Service / AI
RAG that cites its sources, every time.
Retrieval-augmented generation over your documents and data: hybrid search, reranking and answers that cite the passage they came from, or say they cannot answer.
[ 01 ]The short answer
What is RAG Development?
RAG (retrieval-augmented generation) answers questions from your own documents instead of a model's memory. An ingestion pipeline parses and indexes your sources; at question time, hybrid search finds candidate passages, a reranker orders them and the model answers from those passages with citations. Done well, it keeps answers current and checkable without retraining. Done carelessly, it still invents things, so we measure retrieval and answer quality separately and teach the system to abstain.
What you get
- Ingestion and indexing pipeline
- Retrieval API with hybrid search and reranking
- Chat or search interface with citations
- Evaluation set and dashboard
- Access-control integration
[ 02 ]What we build
The pieces, built to last.
- 01
Ingestion pipelines
Parsing for PDFs, scans, slides, code and tables, with structure-aware chunking that keeps meaning intact.
- 02
Hybrid retrieval
Vector and keyword search fused, because questions mix concepts with exact names and numbers.
- 03
Reranking
A cross-encoder reorders candidates, so the model reads the best evidence first.
- 04
Cited answers
Every claim links to a document, page and passage. Unsupported claims are dropped before the user sees them.
- 05
Permissions-aware search
Access rights travel with every chunk, so retrieval never shows a user what they are not allowed to see.
- 06
Retrieval evaluation
Recall, precision and faithfulness measured on your questions, per source and per question type.
[ 03 ]Where it pays off
Where it earns its keep.
- 01
Internal knowledge assistant
Policies, wikis and tickets answered in seconds, with the source one click away.
- 02
Customer support
Answers drafted from product docs and past resolutions, with uncertain cases escalated.
- 03
Legal and compliance review
Contracts and regulations searched by meaning, with verbatim quotes for every finding.
- 04
Technical due diligence
Code, specs and audits queried in plain English, cited to the exact lines.
[ 04 ]How we deliver
Four steps, one team, start to finish.
The same people scope it, build it and stay after launch. Timings are typical for a first release; we agree yours after the deep dive.
- 01Week 1
Find the decision
We pick the decision or task worth automating, measure how it is done today and agree what better means in numbers.
- 02Week 1 to 2
Build the eval first
A labelled test set from your own data comes before any prompt or training run, so every change is scored, not argued.
- 03Weeks 2 to 10
Build with guardrails
Models suggest, code decides. Permissions, injection checks, human override and audit logs are part of the first version.
- 04Ongoing
Ship and improve
We launch to real users, watch cost, latency and quality per request, and feed failures back into the eval set.
[ 05 ]Stack
Tools we reach for.
Chosen per project, and we work in yours. Nothing here is a lock-in: you own the code and the accounts.
- pgvector
- Postgres full-text
- Elasticsearch
- Qdrant
- Cohere Rerank
- BGE embeddings
- Unstructured
- LlamaIndex
- Claude citations
- Ragas
[ 07 ]Further reading
Problems we found, and how we would solve them.
- Retrieval3 min read
RAG still hallucinates. Grounding takes more than retrieval
ProblemRetrieval-augmented systems still invent facts, cite passages that do not support the claim, miss the decisive document and agree with false premises.ProposalTreat grounding as a pipeline with checks: structure-aware chunking, hybrid retrieval and reranking, citations at passage level that are verified after generation, abstention when evidence is missing, and evaluation of retrieval and answers separately.Read the proposal - Models3 min read
Fine-tune, retrieve or prompt? A decision guide
ProblemTeams pick fine-tuning, RAG or custom training by reputation rather than by what the problem needs, and spend months on the wrong one.ProposalDecide by what must change: prompts for instructions, retrieval for knowledge that changes or must be cited, fine-tuning for behaviour, format and cost, and custom models only where the task or data is truly unusual; always prove it on an evaluation set.Read the proposal
[ 08 ]FAQ
Questions buyers ask.
It reduces them, but it does not stop them on its own: a Stanford study found commercial legal RAG tools still erred on 17 to 34 percent of queries. Citation checks, abstention and evaluation close most of the remaining gap.
Often the one you already run. Postgres with pgvector handles millions of chunks and keeps joins and permissions simple. We move to a dedicated engine only when measurements say so.
Yes. Indexing, embeddings and even the model can run inside your network. See private LLM deployment.
[ 09 ]More AI services
- Custom AI Model DevelopmentA model trained on your data, owned by you.
- LLM Fine-Tuning and DistillationFrontier quality at a fraction of the cost.
- AI Agent DevelopmentAgents that finish the job, inside the rules.
- AI Workflow AutomationHours of back-office work, done in minutes.
- AI Memory and Knowledge GraphsAI that remembers what your organisation learned.
- MCP Server DevelopmentYour product, usable by every AI assistant.
- Voice AI AgentsEvery call answered, qualified and logged.
- Document AI and Intelligent Document ProcessingPaperwork turned into clean, checked data.
- Private LLM DeploymentAI on your infrastructure, data never leaves.
- LLMOps, Evaluation and GuardrailsKnow your AI works before customers find out.
- Predictive ML and ForecastingDecisions made on what will happen next.
One company at a time