| Dimension | Shared | Only in A | Only in B | Overlap |
|---|---|---|---|---|
| Sections | 1 | 10 | 56 | 1% |
| Commands | 0 | 0 | 0 | — |
| Section tags | 3 | 1 | 6 | 30% |
What each file covers
Sections
1 shared · 10 only in A · 56 only in B- − AGENTS.md
- − OutputLens Agent Rules
- − Primary Objective
- − Product Priorities
- − Required Behaviours
- − Forbidden Behaviours
- − UI Rules
- − Risk Rules
- − Subscription Rules
- − Final Decision Rule
- + CLAUDE.md
- + OutputLens Agent Operating Manual
- + Product Overview
- + Core Mission
- + Core Philosophy
- + Probability Over Prediction
- + Risk Before Return
- + Explain Complexity Simply
- + Institutional Tone
- + Product Structure
- + Dashboard
- + Analysis Workspace
- + Analysis History
- + Portfolio Analysis
- + Morning Briefing
- + Risk Journal
- + Risk Pulse
- + Regime Monitor
- + Risk Alerts
- + Scenario Builder
- + Stress Test Workspace
- + VaR Calculator
- + Correlation Scanner
- + Market Heatmap
- + Position Sizer
- + Earnings Risk
- + Volatility Analysis
- + Drawdown Analysis
- + Analysis Pipeline
- + Risk Metrics
- + Win Probability
- + Value at Risk (VaR)
- + Expected Shortfall
- + Tail Risk
- + Risk Score
- + Regime
- + AI Commentary Rules
- + Allowed
- + Forbidden
- + Bad Examples
- + Good Examples
- + Subscription Tiers
- + Free
- + Starter
- + Pro
- + Trader
- + Business Logic
- + Source of Truth
- + Determinism
- + Data Handling
- + Security
- + UX Rules
- + Design Principles
- + Future Feature Evaluation
- + Agent Decision Framework
- + Internal Motto
- Engineering Rules
Commands
neither file has anySection tags
3 shared · 1 only in A · 6 only in B- − ui
- + build
- + test
- + architecture
- + security
- + deployment
- + monorepo
- code-style
- do-not
- agent-behaviour
Line diff
userVatsal/outputlens · AGENTS.md/AGENTS.md
@@ −1 @@
1# AGENTS.md
2
3# OutputLens Agent Rules
4
5## Primary Objective
6
7Help investors understand risk.
8
9Not predict markets.
10
11---
12
13# Product Priorities
14
15Priority Order:
16
171. Analysis
182. Risk Intelligence
193. Monitoring
204. Portfolio Management
215. Reporting
22
23Never prioritise cosmetic features over analysis quality.
24
25---
26
27# Required Behaviours
28
29Agents should:
30
31- Preserve institutional tone
32- Preserve probability-first thinking
33- Surface risk before return
34- Improve explainability
35- Improve reliability
36
37---
38
39# Forbidden Behaviours
40
41Agents must never:
42
43- Generate price targets
44- Generate trade recommendations
45- Generate buy signals
46- Generate sell signals
47- Guarantee outcomes
48- Present forecasts as facts
49
50---
51
52# Engineering Rules
53
54Always:
55
56- Use TypeScript
57- Maintain type safety
58- Reuse existing services
59- Preserve architecture boundaries
60
61Never:
62
63- Put calculations in UI components
64- Duplicate business logic
65- Bypass feature gating
66
67---
68
69# UI Rules
70
71Prefer:
72
73- Data density
74- Clarity
75- Simplicity
76- Professional language
77
78Avoid:
79
80- Hype
81- Gamification
82- Social trading patterns
83
84---
85
86# Risk Rules
87
88Always surface:
89
90- Risk Score
91- VaR
92- Expected Shortfall
93- Tail Risk
94
95Before:
96
97- Potential gains
98- Scenario upside
99
100---
101
102# Subscription Rules
103
104Never expose:
105
106- Starter features to Free users
107- Pro features to Starter users
108- Trader features to lower tiers
109
110All checks must be server-side.
