The Model Is Not the Problem: Why Data Quality Is the Real Bottleneck in Agentic AI

About this session

Everyone building with agentic AI is debating the same things: which model, which framework, which use case. Almost no one is talking about what actually determines whether any of it works in production — the data underneath it. An agent reading stale inventory will promise stock that doesn't exist. An agent working from an outdated policy will make commitments the company can't keep. An agent on fragmented customer data will fail to personalise for anyone. These aren't model failures. They're data failures. And they're happening right now in organisations that invested heavily in AI and almost nothing in the data it runs on. This session makes the case that data quality isn't a pre-condition for AI investment — it IS the AI investment. You'll leave with a four-dimension audit framework you can apply to your own systems immediately, clarity on which data failures are tolerable and which are fatal, and a reframe that changes how you prioritise every AI decision going forward. The technology is ready. The data is the work.

Speaker

Key takeaways

  • A practical four-dimension framework — completeness, freshness, consistency, accuracy — to audit the data your agents depend on, so you can identify which gaps are tolerable and which ones will break your deployment before it reaches users.
  • A reframe that changes how you prioritise AI investment: data quality work is not the preparation for building agents, it is the compounding infrastructure that makes every agent you build — now and in the future — more capable, more trustworthy, and harder for competitors to replicate.
  • Examples of data failures that destroy agent performance and customer trust in production and the design pattern that prevents each one.

Related sessions