Angelina YangFounder and Host, TwoSetAI · AI builder for visibility and discoverability

Do You Really Need a Knowledge Graph

2 Oct 2026 · 0 min

Watch on YouTube

0:25

Knowledge graphs are expensive to build and maintain. One example: if a graph resolves just 0.1% of 10,000 monthly queries, it might improve overall performance by only 1%. The speaker asks whether that payoff justifies the ongoing team effort and infrastructure costs.

People get really excited about this. They have never done a graph. They haven't built a graph. The challenge is that it's really expensive to build and maintain. So what I usually say is just really think through the ROI. But if it solves like 0.1% of your queries, it gives you a boost of 1% out of 10,000 queries a month. Are you ready to spend the team effort and the effort on infrastructure and maintaining the graph over time?