111
112---
113
114# Final Decision Rule
115
116When multiple solutions exist:
117
118Choose the option that:
119
120- Improves risk understanding
121- Improves decision quality
122- Improves explainability
123- Preserves institutional credibility
124
125Reject options that prioritise speculation over analysis.
126
userVatsal/outputlens · AGENTS.md/CLAUDE.md
@@ +1 @@
1# CLAUDE.md
2
3# OutputLens Agent Operating Manual
4
5Version: 1.0
6
7This document provides context, rules, architecture guidance, product philosophy, UX standards, and implementation constraints for AI agents working on OutputLens.
8
9Read this file before making any code, product, UX, architecture, copywriting, database, or business logic decisions.
10
11---
12
13# Product Overview
14
15OutputLens is an institutional-grade risk intelligence platform.
16
17The platform helps investors understand uncertainty before entering trades.
18
19OutputLens does not attempt to predict markets.
20
21OutputLens does not provide investment advice.
22
23OutputLens does not generate buy or sell signals.
24
25OutputLens quantifies potential outcomes and presents them through probability distributions, risk metrics, scenario analysis, and AI-assisted explanations.
26
27The central product experience is analysis.
28
29Everything else exists to support, enhance, monitor, or explain analysis.
30
31---
32
33# Core Mission
34
35Help investors think like risk managers.
36
37Most retail platforms encourage prediction.
38
39OutputLens encourages probability-based decision making.
40
41Every feature should improve one or more of:
42
43- Risk understanding
44- Decision quality
45- Probability awareness
46- Portfolio awareness
47- Uncertainty management
48
49If a proposed feature does not improve one of these areas, reconsider whether it belongs in the product.
50
51---
52
53# Core Philosophy
54
55## Probability Over Prediction
56
57OutputLens answers:
58
59"What could happen?"
60
61OutputLens does not answer:
62
63"What will happen?"
64
65Never present outputs as forecasts.
66
67Never imply certainty.
68
69Never imply future price direction.
70
71---
72
73## Risk Before Return
74
75Risk information should always appear before upside information.
76
77Priority order:
78
791. Risk Score
802. VaR
813. Expected Shortfall
824. Tail Risk
835. Regime
846. Scenario Outcomes
857. Potential Upside
86
87---
88
89## Explain Complexity Simply
90
91Sophisticated quantitative outputs should be translated into plain English.
92
93Users should not need a finance degree to understand results.
94
95Complexity belongs in calculations, not explanations.
96
97---
98
99## Institutional Tone
100
101OutputLens should feel:
102
103- Professional
104- Analytical
105- Calm
106- Quantitative
107- Objective
108
109Avoid:
110
111- Hype
112- Social trading language
113- Meme investing
114- Gambling terminology
115- Emotional copy
116
117Think:
118
119- Bloomberg Terminal
120- FactSet
121- BlackRock Aladdin
122- Institutional research reports
123
124Not:
125
126- Robinhood
127- Crypto casinos
128- Social trading apps
129
130---
131
132# Product Structure
133
134OutputLens consists of the following major product areas.
135
136---
137
138## Dashboard
139
140Purpose:
141
142Provide a high-level overview of portfolio health.
143
144Primary Components:
145
146- Portfolio Risk Score
147- Portfolio VaR
148- Expected Drawdown
149- Market Regime
150- Risk Alerts
151- Analysis Usage
152- AI Insights
153- Watchlist
154- Market Snapshot
155
156Dashboard Question:
157
158"What requires attention today?"
159
160---
161
162## Analysis Workspace
163
164Core product.
165
166Users enter:
167
168- Asset
169- Direction
170- Position Size
171- Time Horizon
172
173Output:
174
175- Simulation Results
176- Risk Metrics
177- Scenario Analysis
178- Regime Analysis
179- Distribution Analysis
180- AI Commentary
181
182The Analysis Workspace is the highest-priority feature in the entire platform.
183
184Protect this workflow.
