Run: 2026-02-19-01KHV72HN0CR7FAD4XJSVAG6KG

Run Details

Duration:
36.0s
Cost:
$0.038799
Provider:
Amazon Bedrock

Model input

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

Model response

AI
The glass slipped from Rory's fingers and shattered on the bar floor. She didn't notice. Her eyes had fixed on a face she hadn't seen in three years, framed in the doorway of The Raven's Nest like a photograph she'd thought she'd lost. Niamh Walsh. Same copper hair. Same way of scanning a room as though she owned it. But something sat differently in her shoulders now, a weight that hadn't been there before, and the coat she wore, long, dark, expensively cut, belonged to someone Rory didn't recognise. "You going to stand there or help me clean this up?" Silas said from behind the bar, already reaching for a cloth. Rory crouched and gathered the larger shards by hand, her knuckles white. By the time she straightened, Niamh had spotted her. There was a pause, a flicker of something that crossed Niamh's face and disappeared before it could be named. Then she walked over, and Rory felt the three years collapse into the space between them. "Rory Carter." Her voice was smoother than Rory remembered. The Dublin edges had been filed down. "You look like a bloody banker." Niamh laughed, and for a moment the coat didn't matter. "Sit with me." They took the corner table, the one beneath the old map of Prague that Rory had always assumed was decorative. Silas brought two glasses of Jameson without being asked and withdrew without a word. He had a talent for that. "How did you even find this place?" Rory said. "I didn't. I was just walking." Niamh turned her glass on the table. "I work near here now." "Near Soho." "Canary Wharf, but I had a meeting." A pause. "At a law firm on Wardour Street." Rory said nothing. She drank. "You're not going to ask?" "I know what a law firm on Wardour Street means, Niamh." The old name sat between them like something unearthed. Niamh had gone by Neve at university. Reinvention even then, though it had been gentler, more playful. A nickname shed rather than a self. "Fintech compliance," Niamh said. "Before you get any ideas. I'm not defending anyone interesting." "I didn't say anything." "You've got your Cardiff face on." "I left Cardiff." "So did I." Niamh looked at her properly then, and something honest moved behind her eyes. "You look well. Thin, but well." "I deliver takeaway." "I know. Eva told me." Rory set her glass down. "When did you speak to Eva?" "Christmas. We still talk." A beat. "She worries about you." "She talks too much." "She loves you." Niamh's hand moved as though to reach across the table, then retreated. "We both do." The pub hummed around them, low music and the clink of ice. A man at the bar laughed too loudly at something, and the sound bounced off the walls and died. "You could've called," Rory said. "So could you." Fair. Rory picked up her glass again. "How's Ciarán?" she asked, because it was the last thing she remembered to ask about, the last data point she had on Niamh Walsh's life before the signal went quiet. The change in Niamh's face was small but surgical. "Gone," she said. "Last spring." "Gone like..." "Gone like he packed a bag on a Tuesday and I came home to a note on the kitchen counter." She said it flatly, the way you say things you've said enough times that the meaning has been sanded off. "Six years." Rory exhaled. "Niamh." "Don't." "I'm not doing anything." "You're doing the face." "What face?" "The one where you're about to be kind to me and I'm going to cry in a bar I've never been to before." She smoothed the front of her coat with one hand, a precise gesture, practiced. "I'm fine. It was a year ago." Rory studied her. The coat. The smoothed hair. The way she held her glass by the stem like it was a prop at a business dinner. "You look like you're auditioning for someone else's life," Rory said. Niamh went very still. "I mean that gently," Rory added. "Do you?" "I do." Outside, a bus ground past on the wet street. The neon sign above the door threw its green light across the floorboards in a long, trembling stripe. "I'm doing well," Niamh said. "Genuinely. I got a promotion in March. I moved to a flat in Bermondsey. I joined a book club." She listed it like evidence. "I'm doing well." "I believe you." "You don't." Rory turned her glass. "I believe that you're working very hard at it." The silence that followed was the kind that either breaks something or clears it. Niamh looked down. Her thumb found a small scratch on the table's surface and traced it, back and forth. "Do you ever miss it?" she said. "Cardiff. Who we were." "No," Rory said. Then, more honestly, "Sometimes the people. Not the place." "I miss who I thought I was going to be." Niamh's voice had lost its polish. Just for a moment. "That's a stupid thing to say out loud." "It's a true thing." "True things can still be stupid." She looked up. "Do you ever regret leaving?" Rory thought about Evan's voice through a closed door. About the drive to London with two bags and Eva talking the whole way to fill the silence. "Every day," she said. "And never." Niamh held her gaze. Something shifted in her expression, not quite relief but close to it, the particular comfort of being known by someone who has no obligation to flatter you. "I have an early meeting," she said, but she didn't move. "You said." "I should go." She still didn't move. Rory watched her and waited, and the green light from the sign pulsed once as a taxi rolled past outside. "There's another round in this," Rory said. "If you want it." Niamh looked at her coat, then at the table, then at Rory's face. She reached up and pulled off her coat in one motion, folded it over the back of her chair, and raised two fingers toward Silas at the bar. The coat sat there between them, no longer armour, just fabric. And Rory felt the three years begin, at last, to breathe. Then Niamh's phone lit up on the table. A name on the screen. Ciarán.
created_at"2026-02-19T15:07:41.418Z" 2/19/2026, 3:07:41 PM
model"anthropic/claude-4.6-sonnet-20260217"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1091
moderation_latency121
generation_time35383
tokens_prompt4618
