Intelligence [music] isn't

one-size-fits-all.

AI agents are built with many models,

each bringing different [music]

strengths to the work.

Some tasks call for deep reasoning.

Others demand speed, lower costs, domain

expertise, [music]

or stronger data control.

Frontier models provide state-of-the-art

reasoning for the hardest [music] tasks.

Open models can be fine-tuned on company

data to excel [music] at specialized

work.

They can also run on premises, helping

keep sensitive data secure while

reducing latency for high-volume tasks.

>> [music]

>> Glean uses the system of models approach

to help enterprises search and act on

their data.

Waldo, a specialized model post-trained

[music] on NVIDIA NeMo Triton 3 Nano,

gathers context across sources like

support tickets, Slack, [music] and

survey data.

With that context, it decides whether

the agent should respond directly

[music]

or hand off to a frontier reasoning

model for deeper analysis.

For simple questions, Waldo delivers all

the context to a model that returns the

answer in one shot.

The response is fast.

If the question is more complex, Waldo

sends the task to a frontier model that

reasons deeper. Because the [music]

frontier model receives the right

context upfront, it can produce

structured analysis with themes,

evidence, and segment breakdowns more

efficiently.

Routing lets Glean [music] search

enterprise context 10 times faster.

This translates to 50% lower latency and

25% [music] fewer tokens with no

reduction in answer quality.

In a system of models, frontier and open

models work together [music] to make

your agent smarter, faster, and more

efficient.