Projects & experiments
Things I’m building.
Case studies
AI Reliability Layer
A shared layer for monitoring, diagnosis, and automated recovery across production agents and automations.
Production reliabilityEngineering Coordination Layer
A multi-agent system that helps me maintain a high standard of project coordination by connecting discussions, decisions, and project updates to clear tasks, owners, and next steps.
Engineering operationsCompany Brain
Shared company context from 17 internal systems, available to employee agents and internal products through permission-aware access.
Context infrastructurePII Sanitization Pipeline
A shared pipeline for preparing confidential client and partner data for AI workflows, with field-level policies and local processing before downstream agents receive it.
Data privacy
Show 3 more case studiesShow fewer case studies
Presales Automation
A multi-agent presales system that qualifies leads, answers questions using a knowledge base, and schedules sales calls, with shared context across voice, WhatsApp, email, and SMS.
Presales automationDocument Intelligence Platform
An agent-routed platform that prepares 100K+ confidential documents for downstream systems through local OCR and LLM processing, selective Azure fallback, and legal review.
Document intelligenceQuote Agent
A multi-agent quoting system that interprets site assessments, compares purchasing options, and prepares costed proposals with code-based checks and human approval.
Renovation operations · 2024
Personal projects
agent-claimcheck
Check AI agent success claims against tool receipts and state evidence, with calibrated decisions and a review queue for uncertain cases.
Agent evaluation · Claim verificationAgent Cheat Index
Agent Cheat Index by Andrii Boiko evaluates coding agents with hidden verification, checks for test tampering, and reviews unsupported success claims.
Agent evaluation · Benchmarkobey: Coding Agent Instruction Compliance
obey by Andrii Boiko evaluates coding agent instruction compliance, generates enforcement hooks, and compares behavior with and without repository rules.
Agent evaluation · Instruction enforcementpgwarden
Give AI assistants Postgres access with per-person permissions, PII masking, human-approved writes, and an auditable query history.
MCP infrastructure · Database access controlsloptriage: Bug Report Reference Checks
sloptriage by Andrii Boiko checks code references in bug and security reports against repository versions, with evidence links and optional reproduction.
Security tooling · Evidence-based triagelocal-enough
Compare local and cloud options for a task, then route requests to the least expensive option that clears its quality bar.
Model evaluation · Cost-aware routingtaskdistill
Turn a recurring LLM task into a small local model, with measured quality and automatic escalation to the original API.
Model distillation · Local inferenceproof-of-done
Check a coding agent’s verification claims against command results after its latest edits, with a Claude Code stop hook and a transcript audit CLI.
Developer tools · Verification evidencebooking-truth
Check whether an AI booking agent did what it promised, using calendar-state evaluation, injected failures, and a guarded reference agent.
Agent evaluation · Booking reliabilityTern
Search a video archive by what was said, shown, or written on screen. Built to run locally on Apple Silicon.
Multimodal search · Desktop appwellbrief
Ask questions across drilling reports and build pre-drill risk briefs, with traceable figures and source quotes. Runs offline by default.
Offline retrieval · Decision supportgo-public
Audit a private repository’s Git history before release, then create and re-scan a separate public export.
Developer security · Repository release
Research & experiments
AI Agent Evaluation Research with HUD SDK
Andrii Boiko’s research with HUD SDK: AI agent evaluation, grader validation, reward integrity, trajectory analysis, and reproducible experiments.
Agent evaluation · Research engineering8 DGX Sparks: LLM Serving Capacity
An empirical study of workload-dependent concurrency, prefill interference, and interconnect performance across an eight-node inference fleet.
Inference systems · September 2026