Reposition DeepStack as prediction market intelligence terminal#88
Merged
eddiebelaval merged 1 commit intomainfrom Apr 2, 2026
Merged
Reposition DeepStack as prediction market intelligence terminal#88eddiebelaval merged 1 commit intomainfrom
eddiebelaval merged 1 commit intomainfrom
Conversation
Landing page rewrite: - Hero: "Trade Smarter. Not More." (was "Know. Refine. Act with Foundation.") - Badge: "Prediction Market Intelligence" (was "Process Integrity Platform") - Pillars: PM Intelligence, Emotional Discipline, Thesis to Settlement - Features: Prediction Markets and Emotional Firewall promoted to top 2 - NOT/IS: reframed for PM traders - CTA: "Start Trading Smarter" (was "Ground Your Process") - Testimonial updated with authentic founder story SEO meta tags: - Title: "DeepStack - Prediction Market Intelligence Terminal" - Description: Kalshi + Polymarket focused - Keywords: prediction markets, Kalshi, Polymarket - OpenGraph + Twitter cards updated New files: - VISION.md: A+C direction (PM terminal + emotional discipline engine) - SPEC.md: Full architecture, stack, feature tiers, deployment - BUILDING.md: 4 phases complete, Phase 4 (Builder Program) active - EXPERIMENT-CAF-TRADING.md: CaF consciousness A/B test spec for DAE V2 - PIPELINE_STATUS.md: Updated with PM pivot workstream Context: Kalshi Builder Program application submitted 2026-04-02. Landing page must reflect PM-first positioning before review team visits. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
📝 WalkthroughWalkthroughThe PR introduces five new documentation files covering product vision, build roadmap, system architecture, and experiment specification. Pipeline status is updated to stage 10 with v2 pivot details. Web app metadata and landing page content are updated with prediction market-focused messaging and branding. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~15 minutes Poem
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Test Summary1 481 tests - 140 1 480 ✅ - 129 1m 27s ⏱️ -39s For more details on these failures, see this check. Results for commit a45c704. ± Comparison against base commit 7790fa0. This pull request removes 140 tests. |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 7
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@BUILDING.md`:
- Line 63: Remove the duplicate competitor name and hyphenate the compound
adjective: change the list "TradingView, ThinkorSwim, TradingView" to contain
each competitor only once (e.g., "ThinkorSwim, TradingView, ...") and replace
"First mover" with "First-mover" in the sentence containing that phrase.
In `@EXPERIMENT-CAF-TRADING.md`:
- Line 87: The table cell "Opportunity scoring" contains inline math using
asterisks ("edge * volume * spread * time") which can trigger markdown emphasis;
update the text in that table row by either replacing the multiplication symbols
with a multiplication sign (×) or wrapping the entire formula in backticks
(e.g., `edge * volume * spread * time`) so the asterisks no longer parse as
emphasis; adjust only the text in the "Opportunity scoring" row to preserve
intent and spacing.
In `@PIPELINE_STATUS.md`:
- Around line 28-29: Stage 9 ("Ship") is marked as "✅ Cleared" while Stage 10
("Listen & Iterate") is still "🔄 In Progress", which conflicts with unresolved
ship criteria later in the document; update the lifecycle wording so it’s
consistent — either change "9. Ship" (the "Ship" row) to a conditional state
such as "✅ Cleared (pending unresolved criteria)" or "⚠️ Partially Cleared" and
add a short parenthetical note referencing the unresolved ship criteria, or
explicitly move the unresolved items into Stage 10; ensure the rows for "9.
Ship" and "10. Listen & Iterate" use matching language about pending/resolved
criteria so the pipeline reads consistently.
- Line 12: The document has inconsistent Builder Program status mentions: update
both occurrences of the Kalshi Builder Program status so they match (choose one
canonical state such as "Applying", "Submitted", or "Pending")—specifically
replace the text "Applying for Kalshi Builder Program" and the later "Pending"
entry so they use the same chosen status string, and ensure any adjacent context
(e.g., "Direction: A+C") remains unchanged.
