LLM Evaluation Health Check
Find out where one RAG or agent workflow fails, why, and what to fix first.
- Price
- EUR 2,950 excl. VAT Fixed project fee
- Time
- About 5 working days
- Scope
- One RAG or agent workflow, up to 50 test cases
A working Neo4j and GraphRAG prototype on your own data, with evaluations built in.
At a glance
Contracted with and invoiced by MILEAWAY AI SYSTEMS LIMITED.
Teams that have decided a knowledge graph is worth testing and want a working prototype on their own data, not a slide deck.
Knowledge graph projects often stall between the diagram and the first useful query. A focused prototype answers the practical questions: what the graph model looks like, how the data gets in, and whether it actually improves the answers your users need.
Limits. A prototype shows whether the approach works on your data. It is not production-hardened: security review, scaling and monitoring for production are scoped separately.
Prices are in euro and exclude VAT, which is added where applicable. Any third-party costs, such as model or cloud usage, are confirmed in the quotation. Engagements are contracted with and invoiced by MILEAWAY AI SYSTEMS LIMITED.
Send me what you want the prototype to prove and the data involved. I'll reply to arrange a discovery call, then send a written scope and quotation.
We agree the data slice, the questions the prototype must answer and how success will be measured. You receive a written scope and fixed-price quotation.
I design the graph model with your team and load the agreed data into Neo4j.
I build GraphRAG retrieval for the agreed questions and evaluate it against the agreed cases and a simpler baseline.
Code, documentation and results, walked through with your team, with a clear view of what it would take to go further.
I've built AI systems in financial services and insurance, and I speak and write in public about evaluating LLMs and putting knowledge graphs to work. You can check all of it.
Speaker, NODES 2025
Building Contextual Knowledge Graphs to Adapt, Evaluate, and Leverage LLMs
Watch the session on YouTubeRecognition
Neo4j Featured Community Member, November 2025
Read the feature on neo4j.comWriting
Evaluating a Fine-Tuned LLM Using a Knowledge Graph and Ground Truth Data
Read the article on MediumExperience
Production AI, including financial services and insurance
Experience on LinkedInNo. The prototype is built on Neo4j, in your environment or an agreed sandbox. If you already run Neo4j, I build on your existing graph where that makes sense.
Every sprint includes agreed evaluation cases and results, so the decision to go further rests on evidence rather than a demo.
Ownership of the code and other deliverables is set out in the contract before work starts.
It is built to be extended, but it is a prototype. Production work is scoped separately once you have seen the results.
Access, data handling and confidentiality terms are agreed in writing as part of the scope, before any work starts. I only ask for the access the agreed work needs.
Find out where one RAG or agent workflow fails, why, and what to fix first.
An independent view on whether a knowledge graph will improve your retrieval, before you commit engineering time.
Contact
Book a 30-minute call, or send a few lines about what you're building and what's going wrong.