aggregate_sentiment
ChatGPTTally bullish / bearish / neutral / not_covered counts per asset class. Critical use: call once with source_type='web' (research only), call again unfiltered. Sentiment divergence between research and the broader corpus is a contrarian signal worth investigating.
aggregate_sentiment
ChatGPTTally bullish / bearish / neutral / not_covered counts per asset class. Critical use: call once with source_type='research' (research only), call again unfiltered. Sentiment divergence between research and the broader corpus is a contrarian signal worth investigating.
aggregate_tags
ChatGPTTop tags by mention count, classified as surging / new heat / fading / steady based on recent vs prior split of the window.
aggregate_tags
ChatGPTTop tags by mention count, classified as surging / new heat / fading / steady based on recent vs prior split of the window.
compare_funds
ChatGPTBatched details + metrics for many funds in one call (up to 20). Use this when comparing a curated set of funds — e.g. user picked several candidates, an analyst is evaluating peers. Returns the full detail-shape per fund (classification, exposure, fees, AUM, Hebrew description) PLUS the metrics block (returns, annualized returns, risk). Funds that don't exist (deleted / unknown id) are silently omitted. Detect gaps via the requested_count vs count fields.
compare_funds
ChatGPTBatched details + metrics for many funds in one call (up to 20). Use this when comparing a curated set of funds — e.g. user picked several candidates, an analyst is evaluating peers. Returns the full detail-shape per fund (classification, exposure, fees, AUM, Hebrew description) PLUS the metrics block (returns, annualized returns, risk). Funds that don't exist (deleted / unknown id) are silently omitted. Detect gaps via the requested_count vs count fields.
compare_funds_by_metric
ChatGPTRANK funds by a performance or risk metric — best/worst returns, most/least volatile, highest/lowest Sharpe. Use this for any "top N" or "best X" question. Do NOT use query_funds for ranking — it filters by attributes only and does not sort by performance. Optionally filter the ranked universe by classification category or fund manager.
compare_funds_by_metric
ChatGPTRANK funds by a performance or risk metric — best/worst returns, most/least volatile, highest/lowest Sharpe. Use this for any "top N" or "best X" question. Do NOT use query_funds for ranking — it filters by attributes only and does not sort by performance. Optionally filter the ranked universe by classification category or fund manager.
find_similar
ChatGPTFind similar funds to a seed fund. Reads precomputed table. sort_by="similarity" (default): top-k methodologically similar peers. sort_by="cheaper": only candidates cheaper than the seed, sorted by (similarity desc, fee asc) — for "cheaper version of X". Each result has: fund_id, name, isin, manager, rank, score (0-10), match_level (high|medium|low), reason_he (Hebrew explanation), management_fee, fee_delta_pct (negative = cheaper than seed). Requires numeric fund_id. If you have an ISIN, use query_funds(isin=...) first.
find_similar
ChatGPTFind similar funds to a seed fund. Reads precomputed table. sort_by="similarity" (default): top-k methodologically similar peers. sort_by="cheaper": only candidates cheaper than the seed, sorted by (similarity desc, fee asc) — for "cheaper version of X". Each result has: fund_id, name, isin, manager, rank, score (0-10), match_level (high|medium|low), reason_he (Hebrew explanation), management_fee, fee_delta_pct (negative = cheaper than seed). Requires numeric fund_id. If you have an ISIN, use query_funds(isin=...) first.
get_category_aum_growth
ChatGPTAUM growth scorecard for one TASE classification — is the category gaining or losing assets. Use this to answer "is bond AUM growing", "are equity flows reversing", "what's the asset trajectory of category X". Returns current category AUM and absolute + percentage change across standard windows: 1m/3m/6m/1y/2y. AUM change includes both flows AND market performance — for ETF-heavy categories it conflates investor flows with NAV moves. Cleanest flow signal for stable-NAV categories like money-market and short-bond.
