The Competitor Trail watches your company's competitors in the background. Every morning, the workflow pulls new posts from the stored RSS feeds, analyzes them by AI for topic, positioning, feature and format, and clusters the results into trends across multiple competitors. The result is a finished report with an executive summary, prioritized insights and concrete recommendations for the content team.
\nWhat gets automated is the feed monitoring, the extraction of the relevant characteristics per post, and the aggregation into trends. The human stays in the loop at two points: maintaining the source list (which competitors and feeds get watched in the first place) and judging whether an insight actually calls for action. The report provides a basis, not an automatic decision.
\nThe workflow makes sense for teams who want to keep a regular eye on competitor content but do not have the capacity for daily manual screening. It does not replace deep strategic competitive research, but it supplies the ongoing baseline for it.
\nCopy the prompt below in full into your automation tool or agent builder. As a file: wettbewerbs-spur.en.json
\n" } ], "schritte": [ { "nr": 1, "titel": "Time trigger", "beschreibung": "The workflow starts daily at a fixed time, for example 9:00 a.m., alternatively on a weekly cadence.", "rolle": "mensch" }, { "nr": 2, "titel": "Fetch RSS feeds", "beschreibung": "All stored competitor feeds are loaded, only posts from the last 24 hours are considered, duplicates are filtered out.", "rolle": "automatisch" }, { "nr": 3, "titel": "Extract posts", "beschreibung": "From each new post, the topic, angle, feature or claim, format and addressed target audience are extracted.", "rolle": "automatisch" }, { "nr": 4, "titel": "Aggregate trends", "beschreibung": "The extracted topics are clustered, shifts compared to previous runs are identified, and the most important insights are prioritized.", "rolle": "automatisch" }, { "nr": 5, "titel": "Generate report", "beschreibung": "A structured report is created from the results, with an executive summary, rated top insights and concrete recommendations for action.", "rolle": "automatisch" }, { "nr": 6, "titel": "Save and notify", "beschreibung": "The report is saved in the designated storage location. Optionally, an alert also goes to the team for particularly highly rated findings.", "rolle": "ergebnis" } ], "herausgeber": "Voyage Digital", "version": "2.0", "stand": "2026-07-26", "nutzen": [ { "titel": "Ongoing visibility into trends", "text": "New topics and shifts in positioning across competitors are captured daily, not only in hindsight during research." }, { "titel": "Content gaps become visible", "text": "The report shows which topics the team's own editorial plan does not yet cover compared to the market." }, { "titel": "A finished report instead of raw data", "text": "An executive summary, rated top insights and recommendations are ready to use, the team starts from results instead of screening feeds." } ], "voraussetzungen": [ { "label": "RSS reader", "text": "Feedly, Inoreader or a similar tool for the competitors' blogs and newsrooms.", "icon": "rss_feed" }, { "label": "Storage location", "text": "Notion, Drive or Confluence for the daily reports.", "icon": "folder" }, { "label": "Team chat (optional)", "text": "Slack or Teams for alerts on particularly relevant findings.", "icon": "notifications" }, { "label": "LLM access", "text": "API key for OpenAI, Claude or Gemini.", "icon": "key" } ], "betrieb": { "testing": [ { "label": "Test run", "text": "Test the workflow manually with real competitor feeds before you go live.", "icon": "play_circle" }, { "label": "Feed