Parallax Ai Klarman

Parallax AI Klarman Profile

When not to use

• Bottom-up factor scoring → use /parallax-ai-buffett
• Mechanical formula screen → use /parallax-ai-greenblatt
• Top-down macro analysis → use /parallax-ai-soros
• Cross-profile consensus → use /parallax-ai-consensus
• Full due diligence → use /parallax-due-diligence
• Running backtests → use /backtest

Gotchas

• JIT-load _parallax/parallax-conventions.md for RIC resolution, parallel execution, fallback patterns
• JIT-load _parallax/AI-profiles/profile-schema.md and output-template.md
• JIT-load _parallax/AI-profiles/profiles/klarman.md for the profile spec
• Klarman profile is balance-sheet-first — requires getfinancials(balancesheet) AND getfinancials(cashflow) AND get_financials(ratios), 4 periods each
• 3 statements × 4 periods would be 12 calls, but Parallax returns 4 periods per call → 3 calls + getpeersnapshot + getcompanyinfo = ~5 tokens
• Compute net cash from balance sheet (cash - total debt), not from the ratios summary
• The "no position warranted" output IS valid output — do not treat it as a failure
• NEVER use first-person impersonation; always "Klarman-style"
• Disclaimer verbatim per output-template.md, substituting "Seth Klarman" for [Investor]
• Value threshold is intentionally loose (≥ 4) per Lev-Srivastava 2022 intangibles caveat — do not tighten without re-anchoring
• 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.

Applies Seth Klarman's margin-of-safety framework to a single stock's current balance sheet, cash flow, and peer-relative valuation.

Usage

/parallax-ai-klarman AAPL.O
/parallax-ai-klarman BRKb.N
/parallax-ai-klarman 7203.T

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/klarman.md

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

Step 1 — Resolve ticker

Per shared conventions (RIC suffix table in parallax-conventions.md §1).

Step 2 — Fire data calls in parallel

| Tool | Parameters | Purpose | |---|---|---| | get_company_info | symbol | Sector, market cap, for peer group selection | | get_peer_snapshot | symbol | Factor sub-scores (Value used as backup check) | | get_financials | symbol, statement=balance_sheet | Cash, total debt, equity (4 periods default) | | get_financials | symbol, statement=cash_flow | FCF across 4 periods (default) | | get_financials | symbol, statement=ratios | D/E, P/E, peer medians where available (4 periods default) |

IMPORTANT — MCP parameter serialization: Do NOT pass numeric parameters like periods=4 as explicit arguments via the :periods=4 syntax — the MCP transport serializes them as strings, causing "Expected number, received string" validation errors. The server default is 4 periods; rely on it or pass as a properly-typed integer at the individual tool-call site.

Step 3 — Pre-render cross-validation gate (MANDATORY per spec §6.4)

After get_peer_snapshot returns, cross-check its target_company field (the response carries no name field — each peer's name is comparison[].company) against get_company_info's name. On mismatch, refuse to render and emit:

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

Step 4 — Compute the four Klarman checks

Check 1: Net cash position

• Net cash = (cash and equivalents) − (total debt), from most recent balance sheet
• Net cash ratio = net cash / market cap (from getcompanyinfo)
• PASS if net cash ratio ≥ 0 (positive net cash)
• PARTIAL if ≥ −0.2 (small, manageable net debt)
• FAIL if peer median × 1.0

Backup: Parallax Value sub-score

• Sanity check, not a primary criterion
• Threshold: ≥ 4 (loose per Lev-Srivastava 2022 intangibles caveat)
• If Value

Source: Klarman, S. (1991). Margin of Safety: Risk-Averse Value Investing Strategies for the Thoughtful Investor.

Klarman's framework prioritizes survival over return: balance-sheet strength, downside protection via valuation discount, and willingness to hold cash when nothing qualifies.

| Check | Target | Actual | Result | |------------------------------|---------------------------|---------------------|---------| | Net cash position | Net cash ratio ≥ 0 | | PASS/PARTIAL/FAIL | | Debt vs peer median | D/E ≤ peer median × 1.1 | vs | PASS/FAIL | | FCF stability | Positive ≥ 3 of 4 periods | of 4 | PASS/PARTIAL/FAIL | | Valuation discount | P/E ≤ peer median × 0.85 | vs | PASS/PARTIAL/FAIL |

Parallax Value sub-score (backup check): / 10

Profile fit: — of 4 checks passed.

Verdict sensitivity: the verdict-relevant input nearest its cutoff is ( vs ); state the arithmetic crossing that would change the pass count or Value backup status, and state the verdict change only when that crossing changes the overall match / partial / no-match tier.

[Optional: "No position warranted on this ticker per margin-of-safety principles. Cash is a valid stance."]

Workflow derived from: Klarman, S. (1991). Margin of Safety. Last anchor-tested: 2026-04-07 (BRKb.N, NVDA.O) Tool sequence: getcompanyinfo, getpeersnapshot, getfinancials(balancesheet/cash_flow/ratios, 4 periods) Token cost: ~5 tokens

---

This output is an AI-inferred interpretation of Seth Klarman'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 Seth Klarman 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 7 — Emit

**Steps 1–6 are silent.** Perform the ticker resolution, cross-validation, scoring, threshold logic, and verdict computation internally — none of that working appears in your reply. Your **entire visible response consists only of the rendered Step 6 template plus every required Output addition below**. The analytical template begins at the Header line `Klarman-style profile applied to `. Before it, render only the leading white-label elements required by `integration-pattern.md` §5, in its prescribed order, including a URL logo and the conditional Branding Header when applicable. If no leading white-label element applies, the analytical Header is the absolute first output. The About This Report footer, AI-interaction disclosure, and standard disclaimer remain required parts of the visible response in the positions specified below. Do NOT add `**Step N**` labels, "Cross-validation passed", "All data verified", a "Let me…" preamble, or any other workflow narration.

## 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: `**** Klarman-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 balance-sheet data is unavailable for 4 periods, compute the checks on whatever is available (minimum 2 periods) and flag the coverage loss. If peer-median data is unavailable, skip the debt-vs-peers check and note "Peer comparison unavailable — absolute thresholds applied." If all four checks fail due to missing data, return `DATA_UNAVAILABLE` rather than a false `no_match`.

## 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.