get_category_aum_growth
ChatGPTAUM growth scorecard for one TASE classification — is the category gaining or losing assets. Use this to answer "is bond AUM growing", "are equity flows reversing", "what's the asset trajectory of category X". Returns current category AUM and absolute + percentage change across standard windows: 1m/3m/6m/1y/2y. AUM change includes both flows AND market performance — for ETF-heavy categories it conflates investor flows with NAV moves. Cleanest flow signal for stable-NAV categories like money-market and short-bond.
get_category_competitors
ChatGPTManagers competing in one TASE classification — who has share, fees, AUM. Use this to answer "who competes in [category]", "who is the largest provider of TA-125 trackers", "what does the bond fund landscape look like". Complements get_market_by_category (which enumerates categories) by drilling into one category's competitive structure.
get_category_competitors
ChatGPTManagers competing in one TASE classification — who has share, fees, AUM. Use this to answer "who competes in [category]", "who is the largest provider of TA-125 trackers", "what does the bond fund landscape look like". Complements get_market_by_category (which enumerates categories) by drilling into one category's competitive structure.
get_category_metrics_summary
ChatGPTAggregate risk/return summary across a TASE classification. Use this to answer "what's the average return / Sharpe / volatility for [category]" — useful as a benchmark when evaluating an individual fund. Reads from the precomputed fund_metrics table (fast).
get_category_metrics_summary
ChatGPTAggregate risk/return summary across a TASE classification. Use this to answer "what's the average return / Sharpe / volatility for [category]" — useful as a benchmark when evaluating an individual fund. Reads from the precomputed fund_metrics table (fast).
get_category_performance
ChatGPTPeriod total return for one TASE classification — performance attribution. Use this to answer "how did Israeli bonds do this month", "what's the YTD performance of category X". Computed as the simple (unweighted) mean of per-fund returns over the window — each fund counts once, regardless of its AUM. This is the right frame for "what did the typical fund in this category do" and for comparing individual fund choices; it is NOT money-weighted, so it differs from how a cap-weighted index would behave when a few large funds dominate AUM. Complement to get_category_aum_growth (which tracks size, not performance).
get_category_performance
ChatGPTPeriod total return for one TASE classification — performance attribution. Use this to answer "how did Israeli bonds do this month", "what's the YTD performance of category X". Computed as the simple (unweighted) mean of per-fund returns over the window — each fund counts once, regardless of its AUM. This is the right frame for "what did the typical fund in this category do" and for comparing individual fund choices; it is NOT money-weighted, so it differs from how a cap-weighted index would behave when a few large funds dominate AUM. Complement to get_category_aum_growth (which tracks size, not performance).
get_curated_category
ChatGPTDrill into one curated category — the slug-keyed theme card. Returns the category metadata plus the full fund membership list with per-fund detail (name, manager, AUM, fees, classification). Use after list_curated_categories to inspect a specific theme.
get_curated_category
ChatGPTDrill into one curated category — the slug-keyed theme card. Returns the category metadata plus the full fund membership list with per-fund detail (name, manager, AUM, fees, classification). Use after list_curated_categories to inspect a specific theme.
get_data_points
ChatGPTFlat list of every quoted numerical fact (rates, yields, CPI, FX, index levels) extracted from the corpus, with source attribution. Use to ground claims in actual numbers: never assert a rate value or market level without anchoring it to a quoted data point.
get_data_points
ChatGPTFlat list of every quoted numerical fact (rates, yields, CPI, FX, index levels) extracted from the corpus, with source attribution. Use to ground claims in actual numbers: never assert a rate value or market level without anchoring it to a quoted data point.
get_documents_by_source
ChatGPTAll documents from a single source within the window — for single-voice deep-dives (e.g., all of Modi Shafrir's posts to verify a framework before quoting).
get_documents_by_source
ChatGPTAll documents from a single source within the window — for single-voice deep-dives (e.g., all of Modi Shafrir's posts to verify a framework before quoting).
