← back to home

// service — ai engineering

AI agents & the
data that grounds them _

Most AI projects fail on the data, not the model. I build the full stack — custom Claude agents, skills and MCP servers — and the RAG datasets that make them accurate, current and trustworthy.

agent.log
 agent.init(skills=4)
  loading mcp tools...... ok
  retrieving context..... 12 docs
  grounding response..... ok
 task.complete
✓ 0 hallucinations

// the build

From prompt to production

01

Custom Claude Agents

Purpose-built agents that do real work — research, triage, content ops, data entry. Full cycle: design, tools, prompts, guardrails and deployment.

02

Skills & MCP Servers

Reusable Claude skills and Model Context Protocol servers that connect agents to your APIs, databases and internal tools — securely and predictably.

03

Workflow Automation

End-to-end automations that replace repetitive manual flows. Humans stay in the loop where it matters; the boring parts run themselves.

04

RAG Dataset Engineering

The unglamorous work that makes AI reliable: collecting, cleaning, chunking and embedding domain data into retrieval sets your agents can trust.

05

Knowledge Pipelines

Ingestion pipelines that keep your vector store fresh — scraping, parsing, deduping and re-indexing on a schedule, with quality checks built in.

06

Evaluation & Guardrails

Eval harnesses, grounding checks and safety rails so you know an agent works — and keeps working — before it touches production.

// the part everyone skips

Building a RAG dataset

Retrieval-augmented generation is only as good as the corpus behind it. Here's the pipeline I run to turn raw, messy source material into a dataset an agent can actually rely on.

  1. 01

    collect

    Source domain documents, transcripts, APIs and structured records.

  2. 02

    clean

    Normalise, dedupe and strip noise so the model learns signal, not clutter.

  3. 03

    chunk

    Split content into retrieval-sized passages with metadata that preserves context.

  4. 04

    embed

    Generate embeddings and index into a vector store tuned for your queries.

  5. 05

    ground

    Wire retrieval into the agent and evaluate answers against the source of truth.

// adjacent service

AI media & citations

The same RAG thinking applies to marketing. I structure and seed content so answer engines and AI assistants surface — and cite — your brand. It's SEO for a world where the search box talks back.

Answer Engine Optimisation Citation Tracking Structured Content Entity SEO Schema & Markup

// toolbox

What's under the hood

Claude Agent SDK MCP Skills Python Node Vector DBs Embeddings RAG Evals Webhooks Cron Pipelines

// let's automate it

Have a workflow begging to be an agent?

Tell me what eats your team's time. I'll tell you honestly whether an agent is the answer — and if it is, I'll build it end to end.