index f66304b..94f1e97 100644
@@ -15,4 +15,4 @@ a deep research pipeline where an AI agent doesn't just retrieve results but act
the adaptive feedback piece is what distinguishes this from just chaining search calls. the agent maintains a model of what it knows and what it doesn't — essentially a knowledge graph of the research question — and uses that to drive the next query. it also asks the user targeted clarifying questions when the research direction is genuinely ambiguous, rather than picking an interpretation silently. the output isn't a list of links but a synthesized answer with explicit sourcing, confidence levels, and a statement of what couldn't be verified. this is closer to how a good research assistant operates than any current search product.
-connects to [[life-search|life search]] which applies the same search depth to personal data rather than the web. [[dense-info-generator|dense info generator]] is adjacent — generating a comprehensive briefing is the output format of a successful agentic search run. [[quality-search|quality content search]] is a related problem: the agentic searcher needs to evaluate source quality to weight its synthesis correctly. [[spec-driven-dev|spec-driven dev kit]] uses a similar plan-then-implement pattern in the coding domain. [[b2b-competitive-analysis|B2B competitive analysis]] is a specific application — competitive intelligence is exactly the kind of multi-hop research question this architecture handles well.
\ No newline at end of file
+related: [[life-search|life search]], [[dense-info-generator|dense info generator]], [[quality-search|quality content search]], [[spec-driven-dev|spec-driven dev kit]], [[b2b-competitive-analysis|B2B competitive analysis]]
\ No newline at end of file