get_filter_vocabulary
ChatGPTCanonical filter tag vocabulary used across search and listing tools. Returns the full enumeration of valid theme / strategy / region / geo-theme tags, each with English canonical key and Hebrew display label. Use this for self-discovery: before filtering or interpreting results, call this once to know which values are valid for theme_tags / strategy_tags / geography_tags etc. Returns: Dict mapping each dimension to its allowed values: { "theme": [{en: "defense", he: "ביטחון"}, ...], "strategy": [...], "geography": [...], "geo_theme": [...] }.
get_filter_vocabulary
ChatGPTCanonical filter tag vocabulary used across search and listing tools. Returns the full enumeration of valid theme / strategy / region / geo-theme tags, each with English canonical key and Hebrew display label. Use this for self-discovery: before filtering or interpreting results, call this once to know which values are valid for theme_tags / strategy_tags / geography_tags etc. Returns: Dict mapping each dimension to its allowed values: { "theme": [{en: "defense", he: "ביטחון"}, ...], "strategy": [...], "geography": [...], "geo_theme": [...] }.
get_fund_manager_profile
ChatGPTGet a comprehensive profile for one fund manager. Includes: fund count, total AUM, type split, fee stats, category breakdown with market share per category, and top funds by AUM. Use list_managers first to find the manager_id.
get_fund_manager_profile
ChatGPTGet a comprehensive profile for one fund manager. Includes: fund count, total AUM, type split, fee stats, category breakdown with market share per category, and top funds by AUM. Use list_managers first to find the manager_id.
get_fund_metrics
ChatGPTGet comprehensive performance and risk metrics for a specific fund. Includes total returns (MTD through 5Y), annualized returns (CAGR), and risk metrics: volatility, Sharpe ratio, Sortino ratio, VaR, CVaR, and max drawdown with dates.
get_fund_metrics
ChatGPTGet comprehensive performance and risk metrics for a specific fund. Includes total returns (MTD through 5Y), annualized returns (CAGR), and risk metrics: volatility, Sharpe ratio, Sortino ratio, VaR, CVaR, and max drawdown with dates.
get_fund_profile_card
ChatGPTFull profile for one fund — details + 1Y return & Sharpe — rendered as a card.
get_fund_profile_card
ChatGPTFull profile for one fund — details + 1Y return & Sharpe — rendered as a card.
get_intelligence_documents
ChatGPTFilterable document pull with full enrichment (summary, tags, sentiment, key_data_points, markets, asset_types, relevance). Replaces the snippet-only RAG pattern: instead of search → snippets, query give me last 14 days of high-relevance docs from research sources where bonds sentiment is bearish.
get_intelligence_documents
ChatGPTFilterable document pull with full enrichment (summary, tags, sentiment, key_data_points, markets, asset_types, relevance). Replaces the snippet-only RAG pattern: instead of search → snippets, query give me last 14 days of high-relevance docs from research sources where bonds sentiment is bearish.
get_manager_aum_growth
ChatGPTAUM growth scorecard for one fund manager — asset-gathering performance. Use this to answer "is X gaining assets", "who is bleeding AUM", "rank managers by recent asset growth". Returns the manager's current total AUM plus absolute + percentage change across standard windows: 1m/3m/6m/1y/2y. AUM change includes both flows AND market performance — a manager whose book is mostly ETFs will see "growth" partly from market moves on their existing assets, not just new investor money. For pure-flow signal, interpret carefully against the manager's fund-type mix (see get_manager_overview.funds_by_type).
get_manager_aum_growth
ChatGPTAUM growth scorecard for one fund manager — asset-gathering performance. Use this to answer "is X gaining assets", "who is bleeding AUM", "rank managers by recent asset growth". Returns the manager's current total AUM plus absolute + percentage change across standard windows: 1m/3m/6m/1y/2y. AUM change includes both flows AND market performance — a manager whose book is mostly ETFs will see "growth" partly from market moves on their existing assets, not just new investor money. For pure-flow signal, interpret carefully against the manager's fund-type mix (see get_manager_overview.funds_by_type).