fetch", "text": "Check whether all configured feeds load correctly.", "icon": "download" }, { "label": "Report quality", "text": "Assess whether the insights are structured, relevant and backed by traceable scores.", "icon": "fact_check" }, { "label": "Edge cases", "text": "Test days with no new posts, duplicates, paywalled sources and weekends.", "icon": "rule" } ], "goLive": [ { "label": "Approve to start", "text": "Activate the workflow only once feeds and report run cleanly.", "icon": "check_circle" }, { "label": "Source list", "text": "Define the source list initially and maintain it monthly, adding new sources and removing inactive ones.", "icon": "list_alt" }, { "label": "Refine", "text": "Review report quality over the first two weeks and adjust the prompt accordingly.", "icon": "tune" }, { "label": "Filter", "text": "Filter out pure PR updates without substantive content.", "icon": "filter_alt" } ], "haeufigeFehler": [ { "label": "No new articles", "text": "Validate the feed URLs or extend the time filter to 48 hours.", "icon": "search_off" }, { "label": "Analysis too shallow", "text": "Refine the prompt or choose a stronger model.", "icon": "psychology_alt" }, { "label": "Report not saved", "text": "Check the write permissions in the storage tool.", "icon": "lock" }, { "label": "Duplicates distort trends", "text": "Add deduplication based on URL or title.", "icon": "content_copy" } ] }, "arbeitsprompts": [ { "titel": "Prompt: Content Analysis and Trends", "beschreibung": "Analyzes new competitor posts for topics, developments and trends, and returns a prioritized report with a relevance score.", "prompt": "You are a strategic content analyst. Analyze the following new articles from competitors and create a structured report. Where sufficient information is not available for individual points, mark the affected statement as an assumption instead of presenting it as established fact.\n\nNew articles from the last 24 hours:\n[RSS_FEED_ITEMS]\n\nAnalyze the following aspects:\n1. Main topics and content focus areas\n2. New product features or announcements\n3. Recognizable content strategies and formats\n4. Industry trends and market developments\n5. Tone and target audience approach\n\nCreate a report with the following structure:\n\nCompetitor Content Report, [DATE]\n\nTop Insights: the three to five most important findings as bullet points\n\nTopic Overview: categorized listing of the main topics\n\nNew Developments: product announcements, features, strategic moves\n\nIdentified Trends: overarching patterns and industry trends\n\nRecommendations: concrete suggestions for the content team\n\nFocus on:\n[FOCUS_AREA_1]\n[FOCUS_AREA_2]\n[FOCUS_AREA_3]\n\nRate the relevance of each insight on a scale of 1 to 5 and prioritize the report accordingly." } ], "prompt": "GOAL\nBuild a workflow that fetches new posts from the RSS feeds of defined competitors every day, analyzes the content by AI for topic, positioning, feature and format, aggregates trends across multiple posts, and generates a structured competitor report at the designated storage location. Optionally, an alert should also be triggered in the team chat for particularly relevant findings.\n\nAdapt the structure to the concepts of your automation tool (for example nodes, steps, zaps or agent actions). While doing so, preserve the trigger logic, the sequence and the data flow.\n\nTRIGGER\nType: time based, daily at 9:00 a.m., alternatively weekly.\n\nSTEPS (sequential)\n1. Fetch RSS feeds: load all configured competitor feeds, filter for posts from the last 24 hours, and remove duplicates based on URL or title.