OpenAI case study: V7 Go gives enterprise agents long-term memory via Context Graph

xiaohu · x · 2026-09-22

OpenAI published a case study on V7 Go, the enterprise agent platform from European startup V7, tackling why enterprise agents behave like first-day hires: they don't know which document is current, whether entities across systems are the same, or which source backs a conclusion.

The approach: pre-extract entities, relations, facts and citations into a source-referenced Context Graph, falling back to document-level RAG when the graph is insufficient; recent conversations stay in context while older material is retrieved from the graph. Execution is tiered by difficulty—Luna for high-throughput extraction, Terra/Sol for complex tool calls, Astra for hard graph queries—with reported improvements in cost, error rate and complex-query accuracy.

The architecture fits businesses dense in cross-document relations where every conclusion must trace to evidence; simple Q&A is better served by plain RAG.

Original post →

More from coding & agent

coding & agent channel →