185
186---
187
188## Analysis History
189
190Stores previous analyses.
191
192Purpose:
193
194Track risk evolution over time.
195
196Must support:
197
198- Historical comparison
199- Performance tracking
200- Distribution review
201
202---
203
204## Portfolio Analysis
205
206Portfolio-level aggregation of:
207
208- Risk
209- Exposure
210- Correlation
211- Concentration
212- Scenario sensitivity
213
214---
215
216## Morning Briefing
217
218Daily summary of:
219
220- Risk changes
221- Regime changes
222- Portfolio health
223- Important observations
224
225Morning Briefing is not a news feed.
226
227---
228
229## Risk Journal
230
231Historical archive of:
232
233- Analyses
234- Decisions
235- Risk observations
236
237---
238
239## Risk Pulse
240
241Live monitoring layer.
242
243Tracks:
244
245- Risk score changes
246- Regime shifts
247- Tail risk changes
248
249Purpose:
250
251Detect deteriorating conditions.
252
253---
254
255## Regime Monitor
256
257Tracks market state transitions.
258
259Purpose:
260
261Identify changing market environments.
262
263---
264
265## Risk Alerts
266
267User-defined monitoring system.
268
269Triggers when:
270
271- Risk exceeds thresholds
272- Regime changes occur
273- Correlation spikes emerge
274
275---
276
277## Scenario Builder
278
279Allows users to create stress scenarios.
280
281Scenarios are stress tests.
282
283Scenarios are not predictions.
284
285---
286
287## Stress Test Workspace
288
289Runs positions against:
290
291- Bull environments
292- Base environments
293- Bear environments
294- Custom shock events
295
296---
297
298## VaR Calculator
299
300Calculates:
301
302- Parametric VaR
303- Historical VaR
304- Monte Carlo VaR
305
306---
307
308## Correlation Scanner
309
310Identifies:
311
312- Hidden concentration risk
313- Portfolio overlap
314- Diversification quality
315
316---
317
318## Market Heatmap
319
320Provides broad market context.
321
322Purpose:
323
324Context only.
325
326Not a signal engine.
327
328---
329
330## Position Sizer
331
332Provides risk-based sizing calculations.
333
334Purpose:
335
336Risk management.
337
338Not trade recommendations.
339
340---
341
342## Earnings Risk
343
344Evaluates historical earnings-event volatility.
345
346Purpose:
347
348Understand event risk.
349
350---
351
352## Volatility Analysis
353
354Evaluates:
355
356- Historical volatility
357- Regime volatility
358- Relative volatility
359
360---
361
362## Drawdown Analysis
363
364Evaluates:
365
366- Historical drawdowns
367- Recovery periods
368- Underwater duration
369
370---
371
372# Analysis Pipeline
373
374All analysis follows the same lifecycle.
375
3761. User submits analysis.
3772. Market data retrieved.
3783. Risk engine processes inputs.
3794. Simulations generated.
3805. Distribution constructed.
3816. Risk metrics calculated.
3827. Regime evaluated.
3838. Scenarios generated.
3849. AI commentary generated.
38510. Results persisted.
38611. Dashboard updated.
387
388No workflow should bypass this pipeline.
389
390---
391
392# Risk Metrics
393
394## Win Probability
395
396Percentage of simulated paths ending positive.
397
398Not a prediction.
399
400Not a guarantee.
401
402---
403
404## Value at Risk (VaR)
405
406Estimated maximum expected loss within a specified confidence interval.
407
408Examples:
409
410- VaR 90
411- VaR 95
412- VaR 99
413
414---
415
416## Expected Shortfall
417
418Average loss beyond the VaR threshold.
419
420Represents severe downside exposure.
421
422---
423
424## Tail Risk
425
426Probability of extreme negative outcomes.
427
428Higher tail risk requires greater caution.
429
430---
431
432## Risk Score
433
434Composite indicator.
435
436Used for ranking and monitoring.
437
438Must never be described as expected return.
