"As the year drew to a close, most companies were stuck in the pilot phase of experimenting with AI agents. I think that's going to change this year, and one reason is that tech vendors are figuring out that simply offering AI models with agentic capabilities is not enough. They have to help their customers engineer the entire work flow around the AI agent-either directly, through forward deployed engineers who act as consultants and "customer success" sherpas;"
"A key step in getting these workflows right is making sure AI agents have access to the right information. Since 2023, the standard way to do this has been with some kind of RAG, or retrieval augmented generation, process. Essentially, the idea is that the AI system has access to some kind of search engine that allows it to retrieve the most relevant documents or data from either internal corporate sources or the public internet"
Most companies remained in the pilot phase of experimenting with AI agents through 2025. Tech vendors now recognize that offering agentic models alone is insufficient and must help customers engineer full workflows. Vendors assist either by providing forward-deployed engineers who act as consultants and customer-success sherpas or by offering software that simplifies workflow setup. Ensuring AI agents have access to the right information is a key step in those workflows. Since 2023, retrieval-augmented generation (RAG) has been the standard approach for giving agents relevant internal or public data. RAG is commonly implemented with hybrid search methods and vector databases, but it is not a panacea.
Read at Fortune
Unable to calculate read time
Collection
[
|
...
]