Skip to content
serbyn.io

agentic systems architect

I make AI agents reliable enough to run in production.

I'm Vitalii Serbyn — I work with US, UK, and EU teams to get agent systems production-ready. Two specialties: agent reliability (trajectory evals, false-green-rate metering, evidence-binding gates, trust-tiered execution) and LLM cost engineering (multi-model routing and cost tracking) — bringing spend down without lowering output quality.

Fixed-scope auditsRead-only by defaultNDA on requestUS/UK/EU remote

Updated July 2026

why this mixture is rare

Reliability and cost, held by the same hands

Agent reliability engineering

Trajectory evals, false-green-rate metering, evidence-binding gates, and trust-tiered L0–L4 execution — the machinery that turns "seems fine" into a number you can gate on.

LLM cost engineering

Multi-model routing, semantic caching, and per-service cost tracking that cut the bill without lowering output quality — the same levers whether you spend hundreds or hundreds of thousands.

12+ years of production systems

Long before agents: shipping software people depend on — including a consumer app with 100M+ downloads and a Google Play Editor’s Choice award, and an 80–90% RPC cost reduction on a Web3 platform, both as an engineer in employed roles.

quantified results

The numbers, each with its context

Every figure below says where it came from — a system I built, my own platform, or an employed role. No borrowed client metrics.

18+mature agents (27 total)on Ascend, a system I designed and built
1,178automated testson Ascend, a system I designed and built
101logged pipeline runs · 0.94 pass rateon DW, a system I designed and built
−58%LLM bill: $82 → $34 / monthon my own platform — small bill, same levers scale with spend
100M+app downloads · Google Play Editor’s Choice (Top 100)as engineer, in an employed role
80–90%RPC cost reduction on a Web3 platformas engineer, in an employed role

01_systems_i_designed_and_built

Systems I designed and built

Not client logos — my own systems, where I proved the reliability and cost methods I bring to your agents.

Ascend

Multi-agent orchestration daemon: trust-tiered L0–L4 execution, policy gates, budget guards, and audit logging across live projects.

1,178 tests6-provider LLM fallback · 18+ mature agents (27 total)a system I designed and built
View on GitHub

DW

Autonomous spec-driven development pipeline: a spec goes in, working change comes out, gated by acceptance checks before it lands.

101 runs · 0.94 passlogged runs, methodology defineda system I designed and built
How runs & passes are countedRepository — coming soon

Crest

LangGraph-based content engine: multi-stage pipeline with multi-model routing and multi-platform publishing.

LangGraphmulti-stage content enginea system I designed and built
Visit usecrest.io

Built with Python, LangGraph, FastAPI, PostgreSQL, Redis, and Docker.

03_operator_protocol

How I work

Same sequence every engagement — measure before touching, gate every change on evidence.

  1. 01

    Ground-truth audit first

    Before changing anything, I measure what your agents actually do — real trajectories, real pass/fail, real cost — not what the dashboard claims.

  2. 02

    Evals before changes

    I build the trajectory and false-green evals that turn "seems fine" into a number, so every later change is judged against a fixed bar.

  3. 03

    Evidence-binding

    Every "green" has to point at the evidence that earned it. Claims that cannot cite their proof are treated as failures.

  4. 04

    Gated rollout

    Changes ship behind trust tiers and budget guards, promoting only when the evals and cost metrics hold — with a fast path back.

04_proof_of_method

See the method, not just claims

Sanitized sample audit report

The exact deliverable format — findings, severity, evidence, and a prioritized fix list — with a real (client-anonymized) example.

Available on request

Method walkthrough (2–3 min)

A short screen recording walking through how an agent trajectory is evaluated and where the false-greens hide.

Coming soon

05_what_colleagues_say

What colleagues say

Named recommendations from engineers and leads I've worked with are shared on request, with links to the originals.

Reference available on request.

LinkedIn recommendation

Reference available on request.

LinkedIn recommendation

Reference available on request.

LinkedIn recommendation

06_continuity_and_trust

How engagements are run

Contracting entity
Easelect LTD (UK LTD). Invoiced in USD/GBP/EUR; standard contractor terms.
IP & ownership
Full IP transfer on payment. Your code and findings are yours.
Access
Read-only access by default. Write access only when a change is agreed, scoped, and gated.
NDA / DPA
NDA on request; DPA available for engagements touching personal data.
Continuity
Based in Kyiv with backup power and connectivity in place to keep engagements on schedule.
References
Client references handled privately, shared on request with permission.

Get a straight read on your agents

A 30-minute systems call: tell me what your agents do and where they worry you, and I'll tell you whether an audit, a cost teardown, or a retainer is the right next step.

Fixed-scope audits · Read-only by default · NDA on request · US/UK/EU remote