get_manager_performance
ChatGPTPeriod total return for one fund manager across their fund book. Use this to answer "how did [manager] do recently", "is X outperforming", "rank managers by recent performance". Computed as the simple (unweighted) mean of per-fund returns across all of the manager's funds — each fund counts once, regardless of AUM. NOT money-weighted. Pair with get_manager_aum_growth for size-vs-performance picture.
get_manager_performance
ChatGPTPeriod total return for one fund manager across their fund book. Use this to answer "how did [manager] do recently", "is X outperforming", "rank managers by recent performance". Computed as the simple (unweighted) mean of per-fund returns across all of the manager's funds — each fund counts once, regardless of AUM. NOT money-weighted. Pair with get_manager_aum_growth for size-vs-performance picture.
get_market_by_category
ChatGPTAll TASE classification categories ranked by total AUM. Use this to enumerate the classification space and see how AUM is distributed across asset categories — useful when you don't yet know which specific category to drill into. Returns: List of {category, fund_count, total_aum} ranked by AUM descending. Categories are the canonical Hebrew TASE classification main values (e.g. 'מניות בארץ', 'אג"ח חברות והמרה', 'קרן כספית').
get_market_by_category
ChatGPTAll TASE classification categories ranked by total AUM. Use this to enumerate the classification space and see how AUM is distributed across asset categories — useful when you don't yet know which specific category to drill into. Returns: List of {category, fund_count, total_aum} ranked by AUM descending. Categories are the canonical Hebrew TASE classification main values (e.g. 'מניות בארץ', 'אג"ח חברות והמרה', 'קרן כספית').
get_market_fees
ChatGPTFee positioning per fund manager — how cheap or expensive each manager is. Returns aggregate fee statistics (avg / min / max management fee, avg trustee fee) for every manager, optionally narrowed to one classification. Use this to find the cheapest provider in a category or compare fee discipline across managers.
get_market_fees
ChatGPTFee positioning per fund manager — how cheap or expensive each manager is. Returns aggregate fee statistics (avg / min / max management fee, avg trustee fee) for every manager, optionally narrowed to one classification. Use this to find the cheapest provider in a category or compare fee discipline across managers.
get_market_news
ChatGPTGet the latest market context cards — Hebrew market insights generated by the Superfunds news agent. Each card covers a market signal (bonds, equities, rates, macro, etc.) with an original Hebrew headline, summary, and linked fund IDs for comparison.
get_market_news
ChatGPTGet the latest market context cards — Hebrew market insights generated by the Superfunds news agent. Each card covers a market signal (bonds, equities, rates, macro, etc.) with an original Hebrew headline, summary, and linked fund IDs for comparison.
get_market_overview
ChatGPTTop-level snapshot of the Israeli mutual fund market. Use this to answer "how big is the market", "how many funds exist", "what's the manager / fund-type composition". A starting point before drilling into managers, categories, or specific funds. Returns: Dict with manager_count, fund_count, total_aum (₪), and a funds_by_type mapping (e.g. {"קרן מחקה": 812, "קרן נאמנות": ...}).
get_market_overview
ChatGPTTop-level snapshot of the Israeli mutual fund market. Use this to answer "how big is the market", "how many funds exist", "what's the manager / fund-type composition". A starting point before drilling into managers, categories, or specific funds. Returns: Dict with manager_count, fund_count, total_aum (₪), and a funds_by_type mapping (e.g. {"קרן מחקה": 812, "קרן נאמנות": ...}).
get_market_trending_funds
ChatGPTFunds with the largest AUM movement (inflows or outflows) over a window. Use this to answer "what's hot", "where is money flowing", "which funds are bleeding assets". Movement is measured as % AUM change between the start and end of the window.
get_market_trending_funds
ChatGPTFunds with the largest AUM movement (inflows or outflows) over a window. Use this to answer "what's hot", "where is money flowing", "which funds are bleeding assets". Movement is measured as % AUM change between the start and end of the window.
