RAG as a service for maintained knowledge
CorpusMesh is a managed RAG service for authoritative knowledge that must stay current. We maintain source boundaries, versions, retrieval indexes and citations while your application keeps control of its model and user experience.
Private beta. Access is reviewed manually and public retrieval is not available.6
Source operationsSource-specific monitoringreview before activation
Corpus boundaryBounded for one workflowsize and update cost approved first
Evidence returnedRanked passages + citationsversion and source metadata
Customer controlYour model and UX stay yoursone named application
Exhibit A
Query: “How do Article 6 and Annex III work together to identify high-risk AI systems?”
Official authority, canonical URL, rights evidence and checksum recorded before anything is indexed.
Chunking and retrieval profile are sealed into an immutable version. Activation needs review, evaluation and rollback readiness.
Ranked passages are returned only from the authorized version and the filters your entitlement allows.
Each passage keeps its citation label and source anchor, so your application can show where the context came from.
Private-beta portfolio
Every listed knowledge base is available through our private-beta programme, with coverage scoped to your product, jurisdictions, and update requirements.
Featured private beta
Traceable regulatory material for financial products operating across US and European markets.
Education private beta
27,015 indexed curriculum points, with a sealed 108-query Drafted evaluation reporting zero cross-boundary hits.5
All private betas
Finance, trade, procurement, filings, regulation, and education, qualified around one approved workflow.
Maintained, versioned, attributable
Where CorpusMesh fits
CorpusMesh handles the source and retrieval layer for bounded authoritative domains. It does not replace the product, model, or judgment your team owns.
What CorpusMesh manages
What CorpusMesh does not do
Service boundary
| Responsibility | Internal document RAG | CorpusMesh |
|---|---|---|
| Primary sources | Your organization's files and uploads | Approved authoritative external sources |
| Updates | Your team detects changes and reindexes | CorpusMesh monitors, reviews, versions, and activates |
| Retrieval evidence | Depends on your implementation | Source anchors, versions, checksums, and evaluation |
| Answer generation | Your application | Your application |
Exhibit B
Published evaluation · 80 fixed queries. This is one evaluated EU AI Act workload, not a universal quality claim.2
The knowledge layer
CorpusMesh owns the difficult pipeline so your team can focus on prompts, agents and product behavior.
One verified implementation
The EU AI Act proves the shared factory: collection, provenance, structure, retrieval evaluation, activation, and rollback.
Inspect the verified exampleRetrieval profiles
Dense, lexical, hybrid and reranked retrieval can be versioned per knowledge base.
Illustration, not a measured result.
Access control
Entitlements, filters, bounded responses and exposure monitoring are part of delivery.
Exhibit C
From the original document to the exact retrieved chunk, each result carries its authority, version, checksum and citation path. The published benchmark and trace remain pinned to the reviewed v1 artifact; v2 is active internally and has not been authorized as a public trace.1
Published passages · v1 2026-08-21.1 · 5 of 10 shown
2. In addition to the high-risk AI systems referred to in paragraph 1, AI systems referred to in Annex III shall be considered to be high-risk.
1. Irrespective of whether an AI system is placed on the market or put into service independently of the products referred to in points (a) and (b), that AI system shall be considered to be high-risk where both of the following conditions are fulfilled: (a) the AI system is intended to be used as a safety component of a product, or the AI system is itself a product, covered by the Union harmonisation legislation listed in Annex I; (b) the product whose safety component pursuant to point (a) is the AI system, or the AI system itself as a product, is required to undergo a third-party conformity assessment, with a view to the placing on the market or the putting into service of that product pursuant to the Union harmonisation legislation listed in Annex I.
High-risk AI systems pursuant to Article 6(2) are the AI systems listed in any of the following areas:
High-risk AI systems referred to in Article 6(2)
3. By derogation from paragraph 2, an AI system referred to in Annex III shall not be considered to be high-risk where it does not pose a significant risk of harm to the health, safety or fundamental rights of natural persons, including by not materially influencing the outcome of decision making. The first subparagraph shall apply where any of the following conditions is fulfilled: (a) the AI system is intended to perform a narrow procedural task; (b) the AI system is intended to improve the result of a previously completed human activity; (c) the AI system is intended to detect decision-making patterns or deviations from prior decision-making patterns and is not meant to replace or influence the previously completed human assessment, without proper human review; or (d) the AI system is i
Built for your stack
Send a raw query and structured filters. The prepared private-beta REST boundary returns ranked passages, source metadata and citations.3
POST /v1/retrieve · request body
{
"knowledge_base": "eu-ai-act-reference",
"query": "How do Article 6 and Annex III work together to identify high-risk AI systems?",
"filters": {
"language": [
"en"
],
"jurisdiction": [
"eu"
]
},
"top_k": 5,
"profile": "active"
}Private-beta key required, issued after manual approval
: "${CORPUSMESH_API_KEY:?Set CORPUSMESH_API_KEY first}"
curl --silent --show-error --fail-with-body https://corpusmesh.com/v1/retrieve \
--request POST \
--header "Authorization: Bearer $CORPUSMESH_API_KEY" \
--header "Content-Type: application/json" \
--header "Idempotency-Key: request-article-6-001" \
--data '{
"knowledge_base": "eu-ai-act-reference",
"query": "How do Article 6 and Annex III work together to identify high-risk AI systems?",
"filters": {
"language": [
"en"
],
"jurisdiction": [
"eu"
]
},
"top_k": 5,
"profile": "active"
}'Shape from the API reference · values from the published v1 trace
{
"version": "2026-08-21.1",
"results": [
{
"text": "2. In addition to the high-risk AI systems referred to in paragraph 1, AI systems refe…",
"citation": {
"label": "Article 6 Classification rules for high-risk AI systems",
"source_anchor": "https://eur-lex.europa.eu/eli/reg/2024/1689/oj/eng#art_6",
"source_snapshot_id": "<source-snapshot-uuid>"
},
"metadata": {
"language": "en",
"jurisdiction": "eu",
"verification_status": "verified"
}
}
],
"abstention": {
"decision": "answer"
},
"trace_id": "ret_<trace-id>"
}200 OK 5 passages · 5 citations · reviewed trace
Two ways to use CorpusMesh
The same versioned infrastructure connects teams building AI products with the sources those products need.
01
Ship grounded product experiences without owning the full knowledge pipeline.
02
Prepare maintained collections for controlled delivery to AI applications.
Reviewed v1 artifact 2026-08-21.1, reviewed 2026-08-21 by CorpusMesh product and source review. Shows 5 of 10 retrieved passages with runtime-observed scores.
80 fixed queries on the EU AI Act v1 reference. Recall@10 96.2%, nDCG@10 82.0%, 0 boundary violations. One evaluated EU AI Act workload, not a universal quality claim.
The private-beta REST boundary returns ranked passages, source versions, citations and an answer or abstain decision. It does not generate the final answer.
Version 2026-08-24.3 is verified internally (2026-08-24): 105 sealed fixtures, 0 boundary violations, 2,298 active chunks. Not a public trace; customer access disabled, v1 retained for rollback.
27,015 indexed curriculum points and a sealed 108-query Drafted evaluation reporting zero cross-boundary hits. Coverage is configured per jurisdiction.
Private-beta access is approved against one application, its source set, version, service boundary, and final access contract. Public retrieval is not available.
CorpusMesh
Private beta. Access is reviewed manually and public retrieval is not available.