# Ömer Faruk Koç — Projects

Machine-readable project portfolio.

## Agentic Customer Service Platform

Customer-service agent platform where the LLM proposes refunds, cancellations, lookups, tickets and escalations while deterministic software owns scope, policy, confirmation, revalidation, idempotency and execution.

**Category:** AI Reliability / Execution Infrastructure  
**Status:** current

**Technologies:** Python, FastAPI, LangGraph, SQLAlchemy, PostgreSQL, Alembic, Qdrant, OpenTelemetry, React, TypeScript, Vite, Pydantic, Ruff, Mypy, Vitest, Playwright, Docker Compose

**Engineering topics:**
- Reliable Execution Infrastructure
- Agent Orchestration
- Typed Structured Decisions
- Deterministic Policy Engine
- Human-in-the-Loop
- Durable Checkpointing
- Risk-Based Tool Execution
- Confirmation Revalidation
- Idempotent Business Writes
- Exactly-Once Business Effects
- Policy Audit Trail
- Execution Audit Lifecycle
- Agent Run Projections
- Run / Action Identity
- Failure Taxonomy
- Hybrid RAG
- Immutable Knowledge Snapshots
- Atomic Alias Activation
- Snapshot Rollback
- Customer-Scoped Memory
- Live Model Evaluation
- Multilingual Evaluation
- Provider-Neutral Model Transport
- Structured-Contract Compatibility Gate
- Decision Architecture Evaluation
- Containment Funnel Analysis
- Prompt Injection Resistance
- Provenance Enforcement
- Operational Release Gate
- Fault Injection
- Observability

**Evidence:**
- D2c semantic safety validation: 540/540 measured attempts — semantic/safety · semantic\_decision\_v3
- D2d operational release gate: 18/18 · 8/8 · 6/6 — operational scenarios · phases · fault classes
- Safety hardening journey: 15 → 3 → 0 → 0 → 0 — Unsafe executable survivors, M6.15B → M6.29B
- Deterministic resilience snapshot: 28/28 — Deterministic resilience
- Current runtime contract: semantic\_decision\_v3 — Default semantic contract
- Structured-contract compatibility gate: 1 of 4 candidates qualified — semantic\_decision\_v3 · frozen contract

**Repository:** https://github.com/negativexq/agentic-customer-service-platform

## ModelOps Control Plane

Policy-driven ML release control plane combining progressive canary delivery, delayed-ground-truth quality gates, automated promotion and rollback, and desired-vs-observed routing reconciliation.

**Category:** MLOps / AI Platform  
**Status:** current

**Technologies:** Python, FastAPI, SQLAlchemy, SQLite, Alembic, Next.js, TypeScript, scikit-learn, Locust, Docker Compose

**Engineering topics:**
- Progressive Delivery
- Canary Deployment
- Weighted Routing
- Deployment State Machine
- Policy Engine
- Automated Promotion
- Automated Rollback
- Delayed Ground Truth
- Quality-Gated Promotion
- Label Coverage Gating
- Positive-Label Sufficiency
- Matured Quality Window
- Desired / Observed State
- Control-Loop Reconciliation
- Model-Scoped Routing Generation
- Stale Configuration Rejection
- Router Restart Recovery
- Optimistic Concurrency Control
- DB-Level Rollout Exclusivity
- Manual Automation Hold
- Fault Injection
- Auditable Deployment Timeline
- Policy Evaluation Snapshots
- Model Registry
- Model Serving
- Benchmarking

**Evidence:**
- Automated healthy rollout: 10% → 25% → 50% → 100% — Worker-driven real-stack CI
- Quality-driven rollback: Recall FAIL → automatic rollback — Delayed ground-truth CI
- Restart-safe routing: Router restart recovery — Desired/observed reconciliation · CI scenarios 5–6
- Backend regression suite: 279 tests — Backend suite · ~91% statement coverage

**Repository:** https://github.com/negativexq/modelops-control-plane

## Knowledge Base RAG

Local-first multilingual RAG platform with tenant-scoped hybrid retrieval, measured reranking, strict answer validation, versioned index operations and an evidence-first React console.

