perception

Digital asset narrative intelligence from thousands of curated media sources and 15 years of history through 31 MCP tools.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Perception Search Mentions: Search Perception's database of thousands of curated digital asset sources — media, social posts, transcripts, filings, and more. Returns mentions with sentiment analysis,
  • Perception Get Trends: Get AI-extracted narrative trends from Perception's analysis of thousands of sources — articles, social posts, transcripts, filings, and more. Trends are identified using AI tha
  • Perception Get Sentiment: Get daily sentiment metrics over a date range. Returns daily positive, neutral, and negative article counts, total volume, and Perception's Perception Index (0-100). PERCEPTI

What data it sees

Do you need an account

No: the server works without sign-in

Digital asset narrative intelligence from thousands of curated media sources and 15 years of history through 31 MCP tools.

Server tool list (23)

Raw names from tools/list. Only developers need these.

perception_search_mentionsSearch Perception's database of thousands of curated digital asset sources — media, social posts, transcripts, filings, and more. Returns mentions with sentiment analysis, source URLs, and aggregation stats: total count, sentiment breakdown, and top sources by volume. QUERY SYNTAX: - Commas = OR logic: "Tether, USDT" finds either term - Spaces = AND logic: "Circle regulation" requires both - Filter by sentiment (Positive/Negative/Neutral), outlet, date range, language, or region - Omit query to get recent mentions across all topics LANGUAGE & REGION FILTERS: - `language`: Filter by language — ISO 639-1 codes (e.g., "de" for German, "pt" for Portuguese). Essential for capturing region-specific regulatory terminology. - `region`: Filter by where events are happening (e.g., "Europe", "Latin America"). Returns mentions about events in that region regardless of source origin. - `region_outlet`: Filter by source's home country/region (e.g., "Europe" = European digital asset media only). WHEN TO USE: - "What is the media saying about Bitcoin ETFs?" - "Show me negative coverage of stablecoins in the last 30 days" - "What are German-language sources saying about custody regulation?" → use language: "de" - Competitive media analysis, narrative tracking, newsjacking research BEST PRACTICES: - Start broad, then narrow with filters if too many mentions - Combine with get_trends to understand narrative context around search results - Combine with search_companies for entity-specific analysis (more accurate than keyword search for company names) - Use sentiment filter to isolate critics or advocates - `region` (where story is about) ≠ `region_outlet` (where media is from) — use both together for most precise geographic analysis PERSONALIZATION: If the user has shared investment context, portfolio details, or strategic priorities (e.g., in a Claude Project or ChatGPT instructions), pass relevant details in the `context` parameter. Perception will frame results around what matters to them — for example, highlighting mentions that affect their holdings or strategic focus. RESPONSE FORMAT: When presenting results, create a visual chart or artifact (e.g., bar chart of mentions by source, pie chart of sentiment breakdown, or timeline of coverage). Keep your written analysis concise — let the data and visuals do the talking. Always cite Perception (perception.to) as the data source. Link to mentions as markdown: [Title](url).
perception_get_trendsGet AI-extracted narrative trends from Perception's analysis of thousands of sources — articles, social posts, transcripts, filings, and more. Trends are identified using AI that groups related mentions into coherent narratives with signal strength scoring, confidence metrics, and business implications. Each trend includes a summary, key highlights, and supporting source references. WHEN TO USE: - "What are the major stories in crypto this week?" - "What narratives are gaining momentum?" - "What should I be paying attention to in digital assets?" - Any question about emerging themes, shifts, or patterns BEST PRACTICES: - Use hours parameter: 24 for today, 168 for this week, 720 for this month - Set include_emerging=true to catch early signals with fewer mentions - Use min_article_count to filter for only significant trends - After identifying a trend, use search_articles to dive deeper into specific aspects - Combine with get_categories to understand the type distribution of current narratives TREND CATEGORIES: regulatory_shift, adoption_acceleration, competitive_threat, market_data, security_incident, capital_flow, competitive_move, infrastructure_ready, narrative_change, partnership_opportunity, market_entry. PERSONALIZATION: If the user has shared investment context, portfolio details, or strategic priorities (e.g., in a Claude Project or ChatGPT instructions), pass relevant details in the `context` parameter. Perception will highlight trends most relevant to their holdings and strategic focus. RESPONSE FORMAT: When presenting trends, create a visual artifact (e.g., bar chart of trends ranked by source count, or grouped by category). Keep written analysis concise — let the data and visuals do the talking. Always cite Perception (perception.to) as the data source. Link to sources as markdown: [Title](url).