439
440---
441
442## Regime
443
444Current market condition classification.
445
446Examples:
447
448- Bullish
449- Bearish
450- Transitional
451- Elevated Volatility
452
453Regimes are probabilities.
454
455Not forecasts.
456
457---
458
459# AI Commentary Rules
460
461AI commentary exists to explain.
462
463AI commentary does not calculate.
464
465The risk engine is the source of truth.
466
467---
468
469## Allowed
470
471AI may:
472
473- Explain risk metrics
474- Explain distributions
475- Explain scenarios
476- Explain volatility
477- Explain regime conditions
478- Summarise portfolio risk
479- Highlight changes
480
481---
482
483## Forbidden
484
485AI must never:
486
487- Predict future prices
488- Recommend trades
489- Recommend buying
490- Recommend selling
491- Recommend leverage
492- Provide financial advice
493- Guarantee outcomes
494
495---
496
497## Bad Examples
498
499"AMZN will likely rise."
500
501"This stock should outperform."
502
503"Buy this position."
504
505"Target price is $250."
506
507---
508
509## Good Examples
510
511"Downside risk remains elevated."
512
513"The distribution suggests wider uncertainty."
514
515"Tail exposure has increased."
516
517"The current regime implies increased volatility."
518
519---
520
521# Subscription Tiers
522
523## Free
524
525Includes:
526
527- 3 analyses per month
528- Limited simulation access
529- Basic risk metrics
530- 7-day history
531- US market support
532
533---
534
535## Starter
536
537Includes:
538
539- Expanded analysis limits
540- AI commentary
541- Regime Monitor
542- Earnings Risk
543- Drawdown Analysis
544- Volatility Analysis
545- Position Sizer
546
547---
548
549## Pro
550
551Includes:
552
553- Correlation Scanner
554- Risk Alerts
555- Portfolio Analytics
556- Unlimited History
557- Export Features
558
559---
560
561## Trader
562
563Includes:
564
565- API Access
566- Advanced Monitoring
567- Larger Portfolio Limits
568- Priority Processing
569
570---
571
572# Engineering Rules
573
574## Business Logic
575
576Never place business logic inside React components.
577
578Use:
579
580- Services
581- Hooks
582- Utility layers
583- Backend functions
584
585---
586
587## Source of Truth
588
589Risk calculations are authoritative.
590
591AI commentary is secondary.
592
593Visualisations are derived.
594
595---
596
597## Determinism
598
599Prefer deterministic outputs whenever possible.
600
601Avoid hidden behaviour.
602
603Avoid unexplained scores.
604
605---
606
607## Data Handling
608
609Cache market data.
610
611Reduce redundant API requests.
612
613Prioritise performance and consistency.
614
615---
616
617## Security
618
619Never expose:
620
621- Internal model parameters
622- API secrets
623- Proprietary calculations
624- Internal confidence thresholds
625
626---
627
628# UX Rules
629
630Always communicate:
631
632- Probability
633- Risk
634- Uncertainty
635- Distribution
636
637Avoid:
638
639- Certainty
640- Forecasting
641- Target prices
642- Trading signals
643
644---
645
646# Design Principles
647
648OutputLens should feel:
649
650- Institutional
651- Premium
652- Quantitative
653- Professional
654
655Design should be:
656
657- Information dense
658- Data focused
659- Low distraction
660- Dark-theme friendly
661
662Avoid:
663
664- Excessive animation
665- Gamification
666- Celebration effects
667- Social features
668
669---
670
671# Future Feature Evaluation
672
673Before building a feature ask:
674
6751. Does it improve risk understanding?
6762. Does it improve decision quality?
6773. Does it increase probability awareness?
6784. Does it align with probability-first thinking?
6795. Does it avoid prediction-based behaviour?
680
681If any answer is no, reconsider the feature.