tokens_completion1582
native_tokens_prompt4718
native_tokens_completion1643
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"
usage0.038799
router(null)
provider_responses
0
endpoint_id"83d802cb-44f2-45a0-a9d5-cb9bf79777c8"
id"1ebda0f6-311d-47ab-a2ef-ba2fc73ab104"
is_byokfalse
latency1091
model_permaslug"anthropic/claude-4.6-sonnet-20260217"
provider_name"Amazon Bedrock"
status200
api_type"completions"
id"gen-1771513661-uYMS2xRvk7FRh9RYfFrW"
upstream_id"1ebda0f6-311d-47ab-a2ef-ba2fc73ab104"
total_cost0.038799
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
totalTags23
adverbTagCount0
adverbTags(empty)
dialogueSentences68
tagDensity0.338
leniency0.676
rawRatio0
effectiveRatio0
85.78% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1055
totalAiIsmAdverbs3
found
0
adverb"very"
count2
1
adverb"gently"
count1
highlights
0"very"
1"gently"
100.00% AI-ism character names
Target: 0 AI-default names (16 tracked, −20% each)
codexExemptions
0"Blackwood"
found(empty)
100.00% AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions(empty)
found(empty)
57.35% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1055
totalAiIsms9
found
0
word"shattered"
count1
1
word"scanning"
count1
2
word"weight"
count1
3
word"flicker"
count1
4
word"the last thing"
count1
5
word"silence"
count2
6
word"traced"
count1
7
word"pulsed"
count1
highlights
0"shattered"
1"scanning"
2"weight"
3"flicker"
4"the last thing"
5"silence"
6"traced"
7"pulsed"
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
narrationSentences80
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences80
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences122
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen40
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1055
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions22
unquotedAttributions0
matches(empty)
0.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions55
wordCount712
uniqueNames14
maxNameDensity3.09
worstName"Rory"
maxWindowNameDensity4
worstWindowName"Rory"
discoveredNames
Rory22
Raven1
Nest1
Walsh2
Niamh18
Dublin1
Prague1
Jameson1
Neve1
Fair1
Evan1
London1
Eva1
Silas3
persons
0"Rory"
1"Raven"
2"Nest"
3"Walsh"
4"Niamh"
5"Jameson"
6"Evan"
7"Eva"
8"Silas"
places
0"Dublin"
1"Prague"
2"London"
globalScore0
windowScore0.333
94.44% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences45
glossingSentenceCount1
matches
0"not quite relief but close to it, the particular comfort of being known by someone who has no obligation to flatter you"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches1
per1kWords0.948
wordCount1055
matches
0"not quite relief but close to it, the particular comfort of being known by someon"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences122
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs72
mean14.65
std12.41
cv0.847
sampleLengths
012
131
246
322
421
535
616
76
813
940
109
1118
122
1316
145
155
1611
1733
1814
194
206
213
2222
233
245
2511
2610
274
2818
2931
305
313
327
3330
349
355
362
3742
383
391
404
414
422
4344
4426
4511
464
476
482
492
87.72% Passive voice overuse
Target: ≤2% passive sentences
passiveCount4
totalSentences80
matches
0"been filed"
1"being asked"
2"been sanded"
3"being known"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs129
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences122
ratio0
matches(empty)
98.13% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount712
adjectiveStacks0
stackExamples(empty)
adverbCount30
adverbRatio0.042134831460674156
lyAdverbCount6
lyAdverbRatio0.008426966292134831
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences122
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences122
mean8.65
std7.7
cv0.89
sampleLengths
012
13
228
32
43
511
630
722
812
99
1019
1116
129
137
146
1510
163
1720
1814
196
209
2113
225
232
249
257
263
272
285
2911
309
317
3210
337
344
3510
364
376
383
3916
406
413
425
435
446
456
464
474
4815
493
59.56% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats9
diversityRatio0.4016393442622951
totalSentences122
uniqueOpeners49
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount4
totalSentences61
matches
0"Then she walked over, and"
1"Then, more honestly,"
2"Just for a moment."
3"Then Niamh's phone lit up"
ratio0.066
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount14
totalSentences61
matches
0"She didn't notice."
1"Her eyes had fixed on"
2"Her voice was smoother than"
3"They took the corner table,"
4"He had a talent for"
5"she asked, because it was"
6"She said it flatly, the"
7"She smoothed the front of"
8"She listed it like evidence"
9"Her thumb found a small"
10"She looked up"
11"she said, but she didn't"
12"She still didn't move."
13"She reached up and pulled"
ratio0.23
58.36% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount49
totalSentences61
matches
0"The glass slipped from Rory's"
1"She didn't notice."
2"Her eyes had fixed on"
3"Silas said from behind the"
4"Rory crouched and gathered the"
5"Her voice was smoother than"
6"The Dublin edges had been"
7"Niamh laughed, and for a"
8"They took the corner table,"
9"Silas brought two glasses of"
10"He had a talent for"
11"Niamh turned her glass on"
12"Rory said nothing."
13"The old name sat between"
14"Niamh had gone by Neve"
15"Reinvention even then, though it"
16"A nickname shed rather than"
17"Niamh looked at her properly"
18"Rory set her glass down."
19"Niamh's hand moved as though"
ratio0.803
81.97% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences61
matches
0"By the time she straightened,"
ratio0.016
83.33% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences24
technicalSentenceCount2
matches
0"But something sat differently in her shoulders now, a weight that hadn't been there before, and the coat she wore, long, dark, expensively cut, belonged to some…"
1"Something shifted in her expression, not quite relief but close to it, the particular comfort of being known by someone who has no obligation to flatter you."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags23
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags15
fancyCount1
fancyTags
0"Rory added (add)"
dialogueSentences68
tagDensity0.221
leniency0.441
rawRatio0.067
effectiveRatio0.029
90.2216%