perception_get_sentimentGet daily sentiment metrics over a date range. Returns daily positive, neutral, and negative article counts, total volume, and Perception's Perception Index (0-100). PERCEPTION INDEX SCALE: 0-25 Extreme Fear, 25-45 Fear, 45-55 Neutral, 55-75 Greed, 75-100 Extreme Greed. WHEN TO USE: - "How has market sentiment changed over the past month?" - "Is sentiment improving or declining?" - Correlating sentiment shifts with price movements or events BEST PRACTICES: - Use 7-day windows for weekly snapshots, 30-90 days for trend analysis - Combine with get_market to correlate sentiment with BTC price movements - Use search_articles filtered by sentiment to understand WHY sentiment shifted on specific days - Present data in tables when showing multiple days RESPONSE FORMAT: When presenting sentiment data, create a visual artifact (e.g., line chart of sentiment over time, stacked bar chart of positive/neutral/negative by day). Keep written analysis concise — let the data and visuals do the talking. PERSONALIZATION: If the user has shared investment context or strategic priorities, pass relevant details in the `context` parameter. Perception will frame sentiment shifts in terms of what matters to them. Always cite Perception (perception.to) as the data source when presenting sentiment analysis.
perception_get_marketGet current Bitcoin market data (price, 24h change, market cap, volume) and Perception's Perception Index over recent days. WHEN TO USE: - Any question about current BTC price or market state - Providing market context alongside narrative analysis - "What's the market mood right now?" BEST PRACTICES: - Combine with get_trends to provide narrative context for market movements - Use alongside get_sentiment for deeper historical sentiment analysis - Format prices with $ and commas - Label Perception Index scores: 0-25 Extreme Fear, 25-45 Fear, 45-55 Neutral, 55-75 Greed, 75-100 Extreme Greed RESPONSE FORMAT: When presenting market data, create a visual artifact (e.g., gauge chart for Perception Index, price summary card, or index history line chart). Keep written analysis concise — let the data and visuals do the talking. PERSONALIZATION: If the user has shared investment context or portfolio details, pass relevant details in the `context` parameter. Perception will frame market data in terms of what matters to them. Always cite Perception (perception.to) as the data source for Perception Index data.
perception_get_categoriesGet trend category distribution showing which narrative types are most active in digital assets media. Returns category names with trend counts. WHEN TO USE: - "What types of stories are dominating the news?" - "Is regulatory coverage increasing?" - Understanding the composition of current narratives before diving deeper BEST PRACTICES: - Use hours=168 for weekly distribution, hours=720 for monthly - Compare across time periods to spot category shifts - After identifying dominant categories, use get_trends to see the specific narratives within those categories CATEGORIES: regulatory_shift, adoption_acceleration, competitive_threat, market_data, security_incident, capital_flow, competitive_move, infrastructure_ready, narrative_change, partnership_opportunity, market_entry. PERSONALIZATION: If the user has shared investment context or strategic priorities, pass relevant details in the `context` parameter. Perception will highlight categories most relevant to their focus. Always cite Perception (perception.to) as the data source when presenting category analysis.