list_curated_categories
ChatGPTList all curated category cards — themed fund collections. These are editorially-curated themes (e.g. "Israeli AI exposure", "long-duration bonds", "manager flagships") with hand-picked or rule-based fund membership. Different from get_market_by_category, which enumerates the raw TASE classification tree. Use this when the user asks about themes / topics / "show me funds about X". Returns: Dict with categories: [{slug, title_he, title_en, subtitle_he, category_group, member_count, fund_type_dominant, asset_class_major, geography, tags, is_leveraged, is_kosher, display_order, refreshed_at, fund_ids}], plus a fund_lookup map for the union of all member funds.
list_curated_categories
ChatGPTList all curated category cards — themed fund collections. These are editorially-curated themes (e.g. "Israeli AI exposure", "long-duration bonds", "manager flagships") with hand-picked or rule-based fund membership. Different from get_market_by_category, which enumerates the raw TASE classification tree. Use this when the user asks about themes / topics / "show me funds about X". Returns: Dict with categories: [{slug, title_he, title_en, subtitle_he, category_group, member_count, fund_type_dominant, asset_class_major, geography, tags, is_leveraged, is_kosher, display_order, refreshed_at, fund_ids}], plus a fund_lookup map for the union of all member funds.
list_intelligence_sources
ChatGPTList the intelligence sources catalog with freshness signals. Use this to orient at the start of a research session — see what sources exist, their cadence, and whether any have gone stale (last_doc_date well past expected cadence may indicate scraper issues or meaningful publishing absence).
list_intelligence_sources
ChatGPTList the intelligence sources catalog with freshness signals. Use this to orient at the start of a research session — see what sources exist, their cadence, and whether any have gone stale (last_doc_date well past expected cadence may indicate scraper issues or meaningful publishing absence).
list_managers
ChatGPTList all Israeli mutual fund managers with their market position. Returns each manager's fund count, total AUM, and market share percentage. Use this to discover managers before diving into a specific manager's profile. Returns: All managers ranked by AUM with fund count and market share.
list_managers
ChatGPTList all Israeli mutual fund managers with their market position. Returns each manager's fund count, total AUM, and market share percentage. Use this to discover managers before diving into a specific manager's profile. Returns: All managers ranked by AUM with fund count and market share.
list_recently_launched_funds
ChatGPTList Israeli mutual funds that were recently announced (ק131 prospectus). Use this to answer "what new funds launched recently" questions, surface launch trends by manager or category, or pull a Hebrew description of a just-announced fund. Each row is a NEW-FUND ANNOUNCEMENT, not a live trading fund — these may not yet appear in query_funds results.
list_recently_launched_funds
ChatGPTList Israeli mutual funds that were recently announced (ק131 prospectus). Use this to answer "what new funds launched recently" questions, surface launch trends by manager or category, or pull a Hebrew description of a just-announced fund. Each row is a NEW-FUND ANNOUNCEMENT, not a live trading fund — these may not yet appear in query_funds results.
query_fund_details
ChatGPTFetch detailed information for a specific mutual fund. Includes metadata, classification, exposure profile, and latest AUM.
query_fund_details
ChatGPTFetch detailed information for a specific mutual fund. Includes metadata, classification, exposure profile, and latest AUM.
query_fund_eod
ChatGPTFetch EOD price and NAV history for a mutual fund.
query_fund_eod
ChatGPTFetch EOD price and NAV history for a mutual fund.
query_funds
ChatGPTSearch and filter the Israeli mutual fund universe. STRUCTURED filter by exact fields (type, manager, classification, name, ISIN). For free-text/thematic queries ("defense", "leveraged Nasdaq", Hebrew questions) use search_funds_flex instead — it understands themes; this tool does not. For ranking by performance use compare_funds_by_metric. Use isin=... to resolve an ISIN to a fund_id (other tools like find_similar require numeric fund_id). Always returns: fund_id, name, fund_type, manager_name, management_fee, isin, classification (main/major/secondary), latest_aum, latest_aum_date, inception_date. Opt-in enrichments (each adds one extra query, off by default): - include_returns: total period returns 1M / 3M / 6M / YTD / 1Y / 3Y / 5Y (computed from sellPrice; None when history is insufficient). - include_indices: tracked_indices[] with index_name, index_provider, index_ticker, index_isin, index_methodology_url. Use this to know which benchmark each fund tracks. - include_reports: fund_report_url — canonical fund document URL (priority report first, otherwise most recent by publishDate). - include_descriptions: long_name (full Hebrew name) and description_he (LLM-generated Hebrew fund summary). - include_tags: classification tags from fund_search_index — geography_tags, theme_tags, strategy_tags (canonical kebab-case), asset_class, asset_class_major, currency_denom, is_leveraged, is_kosher, is_irish.