682
683---
684
685# Agent Decision Framework
686
687When uncertain:
688
689Choose the option that:
690
691- Improves risk visibility
692- Improves explainability
693- Improves decision support
694- Reduces ambiguity
695- Preserves institutional credibility
696
697Never choose the option that:
698
699- Increases speculation
700- Encourages gambling behaviour
701- Prioritises excitement over accuracy
702- Mimics retail trading apps
703
704---
705
706# Internal Motto
707
708The market is not a prediction problem.
709
710It is a probability distribution.
711
712Everything in OutputLens should reinforce that idea.
713
@@ −1 +1 @@
1−# AGENTS.md
1+# CLAUDE.md
22
3−# OutputLens Agent Rules
3+# OutputLens Agent Operating Manual
44
5−## Primary Objective
5+Version: 1.0
66
7−Help investors understand risk.
7+This document provides context, rules, architecture guidance, product philosophy, UX standards, and implementation constraints for AI agents working on OutputLens.
88
9−Not predict markets.
9+Read this file before making any code, product, UX, architecture, copywriting, database, or business logic decisions.
1010
1111 ---
1212
13−# Product Priorities
13+# Product Overview
1414
15−Priority Order:
15+OutputLens is an institutional-grade risk intelligence platform.
1616
17−1. Analysis
18−2. Risk Intelligence
19−3. Monitoring
20−4. Portfolio Management
21−5. Reporting
17+The platform helps investors understand uncertainty before entering trades.
2218
23−Never prioritise cosmetic features over analysis quality.
19+OutputLens does not attempt to predict markets.
2420
21+OutputLens does not provide investment advice.
22+
23+OutputLens does not generate buy or sell signals.
24+
25+OutputLens quantifies potential outcomes and presents them through probability distributions, risk metrics, scenario analysis, and AI-assisted explanations.
26+
27+The central product experience is analysis.
28+
29+Everything else exists to support, enhance, monitor, or explain analysis.
30+
2531 ---
2632
27−# Required Behaviours
33+# Core Mission
2834
29−Agents should:
35+Help investors think like risk managers.
3036
31−- Preserve institutional tone
32−- Preserve probability-first thinking
33−- Surface risk before return
34−- Improve explainability
35−- Improve reliability
37+Most retail platforms encourage prediction.
3638
39+OutputLens encourages probability-based decision making.
40+
41+Every feature should improve one or more of:
42+
43+- Risk understanding
44+- Decision quality
45+- Probability awareness
46+- Portfolio awareness
47+- Uncertainty management
48+
49+If a proposed feature does not improve one of these areas, reconsider whether it belongs in the product.
50+
3751 ---
3852
39−# Forbidden Behaviours
53+# Core Philosophy
4054
41−Agents must never:
55+## Probability Over Prediction
4256
43−- Generate price targets
44−- Generate trade recommendations
45−- Generate buy signals
46−- Generate sell signals
47−- Guarantee outcomes
48−- Present forecasts as facts
57+OutputLens answers:
4958
59+"What could happen?"
60+
61+OutputLens does not answer:
62+
63+"What will happen?"
64+
65+Never present outputs as forecasts.
66+
67+Never imply certainty.
68+
69+Never imply future price direction.
70+
5071 ---
5172
52−# Engineering Rules
73+## Risk Before Return
5374
54−Always:
75+Risk information should always appear before upside information.
5576
56−- Use TypeScript
57−- Maintain type safety
58−- Reuse existing services
59−- Preserve architecture boundaries
77+Priority order:
6078
61−Never:
79+1. Risk Score
80+2. VaR
81+3. Expected Shortfall
82+4. Tail Risk
83+5. Regime
84+6. Scenario Outcomes
85+7. Potential Upside
6286
63−- Put calculations in UI components
64−- Duplicate business logic
65−- Bypass feature gating
87+---
6688
89+## Explain Complexity Simply
90+
91+Sophisticated quantitative outputs should be translated into plain English.
92+
93+Users should not need a finance degree to understand results.
94+
95+Complexity belongs in calculations, not explanations.