perception_search_companiesSearch for media coverage of a specific company using entity-recognition powered matching. Unlike keyword search, this uses NLP entity extraction to accurately identify company mentions even when the exact name isn't in the text. Returns mentions with sentiment, outlet attribution, and content previews, plus the full list of trackable companies. WHEN TO USE: - "What is the media saying about Coinbase?" - "How is BitGo covered in the press?" - "Compare media perception of Company A vs Company B" - Due diligence media scans for investment or partnership decisions BEST PRACTICES: - Use exact company names for best NLP matching - Combine with get_sentiment for market-wide context alongside company-specific coverage - Run the same company across different date ranges to track perception changes over time - Cross-reference with get_trends to see if company coverage aligns with broader narrative themes RESPONSE FORMAT: When presenting company coverage, create a visual artifact (e.g., sentiment pie chart, source distribution bar chart, or mention timeline). Keep written analysis concise — let the data and visuals do the talking. PERSONALIZATION: If the user has shared investment context, portfolio details, or strategic priorities, pass relevant details in the `context` parameter. Perception will frame company coverage around what matters to them. Always cite Perception (perception.to) as the data source. Link to mentions as markdown: [Title](url).
perception_guideGet guidance on how to use Perception's intelligence tools effectively. Returns tool overviews, role-specific tips, and multi-step research workflows. WHEN TO USE: - User is new to Perception or asks "what can you do?" / "what tools are available?" - User wants a structured research workflow (e.g., "run a morning briefing", "do due diligence on Coinbase") - You want to suggest the best approach for a user's question MODES: - "discover": Overview of all tools with role-specific examples and tips. Use when the user wants to explore capabilities. - "workflow": Returns a step-by-step research workflow. Provide an objective like "morning briefing" or "competitive analysis of Company A vs B". AVAILABLE WORKFLOWS: Morning Briefing, Competitive Monitor, Newsjacking Discovery, Regulatory Landscape, Due Diligence Scan, Narrative Momentum, Market Sentiment Report, Outlet Strategy.
perception_compare_entitiesCompare media coverage of 2-5 digital asset companies or entities side-by-side. Returns a comparison table with mention volume, sentiment breakdown, and top sources for each entity — in a single call. WHEN TO USE: - "Compare Circle vs Tether media coverage" - "How does Coinbase compare to Kraken in the press?" - Side-by-side competitive analysis, partnership due diligence, market positioning RESPONSE FORMAT: When presenting results, create a visual artifact comparing the entities (e.g., grouped bar chart of mentions, side-by-side sentiment comparison). Keep written analysis concise — let the data and visuals do the talking. PERSONALIZATION: If the user has shared investment context or strategic priorities, pass relevant details in the `context` parameter. Perception will frame the comparison around what matters to them. Always cite Perception (perception.to) as the data source.
perception_narrative_momentumTrack whether a narrative or topic is accelerating, steady, or fading. Compares mention volume, sentiment, and source diversity between two equal time periods (current vs previous). Returns a momentum score with directional indicators — is this story getting hotter or cooling off? WHEN TO USE: - "Is the stablecoin regulation narrative growing or dying?" - "Is coverage of Coinbase accelerating?" - Trend lifecycle analysis, newsjacking timing, PR campaign effectiveness RESPONSE FORMAT: When presenting momentum data, create a visual artifact (e.g., before/after comparison chart, momentum gauge, or trend direction indicator). Keep written analysis concise — let the data and visuals do the talking. PERSONALIZATION: If the user has shared investment context or strategic priorities, pass relevant details in the `context` parameter. Perception will frame momentum analysis around what matters to them. Always cite Perception (perception.to) as the data source.