query_funds
ChatGPTSearch and filter the Israeli mutual fund universe. STRUCTURED filter by exact fields (type, manager, classification, name, ISIN). For free-text/thematic queries ("defense", "leveraged Nasdaq", Hebrew questions) use search_funds_flex instead — it understands themes; this tool does not. For ranking by performance use compare_funds_by_metric. Use isin=... to resolve an ISIN to a fund_id (other tools like find_similar require numeric fund_id). Filter by tracked benchmark index with index_provider / index_ticker / index_name_contains — e.g. all funds tracking the iNDEX "Israeli Banks" index: index_provider="iNDEX", index_ticker="2141". provider and ticker match case-insensitively and exactly; index_name_contains is a case-insensitive substring. All index conditions must hold on the same tracked-index row; funds tracking multiple indices are not duplicated. Pair with include_indices=True to see the matched benchmark. Always returns: fund_id, name, fund_type, manager_name, management_fee, isin, classification (main/major/secondary), latest_aum, latest_aum_date, inception_date. Opt-in enrichments (each adds one extra query, off by default): - include_returns: total period returns 1M / 3M / 6M / YTD / 1Y / 3Y / 5Y (computed from sellPrice; None when history is insufficient). - include_indices: tracked_indices[] with index_name, index_provider, index_ticker, index_isin, index_methodology_url. Use this to know which benchmark each fund tracks. - include_reports: fund_report_url — canonical fund document URL (priority report first, otherwise most recent by publishDate). - include_descriptions: long_name (full Hebrew name) and description_he (LLM-generated Hebrew fund summary). - include_tags: classification tags from fund_search_index — geography_tags, theme_tags, strategy_tags (canonical kebab-case), asset_class, asset_class_major, currency_denom, is_leveraged, is_kosher, is_irish.
query_funds_aum_bulk
ChatGPTFetch full daily per-fund AUM curves for many funds in one call. Use this ONLY when you need the full daily series — drawing AUM line charts, anomaly/inflection detection, intraperiod analysis. For computing deltas at fixed cutoffs (3M / 6M / 1Y / YTD changes), use query_funds_aum_snapshot instead — it returns ~180x less data and is the right tool for that job.
query_funds_aum_bulk
ChatGPTFetch full daily per-fund AUM curves for many funds in one call. Use this ONLY when you need the full daily series — drawing AUM line charts, anomaly/inflection detection, intraperiod analysis. For computing deltas at fixed cutoffs (3M / 6M / 1Y / YTD changes), use query_funds_aum_snapshot instead — it returns ~180x less data and is the right tool for that job.
query_funds_aum_snapshot
ChatGPTPer-fund AUM at fixed cutoffs — cheap, targeted alternative to bulk. For each requested cutoff label, returns the latest reported assetValue on-or-before that date for every fund_id. Use for "AUM 3M ago / 1Y ago / YTD" style snapshots — typical input for delta tables and ranking queries. ~180x cheaper than query_funds_aum_bulk for this use case. Cutoff labels accepted (mix freely): - "latest" — latest available (no upper bound) - "ytd" — Jan 1 of current year - "mtd" — first day of current month - "-Nd" — N calendar days before today (e.g. "-90d", "-1095d") - ISO date string — "YYYY-MM-DD" (e.g. "2025-11-01")
query_funds_aum_snapshot
ChatGPTPer-fund AUM at fixed cutoffs — cheap, targeted alternative to bulk. For each requested cutoff label, returns the latest reported assetValue on-or-before that date for every fund_id. Use for "AUM 3M ago / 1Y ago / YTD" style snapshots — typical input for delta tables and ranking queries. ~180x cheaper than query_funds_aum_bulk for this use case. Cutoff labels accepted (mix freely): - "latest" — latest available (no upper bound) - "ytd" — Jan 1 of current year - "mtd" — first day of current month - "-Nd" — N calendar days before today (e.g. "-90d", "-1095d") - ISO date string — "YYYY-MM-DD" (e.g. "2025-11-01")
resolve_category
ChatGPTResolve a category by slug to its current member fund_ids. For SQL-pure categories (category_type='sql'), runs the deterministic filter live and returns fresh fund_ids (always up-to-date with the current fund universe). For dynamic categories (category_type='dynamic'), returns the cached fund_ids from the last build run. Use this to answer 'who is currently in category X?' without needing to list the full /categories endpoint.