\n2. AI step: content analysis and trends. Insert the working prompt \"Content Analysis and Trends\" exactly as given (see the Working Prompts section). Result: a structured report with top insights including a relevance score from 1 to 5.\n3. Save: file the report with the date in the title at the designated storage location (Notion, Drive or Confluence).\n4. Branch (optional): if the report contains an insight with a relevance score of 5 out of 5, also send an alert to the team chat with the top findings and the link to the report.\n\nPROMPT GUIDANCE\nThere is a fixed working prompt for the analysis step, see the Working Prompts section. Insert it unchanged and in full into step 2.\n\nDATA FLOW\nStep 1 to step 2: deduplicated posts (title, source, link, teaser or full text) as input for the feed items placeholder in the working prompt.\nSystem to step 2: the current date as input for the corresponding placeholder in the working prompt.\nStep 2 to steps 3 and 4: the finished report and the relevance scores it contains, as the basis for the optional alert branch.\n\nERROR HANDLING\nNo new articles: validate the feed URLs or extend the time filter to 48 hours. On days without new posts, file a short notice report instead of aborting the run without a result.\nDuplicates distort the trends: enforce deduplication from step 1, based on URL or title.\nPaywalled sources: analyze only the title and teaser, and mark the affected finding in the report as limited.\nAnalysis too shallow: refine the focus areas in the working prompt or choose a stronger model. Filter out pure PR updates without substantive content.\nReport not saved: check the write permissions at the storage location.\n\nPLACEHOLDER CONVENTION\nAll placeholders in square brackets in the working prompt are variables. The feed items and the current date are mapped dynamically, as described in the data flow. The three focus areas are not dynamic: set these yourself as the strategic areas of observation before activation. List all placeholders that require manual configuration separately at the end.\n\nSELF CHECK BEFORE COMPLETION\nCheck, before you report the workflow as finished:\n1. Are all steps connected correctly, including the 24 hour filter, deduplication and the optional alert branch at a relevance score of 5 out of 5?\n2. Is the working prompt inserted in full and unchanged, and are the placeholders for feed items and date mapped correctly?\n3. Is the report filed with the date in the title at the correct location?\n4. Are all points listed that require manual configuration: the source list including monthly maintenance, the storage location with write permissions, the alert channel, the three focus areas and the LLM access?", "einrichtung": { "intro": "Two routes lead to the same result. Pick the one that fits your setup.", "varianten": [ { "variante": "Builder-Prompt", "einleitung": "Suitable when you want to build the workflow in your own automation tool.", "schritte": [ "Open your workflow tool, for example n8n, Make, Zapier or Langdock.", "Create a new workflow and give it a name.", "Choose the AI-assisted build option if your tool offers one.", "Paste the builder prompt from above in full.", "Check the result against the step sequence in this document, then add your access credentials and channels." ] }, { "variante": "JSON-Import", "einleitung": "Suitable when you want to take the workflow over unchanged.", "schritte": [ "Download the JSON file from the JSON export section.", "Open the workflow area of your tool and create a new workflow.", "Give it a name and confirm.", "Open the menu on the workflow name and choose to import a JSON file.", "Upload the file, then add your own access credentials.", "Run