Software Engineering Daily · Thursday, September 3, 2026
Yorg Schad emphasizes that Nexus's approach of precomputing context, akin to materialized views, leads to more reproducible and reliable results from AI agents. This contrasts with on-the-fly retrieval, which can yield inconsistent answers due to the probabilistic nature of LLMs.
“Second aspect of that, also with materialized views, I simply I get more reproducible results, right?”
“They're choosing something on the fly and so if I actually care about reproducible results, if I'm asking my data bot about a question, what has been the revenue last year? I really want a consistent answer over time.”
“So I think that kind of reproducibility is another important piece, which makes it more reliable, and with that, I think I'm also getting this audit trails, I'm getting lineage trails.”