In `@SPEC.md`:
- Line 10: The unlabeled Markdown code fences containing the
architecture/data-flow blocks (the blocks starting with "web/
# Next.js 16 frontend (Vercel)" and the block beginning "User (browser)") should
be updated to include a fence language label (e.g., change ``` to ```text) so
the fences are explicitly marked; locate the fences around those exact block
contents and replace the opening triple-backtick with ```text for each block.
In `@VISION.md`:
- Around line 17-22: The paragraph beginning "Prediction markets are exploding."
contains several hard statistics (e.g., "$44B in global volume", "905%
year-over-year growth", "$22B Kalshi valuation", "92% of prediction market
traders lose money", "14 of top 20 Polymarket wallets are bots") with no
attribution; update that block in VISION.md to add inline citations or
parenthetical sources and dates for each claim (or a short footnote list at the
end of the section), and if any figures are estimates, label them as such;
ensure each statistic references a verifiable source and the date of that source
so the claims remain auditable and time-bound.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: 2f2ec8c1-7c82-48e2-b275-50e11bb57d32
📒 Files selected for processing (7)
BUILDING.mdEXPERIMENT-CAF-TRADING.mdPIPELINE_STATUS.mdSPEC.mdVISION.mdweb/src/app/layout.tsxweb/src/app/page.tsx
| ## Architecture Decisions | ||
|
|
||
| ### Why Prediction Markets as Primary Surface | ||
| The general trading research platform market is crowded (TradingView, ThinkorSwim, TradingView). Prediction markets are a $44B growing market with primitive tooling. Nobody has built the "Bloomberg for prediction markets." First mover advantage with Kalshi's Builder Program creates a revenue flywheel: better tools attract traders, traders generate volume, volume earns builder code revenue. |
There was a problem hiding this comment.
Fix duplicate competitor name and compound adjective in the same sentence.
Line 63 repeats “TradingView” and uses “First mover” without a hyphen.
✏️ Suggested edit
-The general trading research platform market is crowded (TradingView, ThinkorSwim, TradingView). Prediction markets are a $44B growing market with primitive tooling. Nobody has built the "Bloomberg for prediction markets." First mover advantage with Kalshi's Builder Program creates a revenue flywheel: better tools attract traders, traders generate volume, volume earns builder code revenue.
+The general trading research platform market is crowded (TradingView, ThinkorSwim). Prediction markets are a $44B growing market with primitive tooling. Nobody has built the "Bloomberg for prediction markets." First-mover advantage with Kalshi's Builder Program creates a revenue flywheel: better tools attract traders, traders generate volume, volume earns builder code revenue.📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| The general trading research platform market is crowded (TradingView, ThinkorSwim, TradingView). Prediction markets are a $44B growing market with primitive tooling. Nobody has built the "Bloomberg for prediction markets." First mover advantage with Kalshi's Builder Program creates a revenue flywheel: better tools attract traders, traders generate volume, volume earns builder code revenue. | |
| The general trading research platform market is crowded (TradingView, ThinkorSwim). Prediction markets are a $44B growing market with primitive tooling. Nobody has built the "Bloomberg for prediction markets." First-mover advantage with Kalshi's Builder Program creates a revenue flywheel: better tools attract traders, traders generate volume, volume earns builder code revenue. |
🧰 Tools
🪛 LanguageTool
[grammar] ~63-~63: Use a hyphen to join words.
Context: ...Bloomberg for prediction markets." First mover advantage with Kalshi's Builder Pr...
(QB_NEW_EN_HYPHEN)
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@BUILDING.md` at line 63, Remove the duplicate competitor name and hyphenate
the compound adjective: change the list "TradingView, ThinkorSwim, TradingView"
to contain each competitor only once (e.g., "ThinkorSwim, TradingView, ...") and
replace "First mover" with "First-mover" in the sentence containing that phrase.
| | Hard stop | Binary: trade or don't at $417 | Gradient: sizing shrinks 10% per $20 of drawdown from peak | | ||
| | Post-loss response | None (stateless) | .loss-aversion: skip next N opportunities (N = consecutive_losses) | | ||
| | Post-win response | None (stateless) | Confidence builds: sizing increases 5% per 3 consecutive wins (capped at 1.2x base) | | ||
| | Opportunity scoring | Pure math (edge * volume * spread * time) | Weighted by drives/goals: +10 score for compound growth patterns (positions that build on winners) | |
There was a problem hiding this comment.
