Systems | Development | Analytics | API | Testing

What are we spending? Who’s using AI? Is it improving productivity? Here’s how we use Fivetran’s own AI connectors to turn fragmented AI consumption data into answers we can act on.

We’re lowering our prices and introducing key product enhancements to power your data pipelines.

AI agents that forget their context are just expensive chatbots. The difference between intelligent agents and simple assistants comes down to memory architecture, specifically how well your system tracks relationships, maintains temporal context, and reasons over evolving information. Graph databases have moved from niche infrastructure to essential AI components, with GraphRAG implementations showing 80% improvements in agent truthfulness and significant accuracy gains over vector-only approaches.

Google Research’s TimesFM 3.0 is a 330-million parameter foundation model that unlocks native multivariate time-series forecasting in BigQuery SQL.

LLM observability is the practice of collecting and analyzing data about how a language model application or AI agent behaves, including prompts, responses, tool calls, cost, speed, and errors, so teams can find problems, measure quality, and improve results. AI agents can now plan tasks, call tools, and work across business systems. That makes them powerful, and it also means a single request can involve many steps that no one sees directly.

Agentic AI security is the set of controls that keep AI agents from accessing, changing, or sharing more than they should. It covers who an agent acts for, which data and tools it can use, which actions need approval, and how its activity is recorded and reviewed. AI agents are moving from pilots into daily operations. They read invoices, update records, answer customers, and trigger workflows across business systems.

With Claude Dashboards entering beta, Anthropic is making it possible for people to ask quick, exploratory questions about their business data and get a dashboard back. You don't need to write SQL or build a visualization. I think that's a good thing. We've spent years trying to make analytics more accessible, and anything that shortens the path from question to answer is progress. I'm increasingly asked what the future of business intelligence looks like when AI can do more of the analysis for us.

Many invoice problems don't start in accounts payable. They start earlier, when someone buys without a purchase order or a delivery goes unrecorded. AP is simply where those gaps become visible, usually as an invoice that can't be paid. That's why it helps to see the accounts payable process end to end. It's how a business receives, checks, approves, pays, and records the bills it owes suppliers, whether those steps run by hand or through accounts payable automation.