Currently running 4 agents in production
§ Service 01 / 06

AI Systems
& Agents.

Autonomous agents, RAG pipelines, and custom LLM workflows that actually ship to production. With eval harnesses, observability, and a sane cost ceiling.

LangGraphOpenAIAnthropicPineconepgvectorTool-useEvalsObservability
agents/support_agent.pyLangGraph · 0.2.34
1from langgraph.graph import StateGraph, END
2from .tools import classify, fetch_order, issue_refund
3
4# the actual graph — five nodes, fully typed
5graph = StateGraph(TicketState)
6graph.add_node("classify", classify)
7graph.add_node("fetch_context", fetch_order)
8graph.add_node("resolve", issue_refund)
9graph.add_conditional_edges(
10  "classify", route_by_confidence, {"high": "resolve", "low": "human"}
11)
12app = graph.compile()  # ready in <120ms
§ What we ship

Real software, not
another POC slide deck.

§ 01

Agent orchestration

Multi-step agents built with LangGraph. Branching logic, retries, human-in-the-loop checkpoints.

§ 02

RAG over your data

Document ingestion, chunking, embeddings, hybrid search, re-ranking. Benchmarked against your real queries.

§ 03

Tool-use & function calling

Typed, tested, instrumented. When it goes wrong, you know which call broke.

§ 04

Eval harness & CI

A test suite for prompts. Every change runs the eval set. You see regressions before users do.

§ 05

Hand-off to humans

When the model isn't confident, the question goes to a person. With context, not a dump.

§ 06

Cost & latency dashboards

Token counts, latency, cost ceiling that pages someone if you cross it.

§ How we approach

Built to be useful,
not impressive.

The demo-able AI agent is a different animal from the useful one. The first one gets your team excited; the second one quietly removes a real cost from the business.

Our default is to start with the smallest possible agent that solves one named problem, instrument it carefully, and grow it from there. No giant orchestration graphs on day one.

Most projects ship a first agent in two to three weeks, then iterate weekly. The eval set comes first.

§ What you get

The complete set
of deliverables.

  • § 01

    Discovery document

    A written read of where the agent should sit.

  • § 02

    Eval set

    50–200 real queries from your team.

  • § 03

    Working agent

    In your stack, in your cloud.

  • § 04

    Admin dashboard

    Token usage, costs, conversation logs.

  • § 05

    Documentation

    For your team to maintain it. Plus a video walkthrough.

  • § 06

    Retainer for the oak

    Optional. But most clients keep us on for the long arc.

§ Sapling
€8k – €18k

A single agent or workflow. Discovery + build + eval + deploy in 3 to 5 weeks.

§ Young oak
€20k – €60k

A full AI product: agents, RAG, dashboards, API. 8 to 12 weeks.

§ Tending the oak
€3k – €8k / mo

Monthly retainer for tuning, new features, eval expansion.