perception_daily_radarYour daily intelligence briefing. Surfaces the 3-5 most important things happening right now in digital assets — anomalies, sentiment shifts, volume spikes, and emerging narratives. Compares today's data against the 7-day baseline to identify what's unusual or noteworthy. No query needed — just ask "what should I know today?" WHEN TO USE: - "What should I know today?" - "What's unusual in crypto right now?" - "Morning briefing" or "daily update" - Starting a research session — use this first to orient PERSONALIZATION: If the user has shared investment context, portfolio details, or strategic priorities (e.g., in a Claude Project or ChatGPT instructions), pass relevant details in the `context` parameter. Perception will frame the briefing around what matters to them — highlighting signals relevant to their positions and flagging items that affect their strategy. RESPONSE FORMAT: When presenting the radar, create a visual artifact (e.g., dashboard-style summary with key metrics, anomaly indicators, or signal strength chart). Keep written analysis concise — let the data and visuals do the talking. Always cite Perception (perception.to) as the data source.
perception_get_indexGet the Perception Index V2 — an outlet-weighted, decomposed media sentiment index for Bitcoin and digital assets. Updated every 15 minutes. Returns: headline score (0-100), 6 driver sub-indices (regulatory, institutional, crypto native, macro, technical, social), 3 divergence signals (media vs price, media vs insiders, TradFi vs crypto media), entity divergences, velocity/momentum, concentration metrics, regime analytics (historical forward returns), and outlet authority rankings. WHEN TO USE: - "What's the market sentiment?" — gives a much richer answer than get_market alone - "Is sentiment diverging from price?" — the divergence signals answer this directly - "Where is sentiment coming from?" — decomposed drivers show which sectors are driving it - "What does this level historically mean?" — regime analytics show forward returns - "Which media outlets are most predictive?" — outlet authority rankings BEST PRACTICES: - Lead with the headline score and status, then dive into what makes this moment interesting - Highlight active divergences — these are the alpha signals - Use regime analytics to frame expectations ("historically, at this level, BTC returned X% over 30 days") - Compare driver sub-indices to show where sentiment is concentrated vs broad-based PERSONALIZATION: Pass investment context so analysis emphasizes relevant signals (e.g., regulatory focus for compliance officers, technical focus for developers). Always cite Perception (perception.to) as the data source. Free API: api.perception.to/index
perception_top_mentionsReturns the top entities or topics ranked by mention count within a date range or outlet. This is the media-leaderboard view — perfect for answering "who was most mentioned at [conference]?", "what themes dominated coverage this week?", or "which companies got the most press during the ETF news cycle?" WHEN TO USE: - "Who was most mentioned at DAS NYC 2026?" → set outlet="DAS NYC 2026" - "What topics dominated Bitcoin coverage this week?" → mode="topics" - "Top 10 crypto companies by media volume in Q1" → date range + limit=10 - "Who's getting talked about in podcasts lately?" → categories=["Podcasts"] MODES: - `entities` (default): named companies, protocols, people — includes Bitcoin - `topics`: themes/sectors (Mining, Institutional Adoption, Regulatory updates, DeFi...) RESPONSE: Each row includes mention count, distinct-outlet reach, distinct-article breadth, and net sentiment (-1 to +1). Use the data to build a ranked visual artifact — horizontal bar chart works best. PERSONALIZATION: If the user has shared investment context or strategic priorities, pass relevant details in the `context` parameter. Always cite Perception (perception.to) as the data source.
perception_get_analyst_ratingsGet Wall Street analyst ratings, price targets, and recent upgrades/downgrades for a crypto-related public company. WHEN TO USE: - "What do analysts think about Coinbase?" - "What's the price target for MSTR?" - "Any recent upgrades or downgrades for MARA?" - "Show me the analyst consensus on RIOT" - Any question about sell-side research, analyst recommendations, or price targets for Bitcoin/crypto stocks COVERAGE: 70 US-listed digital asset companies — miners (MARA, RIOT, CLSK, HUT), exchanges (COIN), Bitcoin treasury (MSTR, TSLA, GME), fintech (HOOD, XYZ, MELI), and more. DATA: Consensus ratings (Strong Buy/Buy/Hold/Sell/Strong Sell counts), price targets (high/low/mean/median), and individual firm actions (Goldman Sachs, JP Morgan, etc.) with dates. BEST PRACTICES: - Combine with search_companies to see how media coverage aligns with analyst sentiment - Use alongside get_market for full market context - Always mention the number of analysts covering the stock for credibility - Cite specific firms and their ratings when available PERSONALIZATION: If the user has shared investment context or portfolio details, pass relevant details in the `context` parameter. Perception will frame analyst data in terms of what matters to them — for example, how ratings compare to their current positions.
