Methodology fused from institutional portfolio-construction and buy-side long/short frameworks; all text is an original paraphrase.
Defaults
| Parameter |
Default Value |
Rationale |
| lookback_quarters |
4 |
Standard window for beta and correlation estimation |
| gross_exposure_target |
150% |
Mid-range of the 130-200% institutional band |
| net_exposure_band |
-20% to +60% |
Defines strategy identity; outside this is style drift |
| beta_net_deviation_max |
15pp |
Gap between raw and beta-adjusted net above which the hedge is mis-specified |
| max_long_position |
5% |
Standard conviction sizing |
| max_short_position |
3% |
Halved for unbounded loss and adverse position drift |
| max_days_to_cover |
5 |
Squeeze avoidance on any single short |
Preflight
Run canonical pre-flight per contracts/preflight.md. Propagate X-Agentii-Trace per contracts/x-agentii-trace-header.md.
Data Source Priority
- Construction methodology —
references/construction-methodology.md (bundled exposure framework)
- Strategy frameworks —
search_investment_strategies(domain=fundamental, kind=position_sizing)
- Historical analogues —
search_by_analogue(market_regime=...) for regime-specific exposure precedent
- Market data —
~~market_data placeholder for beta estimation and borrow/short-interest inputs
Methodology
Retrieval Scope
structured_only
Retrieval Strategy
Ownership & insider signals: search_institutional_holdings (top-10 holders + whale portfolios, direction=accumulating|reducing|new|exited) and search_insider_trades (Form-4 transactions with SEC URLs) are available as signal inputs.
Branch (a) Structured Data Query from contracts/retrieval.md. Retrieve construction frameworks via search_investment_strategies; retrieve regime precedent via search_by_analogue. Detailed methodology in references/construction-methodology.md.
Temporal Scope
See frontmatter temporal_scope block.
Tool Allowlist
See frontmatter allowed_tools.
Protocol
Gross and net exposure are two independent dials. Gross sets how much stock-specific
opportunity the book harvests; net sets how much of the return is simply the market.
Raising gross while holding net constant is the defining move of long/short construction —
it is what separates the strategy from levered long-only. Full derivations, attribution
worked examples, and book-level limit tables are in references/construction-methodology.md.
Foundational principle: return tracks net exposure, not gross. Adding equal-beta
shorts to a long book halves the return without improving selection. A short book that
exists only to damp beta is a pure drag — shorts must earn their own alpha, or index-level
hedging is the cheaper and more honest instrument.
Steps
Exposure Inventory: Compute long %, short %, gross (L+S), and raw net (L−S) against
NAV. Record the starting point before any proposed change.
Beta-Adjusted Net (the decision-grade measure): Compute
(Long% x weighted long beta) - (Short% x weighted short beta). Raw net silently assumes
both sides share market sensitivity. High-beta growth longs hedged with defensive
low-beta shorts can carry more directional risk than raw net implies. If raw and
beta-adjusted net diverge by more than beta_net_deviation_max, the hedge is
mis-specified — re-select or re-size the short side rather than reporting raw net.
Risk Decomposition: Confirm the book's residual is idiosyncratic. Market components
offset across paired exposure, leaving long-side plus short-side company/industry risk.
Note the failure mode explicitly: with beta removed there is no tailwind to carry weak
selection.
Short-Side Classification: Separate alpha shorts (held to earn a return on their
own thesis) from index shorts (held to damp beta). These are not interchangeable —
using alpha shorts as a beta hedge pays the analytical cost of the former for the return
profile of the latter. Screen every alpha short against the seven structural constraints
(market long bias, unbounded loss, timing, borrow availability, short interest and
days-to-cover, volatility asymmetry, sizing).
Position Drift Check: Short weights move adversely by construction — a losing short
grows into the book while a losing long shrinks out of it. Schedule re-sizing rather than
relying on stops alone. Flag any short exceeding max_short_position or
max_days_to_cover.
Pair Integrity (when expressing an explicit pair): same primary risk factor on both
legs; beta-match rather than dollar-match; each leg must clear the research bar
independently; name the divergence catalyst and its date range; size for the decoupled
case, since correlated legs decouple precisely under the stress the pair was built to
survive.
Sensitivity Grid: Publish fund return across a −20% to +20% market range. The slope
of the row is net exposure; the intercept is alpha. Diagnose both separately — a
book can post a good return while its intercept is zero and its slope is merely large.
Limit Reconciliation: Check gross, net band, sector net, and per-position sizes
against Defaults. Recompute all three exposure measures after every position change; the
two dials stay independent only if measured continuously, otherwise a series of
individually reasonable trades silently converts a hedged book into a levered
directional one.
