Nina Lopatina

Everything Nina Lopatina said on any show that made the record, most notable first. Each card names its show and opens the statement there.

LATENT SPACE Disclosure

Nina Lopatina: Contextual AI shifts from MCP to direct API calls

“And I think for us, for me personally, like in my dynamic agent configs, I'm moving more toward API calls. And something a little bit more once I kind of maybe been able to prototype with an MCP server and figure out how I'm going to use this I think then you …”

Nina Lopatina Dec 31, 2025 ▶ 15:48 [State of Context Engineering] Agentic RAG, Context Rot, MCP, Subagents — Nina Lopatina, Contextual

LATENT SPACE Assertion Supported

Nina Lopatina: Claude Code saturated Princeton's agentic research benchmark within weeks

“It's a set of benchmarks for really evaluating longer-running agentic tasks, and in this case, there was one where they were evaluating, recreating a research paper, and that benchmark came out in October, and it was saturated earlier this week.”

Nina Lopatina Dec 31, 2025 ▶ 10:37 [State of Context Engineering] Agentic RAG, Context Rot, MCP, Subagents — Nina Lopatina, Contextual

LATENT SPACE Insight

Nina Lopatina: Smaller models beat larger ones for latency-constrained component tasks

“I think for other component models, like, let's say, like, for a re-ranker, due to latency constraints, smaller is better, is what I've heard from other developers”

Nina Lopatina Dec 31, 2025 ▶ 2:51 [State of Context Engineering] Agentic RAG, Context Rot, MCP, Subagents — Nina Lopatina, Contextual

LATENT SPACE Insight

Nina Lopatina: Agentic RAG and query reformulation outperform traditional RAG baselines

“Agentic RAG is just generally better than RAG. Even that initial incremental step of making that doing query reformulation, so when you receive that initial query, being able to break it down into sub-queries so that you can better match those queries to docum…”

Nina Lopatina Dec 31, 2025 ▶ 5:07 [State of Context Engineering] Agentic RAG, Context Rot, MCP, Subagents — Nina Lopatina, Contextual

LATENT SPACE Prediction Not checkable as stated

Nina Lopatina predicts context engineering will reach deployment scale in 2026

“So I think it's kind of, to me, maybe more in a prototyping stage, and I'm expecting next year we'll really see scale for context engineering.”

Nina Lopatina Dec 31, 2025 ▶ 10:03 [State of Context Engineering] Agentic RAG, Context Rot, MCP, Subagents — Nina Lopatina, Contextual

LATENT SPACE Opinion

Nina Lopatina: Anthropic's Model Context Protocol heavily drives context engineering

“I think MCP has been a huge driver of context engineering.”

Nina Lopatina Dec 31, 2025 ▶ 14:20 [State of Context Engineering] Agentic RAG, Context Rot, MCP, Subagents — Nina Lopatina, Contextual

LATENT SPACE Assertion Supported

Nina Lopatina: Agentic Context Engineering outperforms prompt-rewriting on complex documents

“So so actually, Identity Context Engineering, that approach actually has shown better benchmark performance on financial and other complex document sets, and the approach they've taken is quite interesting.”

Nina Lopatina Dec 31, 2025 ▶ 18:41 [State of Context Engineering] Agentic RAG, Context Rot, MCP, Subagents — Nina Lopatina, Contextual

LATENT SPACE Insight

Nina Lopatina: Imposing turn limits on sub-agents is critical for reliability

“Having turn limits and limits on the sub-agents checking and validating their work is super important.”

Nina Lopatina Dec 31, 2025 ▶ 6:20 [State of Context Engineering] Agentic RAG, Context Rot, MCP, Subagents — Nina Lopatina, Contextual

One line per show, most statements first. The link opens Nina's full record on that show: the calibration, argument clarity, speaking style and every statement made there.

Show	Role there	Eps	Statements	Record
LATENT SPACELEDGER		1	8	100% 2/2	full record on Latent Space →