a test before you activate the workflow." ] } ] }, "exportMeta": { "datei": "w02_wettbewerbs-spur__workflow.json", "format": "voyage-workflow/1" }, "download": { "schema": "voyage-workflow/1", "name": "Die Wettbewerbs-Spur", "beschreibung": "Ruft täglich neue Wettbewerber-Beiträge aus mehreren parallel abgefragten RSS-Feeds ab, parst und dedupliziert sie in einem Code-Schritt, analysiert sie in einem einzigen KI-Knoten nach Thema, Positionierung, Feature und Format, aggregiert daraus priorisierte Trends und legt das Ergebnis als strukturierten Report ab, im Originalexport konkret als neue Notion-Seite.", "trigger": { "typ": "Zeitgesteuert (Cron)", "bedingung": "Cron-Ausdruck 0 9 * * *, das heißt täglich um 09:00 Uhr. Uhrzeit und Rhythmus lassen sich über den Cron-Ausdruck anpassen, zum Beispiel auf mehrmals täglich, nur werktags oder wöchentlich." }, "schritte": [ { "nr": 1, "titel": "Zeit-Trigger", "rolle": "mensch", "aktion": "Der Workflow startet automatisch nach Zeitplan. Im Originalexport ist der Cron-Ausdruck 0 9 * * * hinterlegt, täglich 09:00 Uhr. Der Trigger löst die drei parallelen Feed-Abrufe von Schritt 2 gleichzeitig aus.", "prompt_ref": null, "eingang": [], "ausgang": [ "Start-Signal für die parallelen Feed-Abrufe" ] }, { "nr": 2, "titel": "RSS-Feeds abrufen", "rolle": "automatisch", "aktion": "Drei HTTP-Abrufe laufen parallel, je einer pro beobachtetem Wettbewerber-Feed. Im Originalexport stehen dort noch Platzhalter-Domains (siehe Platzhalter COMPETITOR_1_FEED_URL bis COMPETITOR_3_FEED_URL), die vor dem Go-Live durch echte Feed-URLs ersetzt werden. Ein anschließender Code-Schritt parst die XML-Antworten aller Feeds, extrahiert je Beitrag Titel, Link, Beschreibung, Datum und Content, filtert auf Beiträge der letzten 24 Stunden und entfernt Dubletten auf URL- oder Titel-Basis.", "prompt_ref": null, "eingang": [], "ausgang": [ "Deduplizierte Beiträge je Wettbewerber (Titel, Link, Beschreibung, Datum, Content)" ] }, { "nr": 3, "titel": "Beiträge extrahieren", "rolle": "automatisch", "aktion": "Diese Extraktion erfolgt im Originalexport zusammen mit den Schritten 4 und 5 in einem einzigen KI-Knoten, dem Competitive Intelligence Analyst. Er liest alle deduplizierten Beiträge und leitet daraus Themenschwerpunkte, neue Produktfeatures oder Ankündigungen, erkennbare Content-Strategien und Formate sowie die adressierte Zielgruppe ab.", "prompt_ref": "arbeitsprompt-1", "eingang": [ "Deduplizierte Beiträge je Wettbewerber" ], "ausgang": [ "Extrahierte Merkmale je Beitrag" ] }, { "nr": 4, "titel": "Trends aggregieren", "rolle": "automatisch", "aktion": "Im selben KI-Knoten werden die extrahierten Themen geclustert, Verschiebungen und Branchentrends herausgearbeitet und die Wettbewerberpositionierung eingeordnet. Daraus entstehen priorisierte Insights.", "prompt_ref": "arbeitsprompt-1", "eingang": [ "Extrahierte Merkmale je Beitrag", "Aktuelles Datum" ], "ausgang": [ "Priorisierte Insights mit Relevanz-Score" ] }, { "nr": 5, "titel": "Report erzeugen", "rolle": "automatisch", "aktion": "Der Analyse-Knoten liefert ein strukturiertes Ausgabeschema mit acht Pflichtfeldern: summary, product_insights, content_strategy, industry_trends, competitor_positioning, top_priority_actions, articles_analyzed (Anzahl der analysierten Artikel) und success (Bestätigung, ob die Analyse erfolgreich lief). Diese Felder bilden zusammen den Report.", "prompt_ref": "arbeitsprompt-1", "eingang": [ "Priorisierte Insights mit Relevanz-Score" ], "ausgang": [ "Strukturierter Report (8 Felder)" ] }, { "nr": 6, "titel": "Speichern und benachrichtigen", "rolle": "ergebnis", "aktion": "Der Report wird im Originalexport als neue Notion-Seite