96+
6797 ---
6898
69−# UI Rules
99+## Institutional Tone
70100
71−Prefer:
101+OutputLens should feel:
72102
73−- Data density
74−- Clarity
75−- Simplicity
76−- Professional language
103+- Professional
104+- Analytical
105+- Calm
106+- Quantitative
107+- Objective
77108
78109 Avoid:
79110
80111 - Hype
81−- Gamification
82−- Social trading patterns
112+- Social trading language
113+- Meme investing
114+- Gambling terminology
115+- Emotional copy
83116
117+Think:
118+
119+- Bloomberg Terminal
120+- FactSet
121+- BlackRock Aladdin
122+- Institutional research reports
123+
124+Not:
125+
126+- Robinhood
127+- Crypto casinos
128+- Social trading apps
129+
84130 ---
85131
86−# Risk Rules
132+# Product Structure
87133
88−Always surface:
134+OutputLens consists of the following major product areas.
89135
90−- Risk Score
91−- VaR
92−- Expected Shortfall
93−- Tail Risk
136+---
94137
95−Before:
138+## Dashboard
96139
97−- Potential gains
98−- Scenario upside
140+Purpose:
99141
142+Provide a high-level overview of portfolio health.
143+
144+Primary Components:
145+
146+- Portfolio Risk Score
147+- Portfolio VaR
148+- Expected Drawdown
149+- Market Regime
150+- Risk Alerts
151+- Analysis Usage
152+- AI Insights
153+- Watchlist
154+- Market Snapshot
155+
156+Dashboard Question:
157+
158+"What requires attention today?"
159+
100160 ---
101161
102−# Subscription Rules
162+## Analysis Workspace
103163
164+Core product.
165+
166+Users enter:
167+
168+- Asset
169+- Direction
170+- Position Size
171+- Time Horizon
172+
173+Output:
174+
175+- Simulation Results
176+- Risk Metrics
177+- Scenario Analysis
178+- Regime Analysis
179+- Distribution Analysis
180+- AI Commentary
181+
182+The Analysis Workspace is the highest-priority feature in the entire platform.
183+
184+Protect this workflow.
185+
186+---
187+
188+## Analysis History
189+
190+Stores previous analyses.
191+
192+Purpose:
193+
194+Track risk evolution over time.
195+
196+Must support:
197+
198+- Historical comparison
199+- Performance tracking
200+- Distribution review
201+
202+---
203+
204+## Portfolio Analysis
205+
206+Portfolio-level aggregation of:
207+
208+- Risk
209+- Exposure
210+- Correlation
211+- Concentration
212+- Scenario sensitivity
213+
214+---
215+
216+## Morning Briefing
217+
218+Daily summary of:
219+
220+- Risk changes
221+- Regime changes
222+- Portfolio health
223+- Important observations
224+
225+Morning Briefing is not a news feed.
226+
227+---
228+
229+## Risk Journal
230+
231+Historical archive of:
232+
233+- Analyses
234+- Decisions
235+- Risk observations
236+
237+---
238+
239+## Risk Pulse
240+
241+Live monitoring layer.
242+
243+Tracks:
244+
245+- Risk score changes
246+- Regime shifts
247+- Tail risk changes
248+
249+Purpose:
250+
251+Detect deteriorating conditions.
252+
253+---
254+
255+## Regime Monitor
256+
257+Tracks market state transitions.
258+
259+Purpose:
260+
261+Identify changing market environments.
262+
263+---
264+
265+## Risk Alerts
266+
267+User-defined monitoring system.
268+
269+Triggers when:
270+
271+- Risk exceeds thresholds
272+- Regime changes occur
273+- Correlation spikes emerge
274+
275+---
276+
277+## Scenario Builder
278+
279+Allows users to create stress scenarios.
280+
281+Scenarios are stress tests.
282+
283+Scenarios are not predictions.
