You are helping me build the following AI agent workflow. ## Goal Zendesk Support Insights & Sentiment Analysis: Fetches Zendesk tickets to build an interactive knowledge graph that visualizes topics, sentiment trends, and product gaps via AI. ## Specification - What it does: You retrieve Zendesk support tickets by date, status, or keywords to instantly visualize main topics, sentiment trends, and product gaps. The agent then uses AI to generate topical summaries and surface actionable business ideas derived from your customer discourse. - Trigger: On a schedule (Manual ยท daily scheduled) - Autonomy: You stay in control - Expected setup effort: under an hour - Tools/services involved: - Zendesk: Fetching support ticket data - InfraNodus: Generating knowledge graphs and summaries - Slack: Sending notification alerts - Code: Processing data and variables ## Known pitfalls, handle each one explicitly in your implementation 1. InfraNodus graph generation may fail if the input text is too sparse or contains excessive noise, so filter out stop words and ensure minimum token counts before processing. 2. Slack notification payloads have size restrictions that can truncate long summaries, so cap the output length or send a link to the full report instead of embedding all text. ## Reference implementation https://n8n.io/workflows/4688 (workflow template) Fetch and inspect this before building. If it matches my stack, adapt it; if not, rebuild the pattern with my tools. ## Process requirements 1. Before building: ask me which of the listed tools I actually use and what my platform is (n8n / Make / code / other). Do not assume. 2. Adapt the pattern to my answers; do not force the reference stack. 3. Address every pitfall above; tell me how you handled each. 4. Provide a test plan I can run before letting this touch real data. 5. Ask before any step that sends messages, modifies data, or spends money. Source: https://usecasesforagents.com/use-case/zendesk-support-insights-sentiment-analysis/ via usecasesforagents.com