**Category:** Generative AI / RAG Platform  
**Status:** current

**Technologies:** Python, FastAPI, React, TypeScript, Vite, Qdrant, Ollama, OpenTelemetry, Jaeger, Docker Compose

**Engineering topics:**
- Multi-Source Ingestion
- Incremental Sync
- Tenant-Scoped Retrieval
- Role-Based Access Control
- Hybrid Retrieval
- Dense Retrieval
- Sparse Retrieval
- RRF Fusion
- Multilingual Reranking
- Untrusted RAG Context
- Prompt Injection Resistance
- Strict Output Validation
- Citation Integrity
- Pipeline Fingerprinting
- Versioned Index Activation
- Alias Rollback
- Distributed Tracing
- Artifact-Backed Evaluation

**Evidence:**
- Repository test evidence: 844 backend · 18 frontend — Last recorded full verification
- Multilingual reranker evaluation: Recall@5 1.0000 · MRR 0.9558 — 220-query paired benchmark
- Prompt-security evaluation: 82 adversarial cases — Tenant ACL · untrusted context · strict validation
- Generation sanity: 26/26 successful — Baseline generation path

**Repository:** https://github.com/negativexq/knowledge-base-rag

## Real-Time Commerce Platform

Production-oriented event-driven commerce platform where Kafka may redeliver, but layered idempotency, transactional persistence and bounded failure handling protect durable business effects.

**Category:** Distributed Systems / Streaming  
**Status:** current

**Technologies:** Python, TypeScript, FastAPI, Next.js, Kafka, PostgreSQL, Redis, Prometheus, Grafana, Docker Compose

**Engineering topics:**
- Event-Driven Architecture
- At-Least-Once Delivery
- Idempotent Consumer
- Transactional Outbox
- Bounded Retry
- Dead Letter Queue
- Unit of Work
- Consumer Groups
- Partition-Scoped Ordering
- Query-Plan Analysis
- Offset-Commit Batching
- Observability
- Performance Engineering

**Evidence:**
- Sustainable capacity improvement: 750 → 1,050 evt/s (+40%) — Isolated local benchmark · Kafka → processor → persistence
- Recent-payment lookup: 10.897 → 0.253 ms — Query-plan-driven optimization

**Repository:** https://github.com/negativexq/real-time-commerce-platform

## Repo Context Forge

Local-first MCP repository intelligence and agent platform for deterministic, source-grounded code analysis within strict read-only boundaries.

**Category:** Agent Infrastructure / Developer Tooling  
**Status:** current

**Technologies:** Python, MCP, FastMCP, Python AST, Typer, Docker, Git, Ollama

**Engineering topics:**
- Repository Intelligence
- Source-Grounded Context
- Deterministic Code Search
- Symbol Analysis
- References
- Callers / Callees
- Dependency Analysis
- Dependency Graphs
- Read-Only Git Intelligence
- Context Packs
- Task Bundles
- Validated Tool Arguments
- Filesystem / Path Containment
- Read-Only Process Boundaries
- Bounded Local Agent

**Evidence:**
- Configured MCP surface: 40 tools — Six local MCP servers
- Prerelease validation: 206 tests · 87% coverage — v0.2 alpha validation

**Repository:** https://github.com/negativexq/repo-context-forge

## dbt Feature Lineage

Local-first dbt analysis for model dependencies, cross-model column lineage, change impact and query flow without a live warehouse.