Output: Report both exposure measures, the attribution split (beta contribution vs
alpha contribution per side), the sensitivity grid, and every limit breach.
Output File
{ticker}/{YYYY-MM-DD_HHMM}_long-short-construction_{affix}.md
Output Structure
- Executive Summary — current gross/net/beta-adjusted net and whether the book sits within its mandate band
- Exposure Table — long %, short %, gross, raw net, beta-adjusted net, with weighted betas per side
- Attribution Split — beta contribution vs alpha contribution for the long and short books separately
- Short-Side Review — alpha vs index classification, seven-constraint screen, days-to-cover and borrow status
- Pair Detail — per-pair legs, beta match, divergence catalyst and expected window
- Sensitivity Grid — fund return across −20% to +20% market range, with slope (net) and intercept (alpha) called out
- Limit Reconciliation — every Defaults threshold with pass/breach status
- Historical Analogues — regime-matched exposure precedent with /v/ citations
- Coverage Gaps — missing betas, unavailable borrow data, degraded-mode flags
Error Handling
| Error |
Fallback |
| No beta data for a holding |
Use sector-median beta; flag the substitution and widen the reported beta-adjusted net as a range |
| Borrow / short-interest data unavailable |
Report the short as unverified for squeeze risk; do not clear it against max_days_to_cover |
search_investment_strategies unreachable |
Proceed with references/construction-methodology.md; annotate coverage_gap |
search_by_analogue returns empty |
Continue without regime precedent; flag reduced confidence on the exposure band |
Memory Load
See contracts/memory-load.md.
Snapshot
See contracts/snapshot-synthesis.md.
Final Summary (TUI)
Include ### Key Citations block with 0-10 clickable /v/ URLs.
References
references/construction-methodology.md
contracts/citation-and-memory.md
contracts/retrieval.md
contracts/output-frontmatter-schema.md
contracts/memory-load.md
contracts/snapshot-synthesis.md
contracts/preflight.md
1---2name: long-short-construction3description: Long short portfolio construction, market neutral positioning, factor-balanced book, gross and net exposure management, pair selection, beta hedging, portfolio construction methodology4---56> Methodology fused from institutional portfolio-construction and buy-side long/short frameworks; all text is an original paraphrase.78## Defaults910| Parameter | Default Value | Rationale |11|-----------|---------------|-----------|12| lookback_quarters | 4 | Standard window for beta and correlation estimation |13| gross_exposure_target | 150% | Mid-range of the 130-200% institutional band |14| net_exposure_band | -20% to +60% | Defines strategy identity; outside this is style drift |15| beta_net_deviation_max | 15pp | Gap between raw and beta-adjusted net above which the hedge is mis-specified |16| max_long_position | 5% | Standard conviction sizing |17| max_short_position | 3% | Halved for unbounded loss and adverse position drift |18| max_days_to_cover | 5 | Squeeze avoidance on any single short |1920## Preflight2122Run canonical pre-flight per `contracts/preflight.md`. Propagate X-Agentii-Trace per `contracts/x-agentii-trace-header.md`.2324## Data Source Priority25261. Construction methodology — `references/construction-methodology.md` (bundled exposure framework)272. Strategy frameworks — `search_investment_strategies(domain=fundamental, kind=position_sizing)`283. Historical analogues — `search_by_analogue(market_regime=...)` for regime-specific exposure precedent294. Market data — `~~market_data` placeholder for beta estimation and borrow/short-interest inputs3031## Methodology3233### Retrieval Scope34structured_only3536### Retrieval Strategy37**Ownership & insider signals**: `search_institutional_holdings` (top-10 holders + whale portfolios, `direction=accumulating|reducing|new|exited`) and `search_insider_trades` (Form-4 transactions with SEC URLs) are available as signal inputs.3839Branch (a) Structured Data Query from `contracts/retrieval.md`. Retrieve construction frameworks via `search_investment_strategies`; retrieve regime precedent via `search_by_analogue`. Detailed methodology in `references/construction-methodology.md`.4041### Temporal Scope42See frontmatter temporal_scope block.4344### Tool Allowlist45See frontmatter allowed_tools.4647### Protocol4849Gross and net exposure are **two independent dials**. Gross sets how much stock-specific50opportunity the book harvests; net sets how much of the return is simply the market.51Raising gross while holding net constant is the defining move of long/short construction —52it is what separates the strategy from levered long-only. Full derivations, attribution53worked examples, and book-level limit tables are in `references/construction-methodology.md`.5455**Foundational principle**: return tracks **net** exposure, not gross. Adding equal-beta56shorts to a long book halves the return without improving selection. A short book that57exists only to damp beta is a pure drag — shorts must earn their own alpha, or