---
type: "post"
id: "sarvam-s-knowledge-fabric-compiles-enterprise-docs-into-4ffcbd"
slug: "sarvam-s-knowledge-fabric-compiles-enterprise-docs-into-4ffcbd"
title: "Sarvam's knowledge fabric compiles enterprise docs into a navigable tree plus a typed domain ontology."
description: "Sarvam AI has described a “knowledge fabric” for enterprise agents that compiles documents and data into two layers: a navigable knowledge tree and a typed domain ontology."
retrieval_nugget: "Sarvam AI has described a “knowledge fabric” for enterprise agents that compiles documents and data into two layers: a navigable knowledge tree and a typed domain ontology."
published_at: "2026-10-26"
updated_at: "2026-10-26"
record_date: "2026-10-26"
date_kind: "published_at"
topics: ["enterprise-agents"]
entities: ["Sarvam AI","Knowledge Fabric","Model Context Protocol","Sarvam Vision 2.1","GLM 5.3","GLM 5.2","Harvey LAB","tau-knowledge"]
related_patterns: ["company-memory-needs-write-loops","agent-protocols-become-interoperability-layer","agent-ready-software-exposes-capabilities"]
novelty_label: "new_fact"
what_changed: "Sarvam describes a new enterprise knowledge fabric that compiles documents into a structured, navigable layer, reporting 84.2% rubric performance on Harvey LAB at lower cost and matching tau-knowledge accuracy with 64% fewer tokens."
prior_refs: ["memory:3d5ce341-6554-8510-a552-615b19c173a8","memory:2c092c7b-368d-87be-a226-c21e86d04a87","memory:68145a6d-bb19-84e1-a970-d063708eb4b6"]
source_url: "https://www.sarvam.ai/blogs/knowledge-fabric-enterprise-agents"
source_urls: ["https://www.sarvam.ai/blogs/knowledge-fabric-enterprise-agents"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:sarvam-s-knowledge-fabric-compiles-enterprise-docs-into-4ffcbd"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/sarvam-s-knowledge-fabric-compiles-enterprise-docs-into-4ffcbd/","markdown":"https://newruntime.com/posts/sarvam-s-knowledge-fabric-compiles-enterprise-docs-into-4ffcbd.md","json":"https://newruntime.com/posts/sarvam-s-knowledge-fabric-compiles-enterprise-docs-into-4ffcbd.json"}
---

# Sarvam's knowledge fabric compiles enterprise docs into a navigable tree plus a typed domain ontology.

## Retrieval answer

Sarvam AI has described a “knowledge fabric” for enterprise agents that compiles documents and data into two layers: a navigable knowledge tree and a typed domain ontology.

Sarvam AI has described a “knowledge fabric” for enterprise agents that compiles documents and data into two layers: a navigable knowledge tree and a typed domain ontology. The tree organizes a corpus into folders, indexes, document summaries, page ranges and tables; the ontology represents domain entities and their relationships.

According to the company, the tree is served over MCP. An agent can list folders, read indexes, search the corpus, open page ranges and inspect tables. Sarvam says citations link back to a passage, image or table row in the original source. Its parsing pipeline converts files to Markdown and uses Sarvam Vision 2.1 for scanned pages, complex layouts, tables and Indic scripts.

The post reports 84.2% of expert-rubric criteria met on Harvey LAB with GLM 5.3, compared with 55.1% for agentic RAG; it reports average task cost of $0.28 versus $0.64. On Sierra's tau-knowledge banking benchmark, it says the fabric matched baseline accuracy with 64% fewer tokens using GLM 5.2. It also reports navigation gains across four public benchmarks, including 91.3% versus 75.5% on BrowseComp-Plus.

The source does not establish general availability, pricing, customer deployment details, or independent validation of the benchmark comparisons.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Enterprise Agents](https://newruntime.com/topics/enterprise-agents.md): Explore the enterprise-agents topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)