abgelegt: Titel im Format Wettbewerber-Analyse, aktuelles Datum, Inhalt aus den acht Ausgabefeldern des Analyse-Knotens zusammengesetzt (Überblick, Produktentwicklungen, Content-Strategien, Branchentrends, Wettbewerbspositionierung, Handlungsempfehlungen, Anzahl analysierter Artikel). Als Ablageort ist aktuell der persönliche Notion-Workspace-Root hinterlegt, für einen festen Team-Ablageort ist die Seiten-ID anzupassen (siehe Platzhalter NOTION_PARENT_ID). Einen eigenen Knoten für einen Team-Chat-Alert bei Relevanz-Score 5 von 5 enthält der Originalexport nicht, dieser Zweig wäre bei Bedarf zusätzlich anzulegen.", "prompt_ref": null, "eingang": [ "Strukturierter Report (8 Felder)" ], "ausgang": [ "Abgelegte Notion-Seite", "Team-Alert (optional, zusätzlich anzulegen)" ] } ], "prompts": { "arbeitsprompt-1": { "titel": "Content-Analyse und Trends", "text": "Sie sind ein strategischer Content-Analyst. Analysieren Sie die folgenden neuen Artikel von Wettbewerbern und erstellen Sie einen strukturierten Report. Wenn zu einzelnen Punkten keine ausreichenden Informationen vorliegen, kennzeichnen Sie die betreffende Aussage als Annahme statt sie als gesichert darzustellen.\n\nNeue Artikel der letzten 24 Stunden:\n[RSS_FEED_ITEMS]\n\nAnalysieren Sie folgende Aspekte:\n1. Hauptthemen und Content-Schwerpunkte\n2. Neue Produktfeatures oder Ankündigungen\n3. Erkennbare Content-Strategien und Formate\n4. Branchentrends und Marktentwicklungen\n5. Tonalität und Zielgruppenansprache\n\nErstellen Sie einen Report mit folgender Struktur:\n\nCompetitor Content Report, [DATUM]\n\nTop-Insights: die drei bis fünf wichtigsten Erkenntnisse als Bullet Points\n\nThemenübersicht: kategorisierte Auflistung der Hauptthemen\n\nNeue Entwicklungen: Produktankündigungen, Features, strategische Schritte\n\nErkannte Trends: übergreifende Muster und Branchentrends\n\nHandlungsempfehlungen: konkrete Vorschläge für das Content-Team\n\nFokussieren Sie sich auf:\n[FOKUS_BEREICH_1]\n[FOKUS_BEREICH_2]\n[FOKUS_BEREICH_3]\n\nBewerten Sie die Relevanz jedes Insights auf einer Skala von 1 bis 5 und priorisieren Sie den Report entsprechend." } }, "datenfluss": [ { "von": 1, "nach": 2, "nutzlast": "Trigger-Signal, löst die drei parallelen Feed-Abrufe gleichzeitig aus" }, { "von": 2, "nach": 3, "nutzlast": "Deduplizierte Beiträge aller Wettbewerber-Feeds (Titel, Link, Beschreibung, Datum, Content) als [RSS_FEED_ITEMS]" }, { "von": "System", "nach": 3, "nutzlast": "Aktuelles Datum als [DATUM]" }, { "von": 3, "nach": 4, "nutzlast": "Extrahierte Merkmale je Beitrag, innerhalb desselben KI-Knotens weitergereicht" }, { "von": 4, "nach": 5, "nutzlast": "Priorisierte, geclusterte Insights, ebenfalls innerhalb desselben Knotens" }, { "von": 5, "nach": 6, "nutzlast": "Strukturierter Report mit den Feldern summary, product_insights, content_strategy, industry_trends, competitor_positioning, top_priority_actions, articles_analyzed, success" } ], "voraussetzungen": [ "RSS-Reader oder vergleichbare Feed-Quelle für die Wettbewerber-Blogs und Newsrooms, zum Beispiel Feedly oder Inoreader", "Ablageort für die täglichen Reports, zum Beispiel Notion, Drive oder Confluence. Der Originalexport implementiert konkret eine Notion-Seite", "Team-Chat optional für Alerts bei besonders relevanten Funden, zum Beispiel Slack oder Teams. Im Originalexport noch nicht als eigener Knoten angelegt", "LLM-Zugang per API-Key (OpenAI, Claude oder Gemini)", "Gepflegte und aktuell gehaltene Quellenliste der beobachteten Wettbewerber und Feeds" ], "fehlerbehandlung": [ { "fall": "Keine neuen Artikel gefunden", "massnahme": "Feed-URLs validieren oder Zeitfilter auf 48 Stunden erweitern. An Tagen ohne Beiträge einen