AI agents are changing retrieval requirements. As organizations move from chatbots to AI systems that investigate, reason, and act on users’ behalf, retrieval is becoming the foundation of application quality. Better retrieval doesn’t just produce better answers—it enables more capable assistants, more personalized experiences, and more trustworthy autonomous systems.Traditional search and even many RAG applications could tolerate imperfect retrieval. If a user didn’t find exactly what they wanted, they refined the query or tried again. Agents don’t have that luxury.“As organizations move from chatbots to AI systems that investigate, reason, and act on users’ behalf, retrieval is becoming the foundation of application quality.”An AI agent plans, reasons, invokes tools, and increasingly makes decisions without a human reviewing every intermediate step. That raises the bar considerably. Retrieval is no longer about finding relevant information—it’s about consistently delivering the right evidence at the right time.For engineers, this creates a familiar set of challenges:Which signals matter most for this user?How do fresh events change relevance?How should structured, unstructured, and behavioral signals be combined?When should a model influence ranking?How do you optimize for business outcomes rather than similarity scores?Those aren’t vector database problems. They’re Retrieval Engineering problems.It’s no longer just about embeddings or vector search. It’s about engineering the entire retrieval workflow: combining hybrid retrieval, real-time signals, ranking, machine learning inference, and continuous experimentation to deliver the best possible decision at serving time.A recent GigaOm Decision Brief argues that as retrieval becomes increasingly commoditized, competitive advantage shifts to decisioning—determining what an application or AI agent should see, and in what order, before it acts.“As retrieval becomes increasingly commoditized, competitive advantage shifts to decisioning—determining what an application or AI agent should see, and in what order, before it acts.”That aligns closely with the way we’ve been thinking about Retrieval Engineering:Prompt engineering influences how a model reasons. Retrieval Engineering determines what it has to reason about.As organizations move from copilots to production AI agents, I believe Retrieval Engineering will become a core engineering discipline alongside prompt engineering and model engineering.If you’re interested in the engineering discipline itself, my earlier article explores Retrieval Engineering in more depth (https://thenewstack.io/ai-retrieval-engineering-bottleneck/). The new GigaOm paper complements that discussion by looking at why these engineering decisions increasingly influence product quality, customer experience, and ultimately business outcomes.Read the GigaOm report. The post AI agents are making retrieval engineering a core engineering discipline appeared first on The New Stack.