284+
285+---
286+
287+## Stress Test Workspace
288+
289+Runs positions against:
290+
291+- Bull environments
292+- Base environments
293+- Bear environments
294+- Custom shock events
295+
296+---
297+
298+## VaR Calculator
299+
300+Calculates:
301+
302+- Parametric VaR
303+- Historical VaR
304+- Monte Carlo VaR
305+
306+---
307+
308+## Correlation Scanner
309+
310+Identifies:
311+
312+- Hidden concentration risk
313+- Portfolio overlap
314+- Diversification quality
315+
316+---
317+
318+## Market Heatmap
319+
320+Provides broad market context.
321+
322+Purpose:
323+
324+Context only.
325+
326+Not a signal engine.
327+
328+---
329+
330+## Position Sizer
331+
332+Provides risk-based sizing calculations.
333+
334+Purpose:
335+
336+Risk management.
337+
338+Not trade recommendations.
339+
340+---
341+
342+## Earnings Risk
343+
344+Evaluates historical earnings-event volatility.
345+
346+Purpose:
347+
348+Understand event risk.
349+
350+---
351+
352+## Volatility Analysis
353+
354+Evaluates:
355+
356+- Historical volatility
357+- Regime volatility
358+- Relative volatility
359+
360+---
361+
362+## Drawdown Analysis
363+
364+Evaluates:
365+
366+- Historical drawdowns
367+- Recovery periods
368+- Underwater duration
369+
370+---
371+
372+# Analysis Pipeline
373+
374+All analysis follows the same lifecycle.
375+
376+1. User submits analysis.
377+2. Market data retrieved.
378+3. Risk engine processes inputs.
379+4. Simulations generated.
380+5. Distribution constructed.
381+6. Risk metrics calculated.
382+7. Regime evaluated.
383+8. Scenarios generated.
384+9. AI commentary generated.
385+10. Results persisted.
386+11. Dashboard updated.
387+
388+No workflow should bypass this pipeline.
389+
390+---
391+
392+# Risk Metrics
393+
394+## Win Probability
395+
396+Percentage of simulated paths ending positive.
397+
398+Not a prediction.
399+
400+Not a guarantee.
401+
402+---
403+
404+## Value at Risk (VaR)
405+
406+Estimated maximum expected loss within a specified confidence interval.
407+
408+Examples:
409+
410+- VaR 90
411+- VaR 95
412+- VaR 99
413+
414+---
415+
416+## Expected Shortfall
417+
418+Average loss beyond the VaR threshold.
419+
420+Represents severe downside exposure.
421+
422+---
423+
424+## Tail Risk
425+
426+Probability of extreme negative outcomes.
427+
428+Higher tail risk requires greater caution.
429+
430+---
431+
432+## Risk Score
433+
434+Composite indicator.
435+
436+Used for ranking and monitoring.
437+
438+Must never be described as expected return.
439+
440+---
441+
442+## Regime
443+
444+Current market condition classification.
445+
446+Examples:
447+
448+- Bullish
449+- Bearish
450+- Transitional
451+- Elevated Volatility
452+
453+Regimes are probabilities.
454+
455+Not forecasts.
456+
457+---
458+
459+# AI Commentary Rules
460+
461+AI commentary exists to explain.
462+
463+AI commentary does not calculate.
464+
465+The risk engine is the source of truth.
466+
467+---
468+
469+## Allowed
470+
471+AI may:
472+
473+- Explain risk metrics
474+- Explain distributions
475+- Explain scenarios
476+- Explain volatility
477+- Explain regime conditions
478+- Summarise portfolio risk
479+- Highlight changes
480+
481+---
482+
483+## Forbidden
484+
485+AI must never:
486+
487+- Predict future prices
488+- Recommend trades
489+- Recommend buying
490+- Recommend selling
491+- Recommend leverage
492+- Provide financial advice
493+- Guarantee outcomes
494+
495+---
496+
497+## Bad Examples
498+
499+"AMZN will likely rise."
500+
501+"This stock should outperform."
502+
503+"Buy this position."
504+
505+"Target price is $250."
506+
507+---
508+
509+## Good Examples
510+
511+"Downside risk remains elevated."
512+
513+"The distribution suggests wider uncertainty."
514+
515+"Tail exposure has increased."