kurzen Hinweis-Report ablegen, statt den Lauf ohne Ergebnis abzubrechen." }, { "fall": "Dubletten verfälschen die Trends", "massnahme": "Deduplizierung auf URL- oder Titel-Basis im Code-Schritt aus Schritt 2 zwingend umsetzen." }, { "fall": "Paywall-geschützte Quellen", "massnahme": "Nur Titel und Teaser analysieren und den betroffenen Befund im Report als eingeschränkt kennzeichnen." }, { "fall": "Analyse zu oberflächlich", "massnahme": "Fokus-Bereiche im Arbeitsprompt schärfen oder ein stärkeres Modell wählen. Reine PR-Updates ohne inhaltliche Substanz aussortieren." }, { "fall": "Report wird nicht gespeichert", "massnahme": "Schreibrechte am Ablageort prüfen, im Originalexport konkret die Notion-Verbindung und die parentId." }, { "fall": "Fehler in einem einzelnen Knoten (Feed-Abruf, Parser, Analyse oder Speichern)", "massnahme": "Im Originalexport sind alle Knoten auf Abbruch bei Fehler konfiguriert, es gibt keine automatische Wiederholung. Für die drei parallelen Feed-Abrufe empfiehlt sich ein eigener Retry- oder Continue-on-Error-Zweig, damit ein einzelner nicht erreichbarer Wettbewerber-Feed nicht den gesamten Lauf stoppt." } ], "platzhalter": [ { "name": "RSS_FEED_ITEMS", "quelle": "Deduplizierte Feed-Beiträge aus dem Code-Schritt in Stufe 2, dynamisch gemappt" }, { "name": "DATUM", "quelle": "Aktuelles Systemdatum, dynamisch gemappt" }, { "name": "FOKUS_BEREICH_1", "quelle": "Erster strategischer Beobachtungsschwerpunkt, vor der Aktivierung manuell festgelegt" }, { "name": "FOKUS_BEREICH_2", "quelle": "Zweiter strategischer Beobachtungsschwerpunkt, vor der Aktivierung manuell festgelegt" }, { "name": "FOKUS_BEREICH_3", "quelle": "Dritter strategischer Beobachtungsschwerpunkt, vor der Aktivierung manuell festgelegt" }, { "name": "COMPETITOR_1_FEED_URL", "quelle": "Feld url im Knoten RSS Feed Wettbewerber 1, im Originalexport eine Platzhalter-Domain, vor Aktivierung durch die echte Feed-URL des ersten Wettbewerbers ersetzen" }, { "name": "COMPETITOR_2_FEED_URL", "quelle": "Feld url im Knoten RSS Feed Wettbewerber 2, dieselbe Platzhalter-Logik wie COMPETITOR_1_FEED_URL" }, { "name": "COMPETITOR_3_FEED_URL", "quelle": "Feld url im Knoten RSS Feed Wettbewerber 3, dieselbe Platzhalter-Logik wie COMPETITOR_1_FEED_URL" }, { "name": "NOTION_PARENT_ID", "quelle": "Feld parentId im Speichern-Knoten, im Originalexport auf workspace gesetzt, also den persönlichen Notion-Root. Für einen festen Team-Ablageort auf eine dedizierte Notion-Seiten-ID setzen" } ], "herausgeber": "Voyage Digital", "version": "2.0", "stand": "2026-07-26" }, "itemIcon": "swords", "recommended": [ { "slug": "benchmark-raster", "category": "skill", "name": "The Benchmark Grid", "teaser": "Places your key metrics next to solid industry benchmarks and turns the comparison into an action plan, not just a numbers exercise.", "domaene": "Recherche & Wissensmanagement", "itemIcon": "gauge" }, { "slug": "wettbewerbs-raster", "category": "skill", "name": "The Competitor Matrix", "teaser": "The Competitor Matrix researches a competitor from publicly available sources and condenses the findings into a one-page battle card ready for your next sales conversation.", "domaene": "Recherche & Wissensmanagement", "itemIcon": "swords" }, { "slug": "presse-kette", "category": "workflow", "name": "The Press Chain", "teaser": "A daily workflow that filters industry news by relevance using AI and delivers it as a categorized briefing in the team channel, instead of someone scrolling through feeds by hand.", "domaene": "Recherche & Wissensmanagement", "itemIcon": "newspaper" }, { "slug": "konkurrenzvergleichs-analyst", "category": "assistent", "name": "The Competitor Comparison