Skip to content
fewtokensai
PL

Senior AI consulting · Kraków

AI that actually pays for itself.

Strategy, engineering, team leadership — from one person. 10 years shipping production AI for fintech, trading, and SaaS. inFakt, IG Group, IBM.

Book a 30-minute call → See a recent engagement →

Worked with

What I do

Five practice areas. All proven in production.

Every practice area is anchored in a specific recent engagement — with numbers, dates, and named clients. No generic promises.

Selected case studies

Specifics, not promises.

Specifics. Real numbers, real dates, real client names — none of the generic promises.

All case studies →
About Michał Czyżewski
Based: Kraków, PL
AGH · Mensa

You'll work directly with me — not an account manager.

Michał Czyżewski is an AI engineering leader based in Kraków, Poland. Founder of fewtokensai and currently AI Engineering Manager at inFakt, where he leads the AI Engineering team building production AI systems — including a Model Context Protocol server and an automated bookkeeping system processing 300,000+ invoices monthly. Previously, over many years at IG Group, he led a Kraków-based data science team working with stakeholders in offices across the UK, US, Japan, Bermuda and Dubai. His work on KYC automation and generative AI adoption generated $390,000+ in combined annual savings and revenue.
More about Michał →
Recent writing

Notes from production.

All writing →
Frequently asked

Questions clients ask first.

/01 How much does an AI deployment cost?

It depends on scope and duration. Typical engagements at fewtokensai run 4–12 weeks and end with a working system (not just a slide deck). RAG audit: 1–2 weeks. MCP server deployment: 4–8 weeks. AI strategy + roadmap: 4–8 weeks. Fractional AI Engineering Manager: retainer from half to two days per week. Concrete rates after the first 30-minute discovery call (no obligation).

/02 Is my company ready for AI?

Most likely yes — the question is what kind of AI. If you have orderly data (CRM, data warehouse) and 1–2 engineering teams, you're ready for a first LLM/RAG deployment. If your data is a mess, start with data architecture — without it, LLMs will hallucinate. In a 30-minute call I can honestly tell you whether AI is the right direction now, or whether you should fix fundamentals first.

/03 How long does a typical AI project take?

Audit: 1–3 weeks. PoC with clear ROI: 4–8 weeks. First production LLM/RAG deployment: 8–16 weeks. Full org-wide AI transformation (strategy + team + 2–3 deployments): 6–12 months. Every stage is measurable with explicit success criteria — we account for shipped systems and business metrics, not slides.

/04 What is AI consulting and how does it differ from a typical agency?

AI consulting is advisory work covering AI strategy, architecture, and implementation of concrete systems. fewtokensai (Michał Czyżewski) operates as a senior solo practice — you work directly with the person who has shipped these systems in production (inFakt, IG Group, IBM), not with an account manager running junior teams. I don't sell 18-month multi-million transformation programs — most orgs need 3–6 months of focus and two good people.
All questions →
Let's talk about your AI

Let's talk.

30 minutes, no obligation. Tell me where your AI initiative is stuck or what you're planning — you'll leave with concrete next steps.

Book a 30-minute call →
Email LinkedIn
admin@fewtokens.pl