Technology thesis · Artificial Intelligence
high conviction growthRetrieval-augmented generation (RAG)
RAG has become the standard architecture for enterprise LLM deployment, enabling models to access private data without retraining.
Position maintained continuously · last reviewed Apr 22, 2026
The thesis
Core thesis
RAG solves the fundamental enterprise LLM problem: models need access to private, current data that wasn't in their training set. LlamaIndex and LangChain provide the infrastructure. Vector databases (Pinecone, Weaviate) store embeddings. Enterprise RAG is a multi-billion dollar market. The challenge: RAG quality depends on chunking strategy, embedding model, and retrieval precision — it's engineering, not research.
State of the art (2026)
By mid-2026, naive vector RAG is a baseline, not a finished system. The default production pattern is hybrid retrieval (semantic plus keyword) followed by a reranking pass, with agentic RAG – a reasoning loop that decomposes the query, retrieves, critiques and retrieves again – now standard for hard questions. Microsoft GraphRAG, open-sourced in 2024, earns its cost on cross-document, connect-the-dots queries, and adaptive routing of each query to the cheapest sufficient pipeline is the emerging best practice. Long context has not killed RAG: Claude Opus and Sonnet 4.6 and Gemini 3 Pro all ship 1M-token windows, yet recall degrades past roughly 600-700K tokens, so retrieval still grounds enterprise systems. Glean ($7.2B, ~$300M ARR) anchors the productised layer.
Everything below is live inside CanaryIQ
The full analysis behind the verdict — the structure is real; the content unlocks when you log in.
Signal stack
Evidence stacked leading → lagging
Technology-native KPIs
Metrics that predict trajectory, tracked over time
Landscape map
Who builds what — and who depends on whom
Catalyst calendar
Dated events that will move the position
Technology roadmap
Milestones on the path to maturity
Watchlists
Companies, people and papers — each with a remove-by condition
Decision frameworks
The same call, framed for your desk
Thesis changelog
When our view changed, and why
Change our mind
3 disconfirming conditions
The rest is inside
You've read the verdict. The file is much deeper.
The full signal stack, technology-native KPIs tracked over time, the landscape of who depends on whom, the dated catalyst calendar, decision frameworks for every desk, live watchlists and the changelog of every time our call on Retrieval-augmented generation (RAG) has changed — all live inside CanaryIQ.