Rag: implementation and integration

19–30%of the workday is spent searching for information (McKinsey / IDC) — that is exactly the market RAG addresses

74% → 89%recall@10: the share of cases where the correct answer lands in the top results after adding reranking (Databricks)

+33–40%answer accuracy from cross-encoder reranking at +~120 ms latency (RAG research)

40–50%of routine requests are resolved by support with sources in the answer, freeing up people (RAG support benchmark)

AI layer

An AI assistant must take action, not just reply with text

Core thesis of the AI block: a pilot with measurable impact, private data under control, agent actions logged, quality passes evals before scaling.

1-2 hof daily routine the assistant takes off an employee or manager

2-4 wksenough for a pilot on one process with an impact metric

40%of agentic AI projects Gartner expects to be canceled without clear value

Assistant ≠ chatbot

A chatbot answers; an assistant checks the regulations, queries systems, records the deviation and proposes the next step.

Control plane

Agent registry, owner, permissions, memory, evals, trace logs, kill-switch and budget at the enterprise-layer level.

Data

RAG returns an answer with a source citation; LLM Gateway obfuscates personal data before the model and restores it after the response.

Processcorporate memoryagentaction in the systemlogs and evals

Internal links

Agent governance layer RAG with sources LLM Gateway and personal data

Sources

Anthropic: Building effective agents Gartner agentic AI cancellations Chip Huyen: AI Engineering

Industry solutions

What you can build with RAG

All Solutions

Manufacturing LLM-wiki over technical regulations, GOST standards, equipment and occupational-safety manuals, with answers citing the source document Engineers and operators finding the right procedure: from minutes to seconds, with no risk of working off an outdated versionLearn more →Retail and e-commerce RAG over product cards, return policies and FAQs for customer support and content managers Request handling and content prep: 40–50% of routine questions are resolved automatically with a sourceLearn more →Logistics Knowledge base on tariffs, routes, customs and warehouse regulations with grounded answers Dispatcher and customer service answers on shipping rules without escalations to expertsLearn more →Finance and Insurance RAG over regulations, product terms and compliance documents, with a mandatory citation to the exact clause Consulting and compliance checks: answers are verifiable and auditable, hybrid RAG reduces hallucinationsLearn more →Development and real estate LLM-wiki over project documentation, contracts and property sales policies Managers finding terms for a site and deal without going through legal and the project teamLearn more →IT and support Internal assistant over runbooks, the incident base and internal regulations for support agents Resolving a ticket: time to find the right process and escalation matrix drops from 8–10 minutes to secondsLearn more →HR and onboarding Corporate LLM-wiki on company policies, benefits and procedures for employees Onboarding and HR questions: a new hire finds the answer themselves, load on the HR line dropsLearn more →Legal and compliance teams RAG over the contract base, precedents and internal policies, with provenance for every answer Drafting opinions and reviewing contracts: every answer is tied to a specific document and clauseLearn more →

Capabilities

RAG capabilities

Sources: wiki, regulations, product data, databasesChunking + embeddingsVector store (pgvector / Qdrant)User queryRetrieval: top-k candidatesReranking (cross-encoder): top-nLLM with grounded contextAnswer + link to source (provenance)

A linear diagram of the anti-hallucination loop. On the left, knowledge sources (wiki, regulations, product data, databases) → chunking and embeddings → vector store (pgvector / Qdrant). The user query goes into retrieval (top-k candidates) → cross-encoder reranking (top-n best) → the LLM gets only the selected context → an answer with a link to the source. The model answers ONLY from the retrieved context, not from its memory; the provenance arrow leads from the answer back to the source document. The loop is loosely coupled — each block (store, retrieval, reranker, LLM) is replaceable independently.

Retrieval over corporate sources

The model answers from your documents, wiki and databases, not from internet "memory" — an employee gets the answer in seconds instead of hours of search across the 19–30% of the day that gets lost.

Grounding and source citations

Every answer shows which document it came from — answers are verifiable, and hallucinations are cut off at the architecture level, not by coaxing the model.

Vector store (pgvector / Qdrant)

Semantic search over millions of chunks: finds the answer by meaning, not by exact word match. pgvector when the data is already in Postgres, Qdrant when you need high-load search with filters.

Chunking and content preparation

Documents are split into meaningful chunks with metadata — the model gets "less but more precise" context, which directly raises relevance and lowers query cost.

Reranking (cross-encoder)

The second stage reorders candidates by real relevance: recall@10 rises from 74% to 89%, answer accuracy by 33–40% in ~120 ms. High ROI at minimal latency.

LLM-wiki — a layer of verified answers

An add-on to RAG: on top of the stack we maintain a vetted corporate wiki, and for critical questions the system returns a pre-verified answer — cutting hallucinations even further.

RAG for support and employees

40–50% of routine requests are resolved automatically with a source in the answer; the internal assistant cuts regulation lookup time from minutes to seconds.

A loosely coupled, detachable stack

Storage, retrieval and model are decoupled: swap the LLM or vector DB without rewriting everything. The solution moves easily between teams and contractors — no vendor lock-in.

Quality evaluation and anti-hallucination

precision@K, provenance coverage and hallucination rate metrics are built into the pipeline — answer quality is measured, not declared, and does not silently degrade after changes.

Approach

How we implement RAG

Minimal core modification

We don't fork or patch the RAG core. RAG stays on the standard upgradable version — business logic goes into separate microservices alongside it, so platform updates don't break your customizations.

International Standards, Not Homegrown Hacks

Where a mature international solution exists, we use it instead of inventing our own protocol or platform. Before writing code, we study how the problem is already solved in the industry.

Transferability

The solution is loosely coupled and documented: it can be handed over between teams and contractors without rewriting. You are not tied to us.

AI compatibility

RAG in the AI stack

Grounding for any LLM

The RAG layer feeds verified context into the model (GPT, Claude, open-source) — grounding answers in your data no matter which LLM you use today or switch to tomorrow.

Integration with MCP / the context layer

We connect the corporate knowledge base to agents via MCP as a standard source: RAG owns "what we know", MCP owns "how the agent fetches it". Both layers are detachable and reusable.

Operating behind the LLM & Security Gateway

Retrieval and model calls pass through a gateway: model routing, budgets, observability and PII obfuscation before sending — corporate knowledge does not leak out.

Foundation for AI agents

Agents that serve users and enter data rely on RAG as the source of truth — turning a "chatty" assistant into a tool that answers from company facts.

Integration with the Sloy platform

RAG/LLM-wiki embeds into Sloy as a corporate-memory layer for enterprise agent management: a single knowledge store, grounding and provenance shared across multiple agents and scenarios.

Blog