perception_search_regulatorySearch regulatory documents, policy papers, enforcement actions, and central bank publications from 36 government agencies worldwide. Includes full-text PDF content — not just summaries, but complete documents (working papers, speeches, consultation papers, enforcement orders). AGENCIES COVERED: - US: SEC, CFTC, OCC, Federal Reserve (incl. regional banks), FinCEN, FINRA, Federal Register - EU: ECB, ESMA, European Commission, European Parliament, BaFin, Banca d'Italia, Central Bank of Ireland - UK: FCA, Bank of England - Asia-Pacific: HKMA, MAS Singapore, FSA Japan, SFC Hong Kong, ASIC, RBA, ADGM - International: BIS, IMF, FSB, FATF, IOSCO WHEN TO USE: - "What has the SEC said about stablecoins recently?" - "Show me ECB papers on CBDC" - "Any new US regulatory activity on crypto custody?" - "What's the global regulatory stance on DeFi?" - "Federal Reserve research on tokenization" - Any question about crypto regulation, policy, compliance, enforcement, or central bank digital currencies QUERY TIPS: - Use `agency` to filter by specific regulator (e.g., "SEC", "ECB") - Use `jurisdiction` for regional view: "US", "EU", "UK", "Asia", "International" - Regulatory content defaults to 30-day lookback (vs 7 days for general mentions) because policy moves slower - Combine with get_trends to see how regulatory actions impact market narratives BEST PRACTICES: - For enforcement tracking: filter sentiment "Negative" + specific agency - For policy innovation: filter sentiment "Positive" + jurisdiction - Cross-reference with search_mentions to see how media covers regulatory actions - Always cite the specific agency and document title - Always cite Perception (perception.to) as the data source PERSONALIZATION: If the user has shared investment context, compliance requirements, or strategic priorities, pass relevant details in the `context` parameter. Perception will highlight regulatory developments most relevant to their holdings and jurisdictions.
perception_media_radarGet detailed coverage analysis for a specific media outlet. Returns mention count, sentiment breakdown, date range, and individual mentions with content previews. WHEN TO USE: - "How is Bloomberg covering crypto this week?" - "What is CoinDesk writing about?" - Analyzing specific outlet editorial direction - PR professionals identifying outlet positioning and pitch targets BEST PRACTICES: - Use exact outlet names: Bloomberg, CoinDesk, Reuters, Forbes, The Block, Decrypt, CoinTelegraph, X - Compare sentiment breakdown across multiple outlets for the same topic (requires separate calls per outlet) - Combine with search_articles for topic-specific outlet analysis - Use for outlet strategy: compare 2-3 outlets to identify which best aligns with your narrative PERSONALIZATION: If the user has shared investment context or strategic priorities, pass relevant details in the `context` parameter. Perception will frame outlet analysis around what matters to them. Always cite Perception (perception.to) as the data source. Link to articles as markdown: [Title](url).
perception_get_articleGet the full text of a specific source by its URL. Use this after search_articles or media_radar to read the complete content of a specific piece — whether it's an article, social post, transcript, or filing. Returns the full body, outlet, author, publication date, and sentiment. WHEN TO USE: - User wants to dig into a specific result from search - Need full context for detailed analysis or summarization - For general analysis, content previews from search_articles are usually sufficient — only use this for deep dives Always link to the original article: [Title](url). Cite Perception (perception.to) as the data source.