**Category:** Data Engineering / Lineage  
**Status:** current

**Technologies:** Python, dbt Core, FastAPI, Next.js, TypeScript, React Flow, sqlglot, NetworkX, Typer, Docker

**Engineering topics:**
- Model DAG
- Column-Level Lineage
- Upstream Trace
- Downstream Trace
- Direct / Transitive Impact
- Static SQL Analysis
- Manifest-Aware Analysis
- Compiled SQL Analysis
- Query Flow
- Exposure-Aware Impact
- Model Health
- Git URL Import
- Deep-Linkable Views

**Evidence:**
- Analysis scope: Cross-model column lineage — Manifest-aware + static analysis

**Repository:** https://github.com/negativexq/dbt-feature-lineage

## Production RAG Platform

Focused single-PDF retrieval foundation covering hybrid search, reranking, citation-aware generation, evaluation and observability.

**Category:** Generative AI / Retrieval  
**Status:** current

**Technologies:** FastAPI, Qdrant, Ollama, OpenTelemetry, Jaeger, DeepEval, PyMuPDF, Docker Compose

**Engineering topics:**
- Hybrid Retrieval
- RRF Fusion
- Cross-Encoder Reranking
- Citation-Aware Generation
- Citations
- Evaluation
- Observability

**Repository:** https://github.com/negativexq/production-rag-platform

## Terraform Docker Infrastructure Lab

Modular Terraform infrastructure lab with state-safe refactoring, native IaC tests, CI security gates, observability, and end-to-end failure validation.

**Category:** Infrastructure as Code / Platform Engineering  
**Status:** current

**Technologies:** Terraform, Docker, FastAPI, PostgreSQL, Nginx, Prometheus, Grafana, Alertmanager, k6, GitHub Actions

**Engineering topics:**
- Infrastructure as Code
- Terraform Modules
- Terraform State
- State Migration
- Moved Blocks
- Native Terraform Tests
- Provider Mocking
- Configuration Hashing
- Infrastructure Validation
- DevSecOps
- Observability
- Alert Lifecycle Testing

**Evidence:**
- State-safe module refactor: 0 add · 0 change · 0 destroy — Verified Terraform migration
- Infrastructure validation: Native Terraform tests — Mock-provider test suite

**Repository:** https://github.com/negativexq/terraform-docker-infrastructure-lab

## Supporting Work

## Go Reliability Labs

A focused series of six Go labs exploring how backend systems remain predictable under load, concurrency, and partial failure — covering latency measurement, idempotency, admission control, dependency resilience, backpressure, and end-to-end deadline budgeting.

_Predictable backend behavior under load and failure._

1. **Measure — go-api-prober**  
   Bounded-concurrency HTTP probing with throughput measurement, latency percentiles, status distributions, connection reuse, graceful cancellation, and race-tested concurrency.  
   https://github.com/negativexq/go-api-prober

2. **Correctness — go-idempotency-lab**  
   Concurrent idempotent request handling backed by PostgreSQL transactions and UNIQUE constraints, preventing duplicate side effects while safely replaying completed results.  
   https://github.com/negativexq/go-idempotency-lab

3. **Admission Control — go-rate-limiter**  
   Local token-bucket and Redis-backed distributed rate limiting with atomic decisions, explicit rate-limit responses, and concurrency-tested global limits.  
   https://github.com/negativexq/go-rate-limiter

4. **Resilience — go-retry-circuit-breaker**  
   Dependency-free bounded retries with exponential backoff and jitter, retryable HTTP classification, response-body lifecycle handling, and a concurrency-safe circuit breaker.  
   https://github.com/negativexq/go-retry-circuit-breaker

5. **Overload Control — go-backpressure-lab**  
   Bounded queues and fixed workers demonstrating saturation behavior, enqueue timeouts, explicit overload rejection, context cancellation, stats, and graceful draining.  
   https://github.com/negativexq/go-backpressure-lab

6. **Time Budget — go-deadline-budget-lab**  
   End-to-end deadline propagation with child timeout budgeting, safety reserves, fail-fast budget exhaustion, budget-aware retries, and parent-child deadline guarantees.  
   https://github.com/negativexq/go-deadline-budget-lab