resolve_category
ChatGPTResolve a category by slug to its current member fund_ids. For SQL-pure categories (category_type='sql'), runs the deterministic filter live and returns fresh fund_ids (always up-to-date with the current fund universe). For dynamic categories (category_type='dynamic'), returns the cached fund_ids from the last build run. Use this to answer 'who is currently in category X?' without needing to list the full /categories endpoint.
search_funds_flex
ChatGPTFlexible natural-language search over the Israeli mutual fund market. Accepts a single free-text query (Hebrew or English) and returns ranked matching funds with enum attributes. Uses hybrid retrieval (BM25 + semantic + reranker) over LLM-generated English fund cards. Understood filter dimensions (extracted automatically from the query): - fund_type: mutual / tracking / etf / foreign-etf - manager, asset_class_major, currency_denom - is_leveraged, is_kosher, is_irish - theme: defense, cyber, healthcare, technology, green-energy, financials, banks, digital-assets, bitcoin, etc. - strategy: leveraged, inverse, large-cap, blend, value, growth, target-maturity, bullet, investment-grade, esg, etc. - geography: country code (US/IL/JP), region (Asia/Europe), or theme (emerging/developed/global) For numeric filters (fee, AUM, returns) or sorting, compose with the existing query_fund_eod / get_fund_metrics / compare_funds_by_metric tools on the returned fund_ids.
search_funds_flex
ChatGPTFlexible natural-language search over the Israeli mutual fund market. Accepts a single free-text query (Hebrew or English) and returns ranked matching funds with enum attributes. Uses hybrid retrieval (BM25 + semantic + reranker) over LLM-generated English fund cards. Understood filter dimensions (extracted automatically from the query): - fund_type: mutual / tracking / etf / foreign-etf - manager, asset_class_major, currency_denom - is_leveraged, is_kosher, is_irish - theme: defense, cyber, healthcare, technology, green-energy, financials, banks, digital-assets, bitcoin, etc. - strategy: leveraged, inverse, large-cap, blend, value, growth, target-maturity, bullet, investment-grade, esg, etc. - geography: country code (US/IL/JP), region (Asia/Europe), or theme (emerging/developed/global) For numeric filters (fee, AUM, returns) or sorting, compose with the existing query_fund_eod / get_fund_metrics / compare_funds_by_metric tools on the returned fund_ids.
search_market_intelligence
ChatGPTSearch Israeli market RESEARCH — research reports, analyst notes, central bank publications. Supports English and Hebrew queries. Use this for opinions, commentary, and analysis ABOUT the market — NOT for finding specific funds. To find actual funds, use search_funds_flex or query_funds instead. Uses hybrid retrieval (BM25 + semantic + reranker) over enriched topic-segmented chunks from multiple research sources.
search_market_intelligence
ChatGPTSearch Israeli market RESEARCH — research reports, analyst notes, central bank publications. Supports English and Hebrew queries. Use this for opinions, commentary, and analysis ABOUT the market — NOT for finding specific funds. To find actual funds, use search_funds_flex or query_funds instead. Uses hybrid retrieval (BM25 + semantic + reranker) over enriched topic-segmented chunks from multiple research sources.