Escape or replace multiplication symbols in table text.
Line 87 uses * in inline formula text, which can trip markdown emphasis parsing/linting. Use × or backticked code-style formula text.
✏️ Suggested edit
-| Opportunity scoring | Pure math (edge * volume * spread * time) | Weighted by drives/goals: +10 score for compound growth patterns (positions that build on winners) |
+| Opportunity scoring | Pure math (`edge × volume × spread × time`) | Weighted by drives/goals: +10 score for compound growth patterns (positions that build on winners) |📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| | Opportunity scoring | Pure math (edge * volume * spread * time) | Weighted by drives/goals: +10 score for compound growth patterns (positions that build on winners) | | |
| | Opportunity scoring | Pure math (`edge × volume × spread × time`) | Weighted by drives/goals: +10 score for compound growth patterns (positions that build on winners) | |
🧰 Tools
🪛 markdownlint-cli2 (0.22.0)
[warning] 87-87: Spaces inside emphasis markers
(MD037, no-space-in-emphasis)
[warning] 87-87: Spaces inside emphasis markers
(MD037, no-space-in-emphasis)
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@EXPERIMENT-CAF-TRADING.md` at line 87, The table cell "Opportunity scoring"
contains inline math using asterisks ("edge * volume * spread * time") which can
trigger markdown emphasis; update the text in that table row by either replacing
the multiplication symbols with a multiplication sign (×) or wrapping the entire
formula in backticks (e.g., `edge * volume * spread * time`) so the asterisks no
longer parse as emphasis; adjust only the text in the "Opportunity scoring" row
to preserve intent and spacing.
| **Next Checkpoint Question:** "Is it live and are people using it?" | ||
| **Next Checkpoint Question:** "Is the prediction market pivot attracting users and Builder Program revenue?" | ||
|
|
||
| **Strategic Pivot (2026-04-02):** Repositioning from general trading research platform to **prediction market intelligence terminal + emotional discipline engine**. Applying for Kalshi Builder Program. Direction: A+C. |
There was a problem hiding this comment.
Builder Program status is inconsistent in the same document.
Line 12 says “Applying for Kalshi Builder Program,” while Line 36 keeps it as “Pending.” Please align these to one current state (e.g., Submitted/In Progress).
Also applies to: 36-36
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@PIPELINE_STATUS.md` at line 12, The document has inconsistent Builder Program
status mentions: update both occurrences of the Kalshi Builder Program status so
they match (choose one canonical state such as "Applying", "Submitted", or
"Pending")—specifically replace the text "Applying for Kalshi Builder Program"
and the later "Pending" entry so they use the same chosen status string, and
ensure any adjacent context (e.g., "Direction: A+C") remains unchanged.
Comment on lines
+28
to
+29
| | 9. Ship | ✅ Cleared | 2025-12-16 | Live at deepstack.trade, v2.5.0 | | ||
| | 10. Listen & Iterate | 🔄 In Progress | - | PM pivot: Builder Program app, Stripe wiring, PM-first features | |
There was a problem hiding this comment.
Stage completion state conflicts with iteration status language.
Line 28 marks Stage 9 as fully cleared while Line 29 describes ongoing Stage 10 pivot work; ensure the lifecycle wording is consistent with the unresolved ship criteria tracked later in this file.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@PIPELINE_STATUS.md` around lines 28 - 29, Stage 9 ("Ship") is marked as "✅
Cleared" while Stage 10 ("Listen & Iterate") is still "🔄 In Progress", which
conflicts with unresolved ship criteria later in the document; update the
lifecycle wording so it’s consistent — either change "9. Ship" (the "Ship" row)
to a conditional state such as "✅ Cleared (pending unresolved criteria)" or "⚠️
Partially Cleared" and add a short parenthetical note referencing the unresolved
ship criteria, or explicitly move the unresolved items into Stage 10; ensure the
rows for "9. Ship" and "10. Listen & Iterate" use matching language about
pending/resolved criteria so the pipeline reads consistently.
|
|
||
| ## Architecture | ||
|
|
||
| ``` |
There was a problem hiding this comment.