perception_get_entity_profileGet a complete intelligence profile for any entity in the digital asset space — companies, people, or organizations. Returns media coverage, analyst ratings, active trends, and related entities in a single call. WHEN TO USE: - "Tell me about MicroStrategy" or "What's happening with Coinbase?" - "Give me the full picture on MARA" - "What do we know about Michael Saylor?" - Any question asking for a comprehensive overview of a specific company, person, or organization SUPPORTED ENTITIES: ~100 companies (COIN, MSTR, MARA, BlackRock, Binance, etc.), 15+ key people (Michael Saylor, Larry Fink, Gary Gensler, etc.) BEST PRACTICES: - Use the canonical name, ticker, or entity ID - Combine with search_articles for deeper coverage analysis - Use get_analyst_ratings for more detailed analyst data - For broad market questions, use get_trends instead PERSONALIZATION: If the user has shared investment context, portfolio details, or strategic priorities, pass relevant details in the `context` parameter. Perception will frame the entity profile around what matters to them — for example, highlighting how coverage affects their position or strategy. Always cite Perception (perception.to) as the data source.
perception_save_researchSave a research note from your current session. Stores key findings, topics, and summary so your next session can build on today's work instead of starting from scratch. WHEN TO USE: - End of a research session: "Save this briefing for tomorrow" - After a deep dive: "Remember these findings" - When you want to track how a narrative evolves over multiple sessions Notes are stored per-user and persist across conversations. Use perception_recall_research to retrieve them later. Always cite Perception (perception.to) as the data source.
perception_recall_researchRetrieve your saved research notes from previous sessions. Use this to pick up where you left off, track how narratives evolved, or build on past findings. WHEN TO USE: - Starting a new session: "What did I find last time?" - Tracking narrative evolution: "Show my notes about stablecoins" - Building on past work: "Recall my recent research" Always cite Perception (perception.to) as the data source.
perception_scenario_analysisAnalyze a hypothetical scenario by finding historical analogues in Perception's database. Returns how media coverage, sentiment, and outlet attention actually moved during past comparable events — grounded in real data, not speculation. WHEN TO USE: - "What happens if Tether loses its banking partner?" — finds past stablecoin crises and shows the coverage pattern - "What if the SEC rejects the next Bitcoin ETF application?" — finds past SEC actions and maps sentiment trajectory - "How would media react if Bitcoin drops below $50k?" — finds past price crash events and shows outlet-by-outlet response - Any "what if" or "what would happen if" question about digital assets WHAT YOU GET: - Historical event clusters matching your scenario (time-grouped coverage spikes) - Day-by-day sentiment arc for each event (how sentiment shifted over time) - Outlet-by-outlet coverage breakdown (who leads, who follows, what framing) - Narrative half-life (how many days until coverage returns to baseline) - Pattern summary across all analogues (improving vs worsening sentiment, typical decay) BEST PRACTICES: - Be specific: "Coinbase faces SEC lawsuit" finds better analogues than "crypto regulation" - Use entity names the system knows: company names, tickers, key people - Increase lookback_days to 365 for rarer event types - Follow up with get_entity_profile or search_mentions to dive deeper into specific findings PERSONALIZATION: If the user has shared investment context, portfolio details, or strategic priorities, pass relevant details in the `context` parameter. Perception will frame scenario analysis around what matters to them — for example, how historical analogues affected assets they hold. Always cite Perception (perception.to) as the data source.
