Parallax Ai Ptj

Parallax AI PTJ Profile

When not to use

• Bottom-up factor scoring → use /parallax-ai-buffett
• Mechanical formula screen → use /parallax-ai-greenblatt
• Balance-sheet-first checks → use /parallax-ai-klarman
• Macro regime screening without ticker focus → use /parallax-macro-outlook
• Cross-profile consensus → use /parallax-ai-consensus
• Multiple tickers → use /parallax-ai-consensus

Gotchas

• JIT-load _parallax/parallax-conventions.md, profile-schema.md, output-template.md, profiles/ptj.md
• PTJ is single-ticker mode only — reject multiple tickers with redirect to AI-consensus
• Channels T, M, V are evaluated independently; verdict requires 3 for match, 2 for partial
• gettechnicalanalysis is async (~2-5s) — may time out; fallback to score_analysis Momentum proxy per §4
• macroanalyst requires listmacro_countries first; cap at 3 markets (home + up to 2 exposure markets)
• NEVER use first-person impersonation ("PTJ would buy"); always frame as "PTJ-style lens identifies" or "Profile flags"
• Disclaimer verbatim per output-template.md, substituting "Paul Tudor Jones" for [Investor]
• Cross-validation gate is NON-BYPASSABLE — symbol mismatch between getcompanyinfo and getpeersnapshot halts rendering
• JIT-load _parallax/white-label/integration-pattern.md before the Pre-Render step. Loader call is load_visual_branding() (7-key visual subset; voice structurally excluded — branding["voice"] raises KeyError). Apply §5 (Branding Header) and §7 (About This Report) in Output Format.

Trend-following + macro-overlay framework: technical momentum validation → macro regime check → volatility-based risk/reward asymmetry assessment.

Usage

/parallax-ai-ptj AAPL.O                    # single-ticker mode — tri-channel evaluation
/parallax-ai-ptj JPM.N                     # evaluate ticker for PTJ-style confluence

Workflow

Execute using mcp__claude_ai_Parallax__* tools.

Step 0 — JIT-load dependencies

Before the first Parallax tool call:

1. Load _parallax/parallax-conventions.md
2. Load _parallax/AI-profiles/profile-schema.md
3. Load _parallax/AI-profiles/output-template.md
4. Load _parallax/AI-profiles/profiles/ptj.md

Call ToolSearch with query "+Parallax" to load the deferred MCP tool schemas.

Step 1 — Parse input

Accept exactly one ticker. Reject multiple tickers: "PTJ profile evaluates single stocks. Use /parallax-ai-consensus for multi-ticker comparison."

Resolve RIC per parallax-conventions.md §1.

Step 2 — Macro workflow setup

1. Call list_macro_countries to get covered markets (1 token).
2. Call get_company_info on input ticker to identify home market and sector (1 token).
3. From list_macro_countries response, identify home market (e.g., "United States" for US-listed, "Japan" for Japan-listed) plus up to 2 relevant exposure markets based on sector (e.g., "China" for semiconductors, "Saudi Arabia" for energy). Cap macro analyst calls at 3 markets.

Step 3 — Core tri-channel batch (parallel)

Launch all 5 tools in parallel:

1. get_technical_analysis on input ticker (5 tokens, async ~2-5s)

• Returns: trend direction (POSITIVE / STRONG_POSITIVE / NEUTRAL / NEGATIVE / etc.), momentum config, volatility regime, support/resistance levels, volume analysis
• Used for Channel T evaluation

1. macro_analyst(component=tactical) for home market (5 tokens)

• E.g., macro_analyst(market="United States", component="tactical")
• Returns: tactical directional view (risk-on / risk-off / neutral), sector positioning, headwinds/tailwinds
• Used for Channel M evaluation

1. get_score_analysis on input ticker (1 token)

• Returns: 52-week factor trends including Momentum sub-trend (↑ / → / ↓)
• Used for Channel T sub-signal validation (is momentum trending up?)

1. get_stock_outlook(aspect=risk_return) on input ticker (1 token)

• Returns: analyst price target, upside %, downside %, risk score
• Used for Channel V upside magnitude check

1. get_peer_snapshot on input ticker (1 token)

• Returns: target_company (for cross-validation), Momentum factor score (0-10)
• Used for Channel V momentum score check (>= 5 threshold)

Note: These are independent calls; batch them all together.

Step 4 — Cross-validation gate

After get_peer_snapshot call completes, cross-check target_company (top-level field) against get_company_info's name per profile-schema.md §2 Step 2.

If mismatch, emit standard error and halt rendering:

Error: Symbol cross-validation failed for .
  get_company_info returned: ""
  get_peer_snapshot returned: ""
Cannot render PTJ-style profile — possible wrong-company mapping (see parallax-conventions.md §2).

Step 5 — Macro regime secondary (depends on Step 3 completion)

After get_technical_analysis, get_score_analysis, and get_stock_outlook complete, call macro_analyst for up to 2 additional exposure markets (based on sector). Fire these in parallel if more than one market is needed.

E.g., for semiconductor ticker, add macro_analyst(market="Taiwan", component="tactical") and optionally macro_analyst(market="South Korea", component="tactical").

