Why the Best Reranker Can't Fix Bad Retrieval

Oct 13, 2026, 10:00am PT | 1:00pm ET

Most teams solve slow, imprecise AI search the same way: retrieve a large candidate set and send it through a bigger model to rerank it into shape. It works, until the dataset, the traffic, and the model bill all grow at once, and the fix that used to work becomes the most expensive line in the stack. The deeper problem sits earlier in the pipeline. No reranker, however capable, can recover a relevant result that retrieval never surfaced in the first place. If the right passage isn’t in the candidate set, ranking it well was never on the table, whether the thing reading the results is a person or an agent deciding what to do next.

In this session, Bonnie Chase and Jenny Morris from Vespa.ai will walk through how to design retrieval as a funnel instead of a single expensive pass: efficient candidate generation first, progressive narrowing through lexical, vector, and hybrid retrieval, and the most expensive ranking models reserved for the candidates where they can actually change the outcome. You will find out where teams get this boundary wrong in production and how the tradeoffs between latency, compute, and relevance actually get decided at each stage.

Key Takeaways

Why reranking everything is a symptom of a retrieval problem, not a fix for one
How to design retrieval and ranking as a multi-stage funnel instead of a single expensive pass
Where lexical, vector, and hybrid retrieval each earn their place in that funnel
How retrieval and ranking change when an agent and not a person is iteratively searching, evaluating evidence, and deciding what gets passed into context
How to tell where expensive ML inference actually adds value, and where it’s just cost

Can’t join us live? Register anyway and we’ll send you a recording after the session. By registering, you consent to receiving email communications from The New Stack and Vespa.ai. You may opt out at any time.

FILL THE FORM BELOW

First Name *

Last Name *

Company Street Address *

Company Suite/Office *

Company Postal/Zip Code *

Company City *

Company State *

Company Country *

By submitting this content request, I have legitimate interest in the content and agree that The New Stack + Vespa.ai, their partners, and the creators of any other content I have selected may contact me regarding news, products, and services that may be of interest to me.

YesNo

By registering, you consent to the TNS Privacy Policy and to receiving email communication from The New Stack and Vespa.ai. You may opt out at any time.

Which best describes your current retrieval setup?