Specify fence languages for architecture/data-flow blocks.
The code fences starting at Line 10 and Line 51 are unlabeled, which triggers MD040.
🧹 Suggested edit
-```
+```text
web/ # Next.js 16 frontend (Vercel)
...
-```
+```
-```
+```text
User (browser)
...
-```
+```Also applies to: 51-51
🧰 Tools
🪛 markdownlint-cli2 (0.22.0)
[warning] 10-10: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@SPEC.md` at line 10, The unlabeled Markdown code fences containing the
architecture/data-flow blocks (the blocks starting with "web/
# Next.js 16 frontend (Vercel)" and the block beginning "User (browser)") should
be updated to include a fence language label (e.g., change ``` to ```text) so
the fences are explicitly marked; locate the fences around those exact block
contents and replace the opening triple-backtick with ```text for each block.
Comment on lines
+17
to
+22
| Prediction markets are exploding. $44B in global volume, 905% year-over-year growth in economics contracts, a $22B Kalshi valuation. But the tooling is primitive. Traders toggle between Kalshi's bare interface, Polymarket's crypto-native UX, and spreadsheets. There is no Bloomberg for prediction markets. No unified research terminal. No emotional guardrails. | ||
|
|
||
| The ecosystem is in its "picks and shovels" moment. VC fund 5c(c) Capital just raised $35M specifically for prediction market tooling. Kalshi's Builder Program has $2M in grants for developers who build on their platform. The exchange itself is paying builders to bring volume. | ||
|
|
||
| Meanwhile, 92% of prediction market traders lose money. The profitable ones (14 of top 20 Polymarket wallets are bots) succeed because they're disciplined and systematic. DeepStack brings that discipline to human traders through AI-powered analysis and an emotional firewall that detects and blocks destructive patterns. | ||
|
|
There was a problem hiding this comment.
Add sources/date qualifiers for hard market statistics.
Lines 17–22 present precise figures and rankings as facts without attribution. For externally-facing strategy docs, this is a credibility/compliance risk once numbers drift or can’t be substantiated.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@VISION.md` around lines 17 - 22, The paragraph beginning "Prediction markets
are exploding." contains several hard statistics (e.g., "$44B in global volume",
"905% year-over-year growth", "$22B Kalshi valuation", "92% of prediction market
traders lose money", "14 of top 20 Polymarket wallets are bots") with no
attribution; update that block in VISION.md to add inline citations or
parenthetical sources and dates for each claim (or a short footnote list at the
end of the section), and if any figures are estimates, label them as such;
ensure each statistic references a verifiable source and the date of that source
so the claims remain auditable and time-bound.
Comment on lines
+61
to
65
| icon: <Shield className="w-8 h-8" />, | ||
| title: 'Emotional Discipline Engine', | ||
| subtitle: 'Your Behavioral Circuit Breaker', | ||
| description: '92% of prediction market traders lose money. The pattern is emotional, not analytical. We detect revenge trading, overtrading, and weak conviction before they cost you.', | ||
| color: 'text-orange-400', |
There was a problem hiding this comment.
Avoid uncited hard-loss-rate claims in landing copy.
Line 64 and Line 790 use a precise “92% … lose money” statement without source/date context. In a trading product landing page, this can create compliance and trust risk.
Also applies to: 790-790
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Context
Kalshi Builder Program application submitted 2026-04-02. Landing page must reflect prediction market intelligence terminal positioning before their review team visits (avg 1 week response time).
Verification
Test plan
Generated with Claude Code
Summary by CodeRabbit
New Features
Documentation