sharp she couldn't identify."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags5
uselessAdditionCount0
matches(empty)
54.76% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags2
fancyCount2
fancyTags
0"His fingers pressed (press)"
1"A vendor called out (call out)"
dialogueSentences21
tagDensity0.095
leniency0.19
rawRatio1
effectiveRatio0.19
88.1530%