Step 6 — Tri-channel evaluation

Evaluate all three channels using thresholds from profiles/ptj.md:

Channel T — Technical setup:

• FLAGGED: get_technical_analysis.trend_direction in [POSITIVE, STRONG_POSITIVE] AND get_score_analysis.momentum_trend is ↑ (upward)
• PARTIAL: Exactly one of the two sub-signals is positive (trend positive but momentum trend neutral, or trend neutral but momentum upward)
• NOTFLAGGED: get_technical_analysis.trend_direction in [NEGATIVE, STRONGNEGATIVE] or momentum trend is ↓
• Fallback (if get_technical_analysis times out): Use get_peer_snapshot.Momentum score >= 6 and get_score_analysis.momentum_trend = ↑; note "Technical analysis unavailable — Channel T uses factor proxy"

Channel M — Macro regime:

• FLAGGED: Home market macro_analyst(tactical) view is risk-on OR sector/company is explicitly noted in any exposure market's tactical themes (e.g., "financials benefiting from higher rates" and company is a major bank)
• PARTIAL: Macro view is neutral (neither risk-on nor risk-off) or mixed (some exposure markets favor, others don't)
• NOT_FLAGGED: Home market macro_analyst view is risk-off AND no exposure market themes favor the company's sector

Channel V — Volatility and asymmetry:

• FLAGGED: get_stock_outlook(risk_return).analyst_upside_to_target >= 15% AND get_peer_snapshot.Momentum factor score >= 5
• PARTIAL: Analyst upside in range 8-15% OR Momentum >= 5 but upside

Source: Schwager, J. D. (1989). Market Wizards: Interviews with Top Traders.

Trend-following + macro-overlay framework: technical momentum validation → macro regime alignment → volatility-based asymmetry assessment.

Ticker exposure check (tri-channel):

Channel T — Technical setup Trend direction: Momentum trend (52-week): Status: FLAGGED / PARTIAL / NOT_FLAGGED

Channel M — Macro regime Home market: Tactical view: Sector alignment: Status: FLAGGED / PARTIAL / NOT_FLAGGED

Channel V — Volatility and asymmetry Analyst upside to target: Momentum factor score: Status: FLAGGED / PARTIAL / NOT_FLAGGED

Profile fit:

• match: all three channels flagged (tri-channel alignment)
• partial_match: two channels flagged (two-signal alignment)
• no_match: zero or one channel flagged (insufficient confluence; capital preservation)

Setup quality:

Workflow derived from: Schwager (1989); Covel (2004). Last anchor-tested: 2026-04-07 (NVDA.O, JPM.N) Tool sequence: listmacrocountries, getcompanyinfo, gettechnicalanalysis, macroanalyst × N (N ≤ 3), getscoreanalysis, getstockoutlook, getpeer_snapshot Token cost: ~20-25 tokens (3 macro markets) / ~14-16 tokens (1 macro market)

---

This output is an AI-inferred interpretation of Paul Tudor Jones's approach, derived solely from publicly available information — the cited source, Parallax factor data, and Parallax's public methodology. It is produced by the Parallax AI Investor Profiles framework. It is not financial advice, not personalized, not endorsed by Paul Tudor Jones or his representatives, and not a recommendation to buy or sell any security. For illustrative and educational use only. Past characterization does not guarantee future relevance. Please consult a qualified financial advisor before making investment decisions.

### Step 9 — Emit

## Output additions (white-label branding + §9.2 disclosure)

These additions apply to the rendered output ABOVE in addition to the persona-specific disclaimer shown in the output example. They are required regardless of view state.

### Pre-Render — Load white-label branding

Load `_parallax/white-label/integration-pattern.md` §2 and compute `white_label_active` + `client_name` per that section. Apply §5 (Branding Header) and §7 (About This Report) when composing the Output Format.

- **Branding Header** (only if `white_label_active` AND `client_name != ""`) — single line at the very top of the rendered output: `**** PTJ-style profile`. Logo handling per integration-pattern.md §5.
- **About This Report** (always present): one line stating branding state per integration-pattern.md §7. If a logo was skipped, append `Logo on file: ` as a second About This Report line.

**AI-interaction disclosure (required regardless of view state):** Render `parallax-conventions.md §9.2` immediately above the disclaimer below. The persona-specific disclaimer in the output example characterizes the source of the framing; the §9.2 banner characterizes the LLM-generated synthesis itself.

Render the standard disclaimer verbatim from `parallax-conventions.md` §9.1.

## Graceful fallback

**If `get_technical_analysis` times out (async tool):**
Evaluate Channel T using `get_peer_snapshot.Momentum` >= 6 AND `get_score_analysis.momentum_trend` = ↑. Note in output: "Channel T: Technical analysis unavailable — using factor proxy (Momentum score + trend direction)." Channel T maximum verdict remains FLAGGED/PARTIAL/NOT_FLAGGED based on proxy data.

**If `macro_analyst` fails for home market:**
Proceed with up to 2 exposure-market macro calls. If ≥1 succeeds, evaluate Channel M based on exposure markets. If all macro calls fail, Channel M is UNAVAILABLE (not NOT_FLAGGED). Maximum verdict becomes partial_match (single-channel + available channels).

**If `get_stock_outlook(risk_return)` fails:**
Channel V cannot be evaluated. Mark as UNAVAILABLE. Verdict maximum is partial_match if other channels succeed.

**If `get_peer_snapshot` fails (cross-validation blocking):**
Cannot complete cross-validation gate. Halt rendering with error message per Step 4.

**If all three channels return UNAVAILABLE:**
Halt rendering: "Insufficient data to evaluate PTJ-style framework. Service temporarily unavailable."

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [bencharoenwong](https://github.com/bencharoenwong)
- **Source:** [bencharoenwong/parallax-workflows](https://github.com/bencharoenwong/parallax-workflows)
- **License:** MIT

Install and usage instructions live in the source repository linked above.