Ascend
daemonMulti-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
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 audits
- Read-only by default
- NDA on request
- US/UK/EU remote
Updated July 2026
Check this claimExample
agent ›“All tests pass. Done.”
claimed · uncheckedSession ledgertool · result
01Editsrc/orders.py
02Bashpytest → 3 failed
03Editsrc/orders.py
—end of session
Rule: a claim counts as proven only if a passing test run happened after the last code edit. Tiers A (proven) → D (no proof). From proof-of-green.
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.
13+ 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.
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
Exhibit · LLM billLLM cost engineering
−58%
Lower is betterLLM bill: $82 → $34 / month
↳ on my own platform — small bill, same levers scale with spend↗ worked example
On a larger bill, the same moves free up real budget.
- Multi-model routing
- Caching
- No drop in output quality
serbyn.io · field report
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.
DW
pipelineAutonomous 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 defined↳a system I designed and built
Crest
content engineContent marketing engine: a research engine that ranks topics, drafting with editorial and fabrication checks, tiered multi-model routing, and publishing to LinkedIn and X.
109 published1,455 posts generated · as of Aug 2026↳a system I designed and built
Built with Python, FastAPI, Celery, PostgreSQL, Redis, and Docker.
02 · Ways to work together
Fixed-scope offers
Audit
AI Agent Production-Readiness Audit
$3,500flat · ~2 weeks · fixed scope
A ground-truth read on whether your agents are safe to run in production: trajectory evals, false-green metering, evidence-binding gaps, and a prioritized fix list.
Learn more →CostLLM Cost Teardown
from $2,000~1 week
A line-by-line teardown of where your LLM spend goes and the six levers that bring it down — without lowering output quality.
Learn more →RetainerFractional AI Architect
from $4,000/mo~1 day/week · 3-month minimum
Ongoing architectural ownership of your agent platform: reliability, cost, and the gated rollout discipline to keep both in line as you scale.
Learn more →Also available: Advisory at $200/hr (10-hour minimum block). Audit fee credited against a retainer started within 60 days.
03 · Operator protocol
How I work
- 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.
- 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.
- 03
Evidence-binding
Every "green" has to point at the evidence that earned it. Claims that cannot cite their proof are treated as failures.
- 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 · 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
- Named recommendations from engineers and leads I’ve worked with, shared on the fit call with links to the originals.
05 · Writing
All writing →Notes on agent reliability
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