WorkshopScoped individually
RAG and Data Readiness Workshop
A workshop with your team on whether your documents and data suit an AI assistant with retrieval (RAG) and what must be prepared.
Domain C · AI systems
AI Applications & Knowledge Systems
We build AI applications that answer from your own documents and data, with sources, permissions and measured quality. That includes internal assistants, document analysis and AI features inside existing products.
Status:AvailableThere is a service page, an intake path and a documented way of delivering it.
Who it is for
- Companies whose knowledge sits in documents, wikis and tickets.
- Teams that process contracts, invoices or forms.
- Product teams adding AI features to an existing application.
AI Applications & Knowledge Systems
Problems it addresses
Employees cannot find answers.
Repetitive questions to the same experts.
Manual reading of documents.
AI demos that hallucinate or ignore permissions.
AI Applications & Knowledge Systems
Service families and capabilities
The status shows what we offer today. Pricing is set once the scope is clear, in a written quote.
Retrieval-augmented assistants (RAG)
AvailableIngestion, chunking, embeddings, hybrid search, access-aware retrieval, cited answers, “no source, no answer”.
Document analysis and extraction
AvailableClassification, field extraction with confidence, validation rules, human review queues.
AI features in products
AvailableSummarisation, drafting, classification and search inside your application, behind feature flags.
Evaluation and quality engineering
Custom engagementTest sets, retrieval and answer metrics, regression gates in CI.
Model adaptation
Custom engagementPrompt and tool design first; fine-tuning only with a demonstrated need and sufficient data.
AI Applications & Knowledge Systems
Workshops and assessments
Consultant-led formats with a clear scope that we usually start with.
What you receive and keep
- An ingestion pipeline.
- Index design with permission filtering.
- An application or API.
- An evaluation set with baseline results.
- Monitoring of cost and latency.
- Data-handling documentation.
How we engage
Assessment
A fixed-scope review with written findings, risks and a prioritised plan.
Workshop
Half a day to two days with your team; decisions and a written summary.
Architecture
Target design, decision records, interfaces, security model and an estimate of the work.
Implementation
Built and tested increments with acceptance criteria and handover documentation.
Managed service
Through Managed AI & Platform Operations
Pricing is set once the scope is clear and is provided in a written quote.
What we need from you
- Access to the source documents and their permission model.
- A content owner who confirms what is authoritative.
- Agreed data-processing terms with the model provider.
What we do not do or promise
- Quality depends on the source documents.
- We do not train foundation models.
- No guarantees of factual accuracy; answers without a source are refused by design.
- Regulated or special-category data only after a data processing agreement and a risk assessment.
Related domains
Data & Integration Engineering
Connected systems and usable data: API integrations, synchronisation, event flows and data models.
AI Governance, Security & Assurance
Safeguards around AI systems that can be checked: permissions, data, quality evaluation and incident handling.
Cloud & Platform Engineering
Cloud infrastructure as code: environments, containers, databases, secrets, backups and cost control.
Managed AI & Platform Operations
Ongoing operation of what has been built: monitoring, maintenance, evaluation, cost and incidents.
Related tools
Start with a quick self-assessment before we talk.
- Available now
Architecture
AI solution builder
Compose a solution from agents, integrations and approval points and get an architecture diagram to discuss.
- For:
- Technical leads and product teams
- You get:
- An architecture diagram of the solution with agents, integrations and approval points.
- Time:
- about 5 min
Discuss an AI application for your data
Describe your task. We will clarify the scope and the engagement model and send a written quote.
- Written quote with a clear scope
- Transparent milestones and timelines
- Your data is used only to reply to you