Service 08
LLM Integration & AI Agents
Agents, assistants and generative tooling on OpenAI, Claude and LangGraph, with evaluation and cost control, so behaviour holds up outside the demo.
What this service covers
An LLM demo takes an afternoon. A feature that behaves consistently for thousands of users, degrades gracefully when the API is slow, and does not quietly triple your bill is a different piece of engineering.
I integrate OpenAI, Claude and LangGraph into products: agents, in-product assistants and generative tooling, including the parts usually skipped: prompt versioning, structured output the rest of the system can depend on, fallback behaviour when a call fails, and cost controls with visibility before the invoice arrives.
At Wolffun I shipped LLM-powered NPC dialogue, quest generation and in-game assistants across a portfolio serving millions of players, so the constraints are familiar: real traffic, real budgets, and real consequences when output goes wrong.
What you get
- An agent or assistant integrated into your product, not bolted beside it
- Prompt versioning and structured outputs other systems can rely on
- Fallback and retry behaviour for slow or failed model calls
- Token and cost controls with usage visibility and alerting
- An evaluation harness, so prompt changes are compared rather than guessed at
How I work
Four stages, and you always know which one you are in
The same process whether the engagement runs two weeks or a year.
Understand the business
I ask product-level questions before quoting, so the work is scoped against what the business needs, not just the ticket as written.
Architecture in writing
You get the proposed architecture in writing before any code is committed. Disagreements happen on the document, where they are cheap.
Delivery in milestones
Work ships in milestones with regular updates, so you always know what has landed and what is next.
Documented handoff
Code is documented and handed off cleanly. Your future engineers should not have to reverse-engineer my decisions.
Direct Project Enquiry
Tell me what you are building
Share what you are building and where it is stuck. If a managed platform already solves it, I will say so. I review every enquiry personally and reply within about four hours.
- 1Send your project goal and the services you think you need.
- 2I review the context and whether I am the right fit.
- 3You get a direct reply with a practical next step.
International projects welcome
I work in English by email, video call or through Upwork, from GMT+7 with overlap hours for US and EU teams.
Read the Privacy Policy, Terms of Service and Cookie Policy.