Run: 2026-02-19-01KHTR6VHT0YEC4XM3H87XK6RH

Run Details

Duration:
45.7s
Cost:
$0.066720
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 trainers squeaked against wet pavement as he darted between pedestrians. Detective Quinn kept pace twenty metres behind, her worn leather watch catching streetlight as she vaulted over a knocked-over bin. "Metropolitan Police. Move!" She shouldered past a group of tourists huddled under an awning. Their complaints faded into the ambient noise of Soho at night, replaced by the pounding of blood in her ears. The man ahead cut sharply into an alley. Smart - the narrow passage would force her to lose ground. But Quinn knew these streets. While he navigated past skips and delivery bikes, she circled around through a parallel lane. She emerged just as he reached the junction, nearly colliding with him. He staggered back, rainwater spraying from his coat. "Going somewhere?" Instead of surrendering, he sprinted toward Camden. Quinn cursed and resumed the chase. Her legs burned, but eighteen years of service had taught her to push through. The suspect was young, quick, but getting sloppy. His breathing grew ragged, his path less precise. He led her past the Raven's Nest, its green neon sign casting an eerie glow through the rain. The familiar bar triggered a memory - something about this route nagged at her. A case from three years ago. Morris had tracked a suspect along this same path before... The man ahead fumbled in his pocket and pulled something out. Even through the rain, Quinn caught the gleam of bone. "Stop! Police!" He vanished down the steps of a disused Tube station. Quinn slowed at the entrance, water dripping from her cropped hair as she drew her torch. The station had been closed for decades, yet warm air drifted up from below, carrying traces of incense and something metallic. Morris. This was where she'd lost contact with him that night. His radio had cut out mid-sentence, and he'd emerged three days later with no memory of what had happened. Within a month, he'd taken early retirement. "Control, this is DC Quinn. Suspect heading into abandoned station at..." She paused. Which station was this? She'd passed it countless times, but suddenly couldn't recall its name. Static crackled through her radio. "Please repeat location, over." Quinn stepped onto the first stair. The warm air wrapped around her ankles like fingers. "Location is..." Again, the name slipped away. "Stand by." The static grew louder, then died completely. She checked her watch - the hands had stopped moving. Below, a door creaked. Footsteps echoed off tile, growing fainter. Soon they'd fade entirely, and she'd lose him. But Morris's vacant stare in the weeks after haunted her. Whatever waited below had broken something in him, turned a twenty-year veteran into a shell. "Sod it." Quinn descended the stairs, torch beam cutting through darkness. The stairs seemed to stretch deeper than they should, each step taking her further from the familiar world above. The tiled walls gave way to rough stone. The air grew thicker, heavier with strange scents - herbs, smoke, decay. Music drifted up, a disjointed melody that made her teeth ache. She reached a landing and found herself facing an archway. Beyond it, lights flickered and voices murmured in dozens of languages. A bone token identical to the suspect's lay at her feet. Quinn picked it up. The surface felt warm, almost alive against her palm. The case file said their dealer worked the Veil Market. She'd assumed it was a pub or club. Now, standing at the threshold of something impossible, she understood why Morris never filed a proper report. "Last chance to walk away, Detective." She spun toward the voice. A man emerged from the shadows - olive skin, curly dark hair, Saint Christopher medallion catching the strange light. Tomás Herrera. The file listed him as a struck-off paramedic with suspected connections to their target. "Your suspect's long gone." He gestured to the archway. "And trust me, you don't want to follow where he's headed. Not without preparation." Quinn raised the bone token. "Seems I've got what I need right here." "That gets you in." Herrera's scar gleamed as he shifted position. "Getting out? That's trickier. Ask your old partner." "What do you know about Morris?" "I know he was lucky. I patched him up after... well. Let's just say there are rules down here. Prices for breaking them." He held out his hand. "Give me the token. Go back to your world. File it as another runner who got away." Quinn studied his face. Concern seemed genuine, but there was something else. Fear? No - anticipation. Her fingers closed around the token. "Here's another option. You tell me exactly what happened to Morris, or I arrest you right now for obstruction." Herrera smiled sadly. "Can't arrest what you can't remember, Detective. But if you're determined..." He stepped aside, gesturing toward the archway. "Welcome to the Veil Market. Try not to make eye contact. And whatever you do, don't accept any gifts." The music grew louder, more dissonant. Quinn stepped through the archway, the bone token burning against her palm. Behind her, Herrera's footsteps followed. Something told her this was no longer just about catching a dealer. This was about Morris, about three years of unanswered questions. About impossible things hiding beneath London's streets. The market sprawled before her, stalls glowing with strange lights and stranger wares. Her radio crackled once more, then fell silent forever.
created_at"2026-02-19T10:47:53.664Z" 2/19/2026, 10:47:53 AM
model"anthropic/claude-3.5-sonnet"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1362
moderation_latency155
generation_time45540
tokens_prompt4663
tokens_completion1412
native_tokens_prompt4720
native_tokens_completion1280
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"
usage0.06672
router(null)
provider_responses
0
endpoint_id"d4fb79bd-9786-4932-af81-b83040e9f4e4"
id"a1a17184-ca71-45dd-a4d9-5e3950796ef1"
is_byokfalse
latency1361
model_permaslug"anthropic/claude-3.5-sonnet"
provider_name"Amazon Bedrock"
status200
api_type"completions"
id"gen-1771498073-UKNERc2qoIMcTABye1zw"
upstream_id"a1a17184-ca71-45dd-a4d9-5e3950796ef1"
total_cost0.06672
cache_discount(null)
upstream_inference_cost0
provider_name"Amazon Bedrock"