Analyst", "teaser": "Compares 2 to 3 concrete competitors along a clearly defined comparison point and delivers a structured comparison table, strategic insights and positioning opportunities for the next 30 days.", "domaene": "Recherche & Wissensmanagement", "itemIcon": "columns-3" }, { "slug": "sekundaerrecherche-sichter", "category": "assistent", "name": "The Secondary Research Scanner", "teaser": "Runs an initial secondary market analysis on market size, target audiences, competition and trends and delivers a structured overview with an optional SWOT as the starting point for strategic planning.", "domaene": "Recherche & Wissensmanagement", "itemIcon": "library-big" }, { "slug": "wissens-kette", "category": "workflow", "name": "The Knowledge Chain", "teaser": "A weekly workflow that clusters the most frequent topics from closed support tickets into reviewed FAQ drafts, so the knowledge base stays current without manual research.", "domaene": "Recherche & Wissensmanagement", "itemIcon": "book-open-text" }, { "slug": "rm-skills", "category": "tool", "name": "rm-skills", "teaser": "rm-skills is an MIT-licensed package of six standalone Claude skills for Gmail triage, infographic generation, LinkedIn asset analysis, tweet reading, video performance analysis and X account monitoring.", "domaene": "Recherche & Wissensmanagement" }, { "slug": "firmenprofil-sichter", "category": "assistent", "name": "The Company Profile Scanner", "teaser": "Scans publicly available sources on a company and distills them into a structured, source backed report.", "domaene": "Recherche & Wissensmanagement", "itemIcon": "building" }, { "slug": "recherche-navigator", "category": "assistent", "name": "The Research Navigator", "teaser": "The Research Navigator breaks a research question into sub-aspects, checks sources for currency and reliability, and delivers a structured report with key findings, detailed analysis, and a clear conclusion.", "domaene": "Recherche & Wissensmanagement", "itemIcon": "telescope" }, { "slug": "dokumenten-kette", "category": "workflow", "name": "The Document Chain", "teaser": "An automation building block that reviews new documents in cloud storage, turns them into a structured summary, and notifies the team with a direct link.", "domaene": "Recherche & Wissensmanagement", "itemIcon": "files" }, { "slug": "unternehmenswissen-lotse", "category": "assistent", "name": "The Company Knowledge Navigator", "teaser": "The Company Knowledge Navigator answers employee questions about policies, products and processes using your own company documents, always citing the exact source behind each answer.", "domaene": "Recherche & Wissensmanagement", "itemIcon": "library" }, { "slug": "graphify", "category": "tool", "name": "graphify", "teaser": "graphify converts code, documentation, PDFs, images and video into a searchable semantic knowledge graph that reads far more token efficiently than ingesting every file individually.", "domaene": "Recherche & Wissensmanagement", "logoFile": "graphify.png", "logoEinzug": 0.78 }, { "slug": "notebooklm", "category": "tool", "name": "NotebookLM", "teaser": "NotebookLM is a source-based notebook from Google that turns documents, videos and audio into a searchable, citable knowledge space.", "domaene": "Recherche & Wissensmanagement", "logoFile": "notebooklm.svg", "logoEinzug": 1 }, { "slug": "perplexity", "category": "tool", "name": "Perplexity", "teaser": "Perplexity is an AI search engine that combines web research with generative AI and delivers answers with traceable, clickable source citations.", "domaene": "Recherche & Wissensmanagement", "logoFile": "perplexity.svg", "logoEinzug": 0.78 } ] }