How do you create a monthly executive report with AI? Run the Executive Decision Brief skill in Databox. Genie, the Databox AI Analyst, reads your connected metrics and writes a one-page leadership brief: the executive takeaway, wins, risks, contradictions between metrics, and three "Should we..." decisions to discuss. It reads in about 90 seconds, and the same skill runs in Claude through Databox MCP.

How do you create a weekly GA4 report with AI? Run the free GA4 Website Traffic & Performance Report skill in Databox. Genie, the Databox AI Analyst, reads your live Google Analytics 4 data and writes the whole weekly report: the verdict, channels, landing pages, conversions, trends and anomaly flags. The same skill also runs in Claude through Databox MCP. In this video: Chapters Key terms Tools and data sources shown: Google Analytics 4, Facebook Ads, Asana (Asana MCP connector), Slack, Claude with Databox MCP. All data is a fictional demo account.

You can talk an AI model into breaking its own rules. Sometimes, all it takes is knowing what to say. Dr. Peter Garraghan has spent years studying how attackers exploit AI systems, and some of his findings are surprisingly human. AI models can be manipulated through language, using techniques that resemble the social engineering tactics cybersecurity professionals have dealt with for decades.

Most data questions come up in Slack. Most data answers require leaving it. In this demo, watch how Spotter, ThoughtSpot's AI analyst, works directly inside your Slack workspace, in direct messages, threads, and public channels. Ask a question in natural language, and Spotter pulls from your governed data models to return an answer with high-level insights and relevant artifacts (images, PDFs, and CSVs), right where the conversation is already happening.

Your governed data is only useful if people can access it where decisions actually happen. For most teams, that's not a BI tool… it's Microsoft Teams. In this demo, watch how Spotter, ThoughtSpot's AI analyst, works directly inside Teams: in direct messages, group chats, and collaborative channels. Ask a question in natural language, and Spotter pulls from your governed data models to return an answer, right in the thread. Every answer names the model it came from, so anyone can verify the number instead of taking it on faith.