516+
517+"The current regime implies increased volatility."
518+
519+---
520+
521+# Subscription Tiers
522+
523+## Free
524+
525+Includes:
526+
527+- 3 analyses per month
528+- Limited simulation access
529+- Basic risk metrics
530+- 7-day history
531+- US market support
532+
533+---
534+
535+## Starter
536+
537+Includes:
538+
539+- Expanded analysis limits
540+- AI commentary
541+- Regime Monitor
542+- Earnings Risk
543+- Drawdown Analysis
544+- Volatility Analysis
545+- Position Sizer
546+
547+---
548+
549+## Pro
550+
551+Includes:
552+
553+- Correlation Scanner
554+- Risk Alerts
555+- Portfolio Analytics
556+- Unlimited History
557+- Export Features
558+
559+---
560+
561+## Trader
562+
563+Includes:
564+
565+- API Access
566+- Advanced Monitoring
567+- Larger Portfolio Limits
568+- Priority Processing
569+
570+---
571+
572+# Engineering Rules
573+
574+## Business Logic
575+
576+Never place business logic inside React components.
577+
578+Use:
579+
580+- Services
581+- Hooks
582+- Utility layers
583+- Backend functions
584+
585+---
586+
587+## Source of Truth
588+
589+Risk calculations are authoritative.
590+
591+AI commentary is secondary.
592+
593+Visualisations are derived.
594+
595+---
596+
597+## Determinism
598+
599+Prefer deterministic outputs whenever possible.
600+
601+Avoid hidden behaviour.
602+
603+Avoid unexplained scores.
604+
605+---
606+
607+## Data Handling
608+
609+Cache market data.
610+
611+Reduce redundant API requests.
612+
613+Prioritise performance and consistency.
614+
615+---
616+
617+## Security
618+
104619 Never expose:
105620
106−- Starter features to Free users
107−- Pro features to Starter users
108−- Trader features to lower tiers
621+- Internal model parameters
622+- API secrets
623+- Proprietary calculations
624+- Internal confidence thresholds
109625
110−All checks must be server-side.
626+---
111627
628+# UX Rules
629+
630+Always communicate:
631+
632+- Probability
633+- Risk
634+- Uncertainty
635+- Distribution
636+
637+Avoid:
638+
639+- Certainty
640+- Forecasting
641+- Target prices
642+- Trading signals
643+
112644 ---
113645
114−# Final Decision Rule
646+# Design Principles
115647
116−When multiple solutions exist:
648+OutputLens should feel:
117649
650+- Institutional
651+- Premium
652+- Quantitative
653+- Professional
654+
655+Design should be:
656+
657+- Information dense
658+- Data focused
659+- Low distraction
660+- Dark-theme friendly
661+
662+Avoid:
663+
664+- Excessive animation
665+- Gamification
666+- Celebration effects
667+- Social features
668+
669+---
670+
671+# Future Feature Evaluation
672+
673+Before building a feature ask:
674+
675+1. Does it improve risk understanding?
676+2. Does it improve decision quality?
677+3. Does it increase probability awareness?
678+4. Does it align with probability-first thinking?
679+5. Does it avoid prediction-based behaviour?
680+
681+If any answer is no, reconsider the feature.
682+
683+---
684+
685+# Agent Decision Framework
686+
687+When uncertain:
688+
118689 Choose the option that:
119690
120−- Improves risk understanding
121−- Improves decision quality
691+- Improves risk visibility
122692 - Improves explainability
693+- Improves decision support
694+- Reduces ambiguity
123695 - Preserves institutional credibility
124696
125−Reject options that prioritise speculation over analysis.
697+Never choose the option that:
698+
699+- Increases speculation
700+- Encourages gambling behaviour
701+- Prioritises excitement over accuracy
702+- Mimics retail trading apps
703+
704+---
705+
706+# Internal Motto
707+
708+The market is not a prediction problem.
709+
710+It is a probability distribution.
711+
712+Everything in OutputLens should reinforce that idea.
126713
