Xebia: Why AI agents fail without the right data foundation

2026-06-11 · Source: AI News · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics, Software Development & Engineering · Depth: Intermediate, medium

Summary

Xebia's global CTO, Niels Zeilemaker, emphasizes that AI agents will fail without a proper data foundation, stressing the necessity of making data available for AI consumption and ensuring accurate data cataloging. Unlike humans, AI agents lack a "back door" to clarify poorly documented data, making precise data catalogs critical for their performance. Xebia offers "Agentic Data Foundation (ADF)" to extend data platforms for hosting agents and "Xebia ACE: AI-Native Software Engineering" to embed AI across the software development lifecycle (SDLC). This approach aims to accelerate delivery by up to 40% and cut legacy transformation costs by up to 70%, while maintaining governance. The company also notes the emerging trend of multi-agent code review tools, like Anthropic's pull request reviewer, to enhance security in AI-driven development.

Key takeaway

For AI Engineers or Directors of AI/ML implementing AI agents, understand that your agents will fail without a robust data foundation. Prioritize comprehensive data cataloging, as agents lack human fallback for data ambiguities. You should consider frameworks like Xebia's Agentic Data Foundation to prepare your data and AI-Native Software Engineering to accelerate secure, governed AI integration across your SDLC, cutting transformation costs and improving delivery speed.

Key insights

AI agents require a robust, well-cataloged data foundation to perform accurately, lacking human fallback for data ambiguities.

Principles

• Agentic AI scales on data strength.
• Data catalogs are critical for agent performance.
• AI-driven SDLC needs governance and security.

Method

Xebia's Agentic Data Foundation (ADF) extends data platforms to host agents for customer-facing and internal use cases. Xebia ACE embeds AI across the SDLC to accelerate delivery and cut costs.

In practice

• Implement robust data cataloging for AI agents.
• Use AI-native engineering frameworks for SDLC.
• Integrate multi-agent code review tools.

Topics

• AI Agents
• Data Foundation
• Data Cataloging
• AI-Native Software Engineering
• SDLC Acceleration
• Xebia

Best for: CTO, VP of Engineering/Data, AI Architect, Director of AI/ML, AI Engineer, Data Engineer

Related on AIssential

• The End of Software’s Monopoly on Work — AI agents shift enterprise work from applications to a trusted data context layer, demanding unified, governed data for reliable action.
• Most AI pilot programs fail to deliver measurable impact — Most AI pilot programs fail due to inadequate data management and insufficient data resilience measures.
• The Best Data Catalog Tools in 2026 and Why Your AI Strategy Depends on Choosing the Right One — Reliable AI function hinges on robust data cataloging for context management and governance.
• D&B's database of 642 million businesses was built for humans, not AI agents. So they rebuilt it. — Enterprise data systems built for humans require fundamental redesign for AI agents.
• Your AI Problem Is a Data Problem — AI project failures often stem from unready data, not model or tooling issues.
• Scaling agentic AI demands a strong data foundation - 4 steps to take first — Scaling agentic AI hinges on a robust foundation of high-quality, trusted data and modernized data architecture.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by AI News.