High Signal Podcasts Evidence ledger
Method
Browse
How the evidence works
← All source episodes

The Cognitive Revolution / episode intelligence

Write, Change, Recall, Forget: MongoDB's Pete Johnson on How Retrieval Drives Agent Performance

1 Sept 2026 6 published claims 0 attributable people
Open original episode ↗ Read the evidence

Speakers in the public record

Claim mix

evaluation 3preference 1commitment 1belief 1

Evidence policy

Every row below preserves an exact excerpt. Identified speakers are linked; unresolved voices are labeled and excluded from people counts.

Claim ledger

The useful parts, with receipts.

6 published records

01 / evaluation

It's just now you don't have to go through the iterations of figuring out the size of the chunks you need. And similarly, there's another voyage feature that all the voyage all the voyage embedding models have called retroa reasoning because the other place you have to make a decision about storage cost versus retrieval quality is with number of dimensions.

“It's just now you don't have to go through the iterations of figuring out the size of the chunks you need. And similarly, there's another voyage feature that all the voyage all the voyage embedding models have called retroa reasoning because the other place you have to make a decision about storage cost versus retrieval quality is with number of dimensions.”
Speaker
Not verified from transcript
Publisher
The Cognitive Revolution

02 / evaluation

The the cool thing about the vector search is I mean vector search at its core is taking some piece of data and mapping it into n space into some geographical geometric space and then really all a vector search is similarity like where what are the closest vectors to this new thing that I'm searching on and video is a great example audio is a great example unstructured data you just take a bunch of PDFs that you have sitting around in a shareepoint I mean those are good examples samples as well. So yeah, I think that there's there's some truth to that that we're it's not just how do I take the data and put it into a database, but now how do I find it and how do I find it in a way that is fast, is scalable, that's at good quality.

“The the cool thing about the vector search is I mean vector search at its core is taking some piece of data and mapping it into n space into some geographical geometric space and then really all a vector search is similarity like where what are the closest vectors to this new thing that I'm searching on and video is a great example audio is a great example unstructured data you just take a bunch of PDFs that you have sitting around in a shareepoint I mean those are good examples samples as well. So yeah, I think that there's there's some truth to that that we're it's not just how do I take the data and put it into a database, but now how do I find it and how do I find it in a way that is fast, is scalable, that's at good quality.”
Speaker
Not verified from transcript
Publisher
The Cognitive Revolution

03 / preference

the podcast or the transcript of the podcast I should say diorized so it knows what I've said and what the guest has said adds up to about a gigabyte in my case and I haven't really optimized it much at all I just kind of let the agent throw it into a database of its choosing and put whatever optimizations on it it felt like it needed to and then we did get a at one point it was like well yeah we could probably do better than keyword so we've got an embedding layer on there as well. I think full disclosure, I believe I used the Gemini embedding model for that.

“the podcast or the transcript of the podcast I should say diorized so it knows what I've said and what the guest has said adds up to about a gigabyte in my case and I haven't really optimized it much at all I just kind of let the agent throw it into a database of its choosing and put whatever optimizations on it it felt like it needed to and then we did get a at one point it was like well yeah we could probably do better than keyword so we've got an embedding layer on there as well. I think full disclosure, I believe I used the Gemini embedding model for that.”
Speaker
Not verified from transcript
Publisher
The Cognitive Revolution

04 / evaluation

I would worry about any memory architecture that instead of relying on lower cost embedders and rerankers is relying on multiple passes of the LLM to help you categorize and shrink the the the corpus of data that you might want to then put into the context window for the larger sort of more functional LLN call because then that's just adding up tokens as well.

“I would worry about any memory architecture that instead of relying on lower cost embedders and rerankers is relying on multiple passes of the LLM to help you categorize and shrink the the the corpus of data that you might want to then put into the context window for the larger sort of more functional LLN call because then that's just adding up tokens as well.”
Speaker
Not verified from transcript
Publisher
The Cognitive Revolution

05 / commitment

I won't say not malleable at all because it depends on how you're laying out the data, but anybody who's ever had to change a SQL schema that's already in production and the cascading effect that has on multiple tables knows the pain of what I'm talking about that if you had some of that data denormalized, it's far easier to add attributes to a document that's already there and do so selectively in a way that isn't possible nearly to the same extent in the SQL world.

“I won't say not malleable at all because it depends on how you're laying out the data, but anybody who's ever had to change a SQL schema that's already in production and the cascading effect that has on multiple tables knows the pain of what I'm talking about that if you had some of that data denormalized, it's far easier to add attributes to a document that's already there and do so selectively in a way that isn't possible nearly to the same extent in the SQL world.”
Speaker
Not verified from transcript
Publisher
The Cognitive Revolution

06 / belief

Now, there still are use cases where you need to control the chunk size for different things, but if that's something that you wanted to not worry about or have to learn about, and the way I think about this is more developers will build AI agents in the next three years than did in the last 3 years.

“Now, there still are use cases where you need to control the chunk size for different things, but if that's something that you wanted to not worry about or have to learn about, and the way I think about this is more developers will build AI agents in the next three years than did in the last 3 years.”
Speaker
Not verified from transcript
Publisher
The Cognitive Revolution
Search evidence