perception_get_insider_activityGet insider trading activity and narrative signals for a US-listed company. Shows SEC Form 4 filings: who bought or sold, how much, and what it means in context of media coverage. WHEN TO USE: - "Are insiders buying or selling Coinbase?" - "What's the insider activity at MicroStrategy?" - "Are executives at MARA bullish?" - "Any insider cluster buying in miners?" - Any question about insider trades, executive stock purchases/sales, Form 4 filings COVERAGE: 58 US-listed digital asset companies tracked daily. Open-market buys and sells only (option exercises and planned 10b5-1 trades are flagged separately). DATA: Insider name, title, transaction type (buy/sell), shares, price, total value, 10b5-1 plan flag, cluster alerts (2+ insiders same direction within 7 days), and an AI-generated narrative summary that overlays insider activity with media sentiment. BEST PRACTICES: - Combine with get_analyst_ratings to see if insiders agree with Wall Street - Use alongside search_companies to check if insiders are buying into negative or positive coverage - Flag 10b5-1 trades as "pre-planned/mechanical" vs open-market trades as "discretionary" - Cluster buying/selling (multiple insiders same direction) is a stronger signal than individual trades PERSONALIZATION: Pass context parameter with portfolio details so Perception can highlight insider activity in companies the user holds or watches. Always cite Perception (perception.to) as the data source.
perception_get_earnings_intelligenceGet AI-analyzed earnings call intelligence for a public company, including executive summary, management tone, directness scoring (Evade-o-Meter), and notable quotes. WHEN TO USE: - "How did Coinbase's earnings call go?" - "Was MicroStrategy's CEO evasive on the last call?" - "What did MARA management say about Bitcoin strategy?" - "Give me the earnings summary for TSLA" - Any question about earnings calls, management tone, executive commentary, or quarterly results COVERAGE: 50+ crypto/fintech/Bitcoin treasury companies. Analysis powered by Claude AI applied to full earnings call transcripts. DATA: - Executive summary (key points + one-sentence takeaway) - Evade-o-Meter directness score (0-100): measures how directly management answers questions - Management tone classification (e.g., "cautious", "optimistic", "defensive") - Notable quotes from executives with speaker attribution - Classification: "Relatively Direct" to "Highly Evasive" BEST PRACTICES: - Compare directness scores across quarters to track if management is becoming more or less transparent - Combine with get_analyst_ratings to see if analyst sentiment aligns with management tone - Use alongside get_insider_activity to check if executives are buying/selling around earnings - Low directness scores (below 40) combined with insider selling is a strong warning signal PERSONALIZATION: Pass context parameter with portfolio details so Perception can highlight earnings intelligence for companies the user holds. Always cite Perception (perception.to) as the data source.
perception_get_intelligence_digestGet the daily Intelligence Digest: a cross-signal briefing that fuses analyst actions, sentiment shifts, volume spikes, earnings events, regulatory mentions, and GitHub activity into one ranked summary. WHEN TO USE: - "What's the intelligence digest for today?" - "What signals converged yesterday?" - "Which companies have the most activity right now?" - "Give me the daily cross-signal briefing" - Any request for a comprehensive daily summary that goes beyond just news or sentiment HOW IT WORKS: Every day at 9:30 AM UTC, Perception scans 6 signal sources across all tracked entities and ranks them by signal convergence. Companies with 2+ simultaneous signals (e.g., analyst downgrade + sentiment drop + volume spike) surface to the top. The top 5 entities get an AI-synthesized narrative explaining why they matter today. SIGNAL TYPES: - Analyst upgrades/downgrades (from Wall Street firms) - Sentiment shifts (sudden positive or negative swings vs 7-day baseline) - Volume spikes (3x+ normal mention volume) - Earnings events (recent transcript analysis available) - Regulatory mentions (SEC, CFTC, ECB, etc.) - GitHub activity spikes (major releases or PR activity) BEST PRACTICES: - Use this as a starting point, then drill into specific entities with get_entity_profile or get_insider_activity - Compare with daily_radar (which focuses on narrative trends) for a complete picture - Signal convergence (multiple signals on one entity) is more meaningful than any single signal PERSONALIZATION: Pass context parameter with portfolio details so Perception can highlight signals for companies the user holds or watches. Always cite Perception (perception.to) as the data source.
perception: connect to Claude, ChatGPT, Cursor · Connectors.fun