Evaluation details

Result Evaluator Details Meta Data
0.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags8
adverbTagCount2
adverbTags
0"the name slipped away [away]"
1"He stepped aside [aside]"
dialogueSentences20
tagDensity0.4
leniency0.8
rawRatio0.25
effectiveRatio0.2
77.58% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount892
totalAiIsmAdverbs4
found
0
adverb"sharply"
count1
1
adverb"suddenly"
count1
2
adverb"completely"
count1
3
adverb"sadly"
count1
highlights
0"sharply"
1"suddenly"
2"completely"
3"sadly"
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)
38.34% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount892
totalAiIsms11
found
0
word"pounding"
count1
1
word"navigated"
count1
2
word"familiar"
count2
3
word"footsteps"
count2
4
word"echoed"
count1
5
word"flickered"
count1
6
word"almost alive"
count1
7
word"anticipation"
count1
8
word"determined"
count1
highlights
0"pounding"
1"navigated"
2"familiar"
3"footsteps"
4"echoed"
5"flickered"
6"almost alive"
7"anticipation"
8"determined"
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
narrationSentences78
matches(empty)
87.91% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount2
hedgeCount1
narrationSentences78
filterMatches
0"watch"
1"watch "
hedgeMatches
0"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences90
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen28
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords894
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions4
unquotedAttributions0
matches(empty)
74.35% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions31
wordCount727
uniqueNames14
maxNameDensity1.51
worstName"Quinn"
maxWindowNameDensity2
worstWindowName"Quinn"
discoveredNames
Quinn11
Soho1
Camden1
Raven1
Nest1
Tube1
Which1
Morris5
Veil1
Market1
Saint1
Christopher1
Herrera4
London1
persons
0"Quinn"
1"Raven"
2"Morris"
3"Market"
4"Saint"
5"Christopher"
6"Herrera"
places
0"Soho"
1"Camden"
2"London"
globalScore0.743
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences60
glossingSentenceCount1
matches
0"seemed genuine but there was something else"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount894
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences90
matches(empty)
97.98% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs33
mean27.09
std13.35
cv0.493
sampleLengths
032
134
239
320
42
543
648
721
82
947
1037
1128
129
1324
1417
1543
1630
1731
1832
1948
206
2140
2223
2313
2419
256
2645
2722
2819
2940
3023
3129
3222
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences78
matches
0"been closed"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs131
matches(empty)
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount6
semicolonCount0
flaggedSentences6
totalSentences90
ratio0.067
matches
0"Smart - the narrow passage would force her to lose ground."
1"The familiar bar triggered a memory - something about this route nagged at her."
2"She checked her watch - the hands had stopped moving."
3"The air grew thicker, heavier with strange scents - herbs, smoke, decay."
4"A man emerged from the shadows - olive skin, curly dark hair, Saint Christopher medallion catching the strange light."
5"No - anticipation."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount725
adjectiveStacks0
stackExamples(empty)
adverbCount27
adverbRatio0.037241379310344824
lyAdverbCount8
lyAdverbRatio0.011034482758620689
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences90
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences90
mean9.93
std5.3
cv0.533
sampleLengths
012
120
214
320
48
511
65
715
812
98
102
117
126
1314
148
158
1618
1714
186
1910
2011
2110
222
2310
2416
2521
261
2710
2819
297
3013
314
3211
335
344
356
369
377
382
397
4010
414
426
438
4410
4515
4611
4719
488
4912
96.67% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats3
diversityRatio0.6
totalSentences90
uniqueOpeners54
90.09% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences74
matches
0"Instead of surrendering, he sprinted"
1"Again, the name slipped away"
ratio0.027
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount19
totalSentences74
matches
0"She shouldered past a group"
1"Their complaints faded into the"
2"She emerged just as he"
3"He staggered back, rainwater spraying"
4"Her legs burned, but eighteen"
5"His breathing grew ragged, his"
6"He led her past the"
7"He vanished down the steps"
8"His radio had cut out"
9"She'd passed it countless times,"
10"She checked her watch -"
11"She reached a landing and"
12"She'd assumed it was a"
13"She spun toward the voice."
14"He gestured to the archway"
15"He held out his hand"
16"Her fingers closed around the"
17"He stepped aside, gesturing toward"
18"Her radio crackled once more,"
ratio0.257
68.11% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount58
totalSentences74
matches
0"The suspect's trainers squeaked against"
1"Detective Quinn kept pace twenty"
2"She shouldered past a group"
3"Their complaints faded into the"
4"The man ahead cut sharply"
5"She emerged just as he"
6"He staggered back, rainwater spraying"
7"Quinn cursed and resumed the"
8"Her legs burned, but eighteen"
9"The suspect was young, quick,"
10"His breathing grew ragged, his"
11"He led her past the"
12"The familiar bar triggered a"
13"A case from three years"
14"Morris had tracked a suspect"
15"The man ahead fumbled in"
16"He vanished down the steps"
17"Quinn slowed at the entrance,"
18"The station had been closed"
19"This was where she'd lost"
ratio0.784
100.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount3
totalSentences74
matches
0"While he navigated past skips"
1"Even through the rain, Quinn"
2"Now, standing at the threshold"
ratio0.041
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences34
technicalSentenceCount0
matches(empty)
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags8
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags0
87.7007%