index-level58hedging is the cheaper and more honest instrument.5960#### Steps61621. **Exposure Inventory**: Compute long %, short %, gross (L+S), and raw net (L−S) against63 NAV. Record the starting point before any proposed change.64652. **Beta-Adjusted Net** (the decision-grade measure): Compute66 `(Long% x weighted long beta) - (Short% x weighted short beta)`. Raw net silently assumes67 both sides share market sensitivity. High-beta growth longs hedged with defensive68 low-beta shorts can carry *more* directional risk than raw net implies. If raw and69 beta-adjusted net diverge by more than `beta_net_deviation_max`, the hedge is70 mis-specified — re-select or re-size the short side rather than reporting raw net.71723. **Risk Decomposition**: Confirm the book's residual is idiosyncratic. Market components73 offset across paired exposure, leaving long-side plus short-side company/industry risk.74 Note the failure mode explicitly: with beta removed there is no tailwind to carry weak75 selection.76774. **Short-Side Classification**: Separate **alpha shorts** (held to earn a return on their78 own thesis) from **index shorts** (held to damp beta). These are not interchangeable —79 using alpha shorts as a beta hedge pays the analytical cost of the former for the return80 profile of the latter. Screen every alpha short against the seven structural constraints81 (market long bias, unbounded loss, timing, borrow availability, short interest and82 days-to-cover, volatility asymmetry, sizing).83845. **Position Drift Check**: Short weights move adversely by construction — a losing short85 grows into the book while a losing long shrinks out of it. Schedule re-sizing rather than86 relying on stops alone. Flag any short exceeding `max_short_position` or87 `max_days_to_cover`.88896. **Pair Integrity** (when expressing an explicit pair): same primary risk factor on both90 legs; beta-match rather than dollar-match; each leg must clear the research bar91 independently; name the divergence catalyst and its date range; size for the decoupled92 case, since correlated legs decouple precisely under the stress the pair was built to93 survive.94957. **Sensitivity Grid**: Publish fund return across a −20% to +20% market range. The slope96 of the row **is** net exposure; the intercept **is** alpha. Diagnose both separately — a97 book can post a good return while its intercept is zero and its slope is merely large.98998. **Limit Reconciliation**: Check gross, net band, sector net, and per-position sizes100 against Defaults. Recompute all three exposure measures after every position change; the101 two dials stay independent only if measured continuously, otherwise a series of102 individually reasonable trades silently converts a hedged book into a levered103 directional one.1041059. **Output**: Report both exposure measures, the attribution split (beta contribution vs106 alpha contribution per side), the sensitivity grid, and every limit breach.107108## Output File109110`{ticker}/{YYYY-MM-DD_HHMM}_long-short-construction_{affix}.md`111112## Output Structure1131141. **Executive Summary** — current gross/net/beta-adjusted net and whether the book sits within its mandate band1152. **Exposure Table** — long %, short %, gross, raw net, beta-adjusted net, with weighted betas per side1163. **Attribution Split** — beta contribution vs alpha contribution for the long and short books separately1174. **Short-Side Review** — alpha vs index classification, seven-constraint screen, days-to-cover and borrow status1185. **Pair Detail** — per-pair legs, beta match, divergence catalyst and expected window1196. **Sensitivity Grid** — fund return across −20% to +20% market range, with slope (net) and intercept (alpha) called out1207. **Limit Reconciliation** — every Defaults threshold with pass/breach status1218. **Historical Analogues** — regime-matched exposure precedent with /v/ citations1229. **Coverage Gaps** — missing betas, unavailable borrow data, degraded-mode flags123124## Error Handling125126| Error | Fallback |127|-------|----------|128| No beta data for a holding | Use sector-median beta; flag the substitution and widen the reported beta-adjusted net as a range |129| Borrow / short-interest data unavailable | Report the short as unverified for squeeze risk; do not clear it against `max_days_to_cover` |130| `search_investment_strategies` unreachable | Proceed with `references/construction-methodology.md`; annotate `coverage_gap` |131| `search_by_analogue` returns empty | Continue without regime precedent; flag reduced confidence on the exposure band |132133## Memory Load134135See `contracts/memory-load.md`.136137## Snapshot138139See `contracts/snapshot-synthesis.md`.140141## Final Summary (TUI)142143Include ### Key Citations block with 0-10 clickable /v/ URLs.144145## References146147- `references/construction-methodology.md`148- `contracts/citation-and-memory.md`149- `contracts/retrieval.md`150- `contracts/output-frontmatter-schema.md`151- `contracts/memory-load.md`152- `contracts/snapshot-synthesis.md`153- `contracts/preflight.md`