GraphRAG Readiness Assessment
An independent view on whether a knowledge graph will improve your retrieval, before you commit engineering time.
- Price
- EUR 2,950 excl. VAT Fixed project fee
- Time
- About one week
- Scope
- One use case and its data
LLM Evaluation Health Check
Find out where one RAG or agent workflow fails, why, and what to fix first.
At a glance
- Price
- EUR 2,950 excl. VAT Fixed project fee
- Time
- About 5 working days After access and scope are agreed
- Scope
- One RAG or agent workflow, up to 50 test cases
Contracted with and invoiced by MILEAWAY AI SYSTEMS LIMITED.
Who it's for
Engineering teams with a RAG or agent feature in production, or close to release, who are seeing answers they can't fully trust, or who need evidence before a model change, a launch or a customer's due-diligence questions.
- Startups and mid-sized businesses shipping AI features to customers, wherever they are based
- Fintech and insurtech teams, where answers must stay grounded in policy, product or regulatory documents
- Teams about to change model, prompts or retrieval, who want a baseline first
The problem it solves
When outputs are unreliable, it is rarely obvious whether the cause is retrieval, context assembly, prompting, the model or the source data. Without a baseline, every fix is a guess and every model or prompt change is a risk you can't measure.
What I assess
- Correctness and groundedness of answers against agreed expectations
- The failure modes that matter for your workflow, such as missed retrieval, unsupported claims, wrong tool calls or prompt sensitivity
- Latency and cost, where the necessary measurements are available
What you get
- Agreed evaluation cases (up to 50), written with your team
- Baseline results across the agreed measures
- A failure analysis showing where and why the workflow fails
- Prioritised fixes, ordered by likely impact and effort
- A 60-minute handover with your team
Scope, price and limits
- One existing RAG or agent workflow
- One agreed evaluation environment
- Up to 50 representative test cases
Limits. Fifty well-chosen cases can expose systematic failures, but they are a sample. The results describe how the workflow behaved on those cases; they are not a statistical guarantee of behaviour in production. The Health Check is not a security audit or certification. Implementing fixes is scoped separately.
- Price
- EUR 2,950 excl. VAT Fixed project fee
- Time
- About 5 working days After access and scope are agreed
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.
Next step
Send me a few lines about the workflow and what's going wrong. I'll reply to arrange a short discovery call and confirm whether the Health Check is the right fit.
How it works
-
Discovery
A short call about the workflow, what's going wrong and what a useful result would look like. If the Health Check isn't the right fit, I'll say so.
-
Agreed scope
A written scope and fixed-fee quotation covering the workflow, the environment, the test cases, access and timing.
-
Assessment
Once access is in place, I build the evaluation cases with your team, run the baseline and analyse the failures.
-
Handover
A 60-minute session to walk through the results and priorities. You keep the evaluation cases and the report.
Why work with me
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 YouTube -
Recognition
Neo4j Featured Community Member, November 2025
Read the feature on neo4j.com -
Writing
Evaluating a Fine-Tuned LLM Using a Knowledge Graph and Ground Truth Data
Read the article on Medium -
Experience
Production AI, including financial services and insurance
Experience on LinkedIn
Questions
What do you need from us?
Access to the workflow in one agreed environment (often staging), a set of real or realistic questions or tasks, any examples of bad outputs you have already seen, and a technical contact who can answer questions during the week.
Are 50 test cases enough?
Enough to find systematic failures and decide what to fix first, if the cases are chosen well. Not enough to make statistical claims about production behaviour, and I won't present the results as if they were. The cases are yours to extend afterwards.
Do you also fix what you find?
The Health Check ends with prioritised fixes and a handover. If you'd like help implementing them, I'll scope that separately, so you can decide with the results in hand.
Does it depend on our framework or model provider?
No. The Health Check evaluates your workflow as it runs, so it works with whatever framework, model provider and vector store you use.
How do you handle confidential data?
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.
Other packages
Knowledge Graph Prototype Sprint
A working Neo4j and GraphRAG prototype on your own data, with evaluations built in.
- Price
- EUR 7,500–12,000 excl. VAT Guide range; a fixed price is agreed in the quotation after scoping
- Time
- 2–3 weeks
- Scope
- One data slice and set of questions