Helping enterprise teams ship production agent systems, from multi-agent orchestration to context engineering.
awesome-applied-ai · 6-layer applied AI map →
Demo at ACM CAIS '26 · San Jose · May 29 →
Multi-Agent Job Classification · ACM Published
18h Applied AI Course · Techcareer
tokalator.wiki · 500+ installs
16,000,000 tokens · 38% saved → how
From arXiv to ACM · 3 papers in 6 months
Turning enterprise data into production AI. Multi-agent systems, context engineering, data preparation, automation. Designing AI systems. Publishing research. Training teams.
9+
Years shipping
95%
Agent accuracy
72.5%
Faster classification
60%
Workload reduction
3+1
Publications + Patent
400+
People trained
Istanbul
--:--
You
--:--
awesome-applied-ai · July 2026
A working map of applied AI for the enterprise
Six layers: Guardrails and Governance, Evaluation and Observability, Orchestration, Caching, Memory, and Retrieval. Includes a live tool index, equations, dictionary, and research for enterprise AI architects.
Case Studies
Problems I solved end to end.
ProblemAI coding assistants burn tokens blindly — no visibility into context cost, no budget guardrails, no cross-model comparison.
ApproachReal-time token budgeting, tab relevance scoring, Cobb-Douglas output-quality models, caching break-even analysis across 17 LLMs.
ResultVS Code extension + web platform shipped. arXiv paper published. $40K Perplexity AI grant secured.
Next.js·TypeScript·VS Code Extension·Token Economics·MCP
Multi-Agent Job Classification System
ProblemFree-form job titles in multiple languages can't be reliably mapped to O*NET/ESCO taxonomies at scale.
ApproachMCP-based multi-agent system: planner, search, extraction, and evaluation agents with shared caching layer.
Result95% accuracy on 14K+ positions. 72.5% faster classification. 41.8% fewer API calls. Accepted at ACM.
MCP·LangGraph·Subagent Architecture·AI Search·Caching
Enterprise AI Transformation
ProblemManual reporting workflows across Sales, Finance, R&D consuming analyst time with no self-service capability.
ApproachMulti-agent orchestration (LangGraph, MCP, Agno) for text-to-SQL, report automation, and AI feedback loops with human checkpoints.
Result60% reduction in manual workload. 100+ users served. Adopted as group-wide AI standard.
FastAPI·LangGraph·Agno·Pydantic·Arize
300M+ Datapoint Metadata Platform
ProblemNo unified metadata layer across a live job platform — fragmented schemas, no lineage, analytics bottlenecked by ad-hoc queries.
ApproachDesigned metadata architecture with DataHub governance, real-time pipelines, and product-analytics instrumentation for strategic decisions.
Result300M+ datapoints unified. Became the foundation for all later AI/LLM deployments — embedding generation, RAG retrieval, and context grounding at scale.
DataHub·Azure Synapse·BigQuery·Real-time Pipelines·Retool
Publications
Peer-reviewed and cited.
Experience
Where I built it.
2025 — now
Senior Applied AI Specialist
Kariyer.net (ilab group)
Lead AI/LLM initiatives across Sales, Finance, R&D. Multi-agent orchestration adopted as group-wide standard. Secured $40K Perplexity AI grant.
Google GenAI Leader · $40K Grant
2022 — 2025
Product Manager — Data
Kariyer.net
Metadata architecture serving 300M+ datapoints. AI strategy alignment. Pipeline infrastructure enabling later LLM deployments at scale.
2021 — 2022
Business Analyst
WorqCompany
Forecasting models, dashboards, and process automation for finance and operations.
2019 — 2021
Co-Founder
Defaro.io
Labour-market analytics startup — compensation intelligence and career pathway analytics. Data pipelines, benchmarking models, product strategy from scratch.
Portfolio
Live products and demos.
VS Code extension, wiki with 58 articles, and token calculator. Real-time token budgeting, tab relevance scoring, and cost modeling across 17 LLMs.
Next.js·Scala·Python·Cobb-Douglas·VS Code Extension
MCP-based multi-agent system for cross-lingual job title normalization to O*NET and ESCO taxonomies. 95% accuracy on 14K+ positions with 72.5% faster classification.
Next.js·MCP·Gemini Agent Garden·Hooks·Vercel AI·Anthropic SDK
Weekend advisor role. Architecting data agents, text-to-report pipelines, canvas flow tools, and enterprise automation workflows.
Agno (Self-Learning)·Text-2-SQL·Metadata·Memory·Orchestrator
Enterprise AI Platform
AI transformation across Sales, Finance, and R&D at Kariyer.net. Business flow automation, text-to-SQL self-service reporting, and AI-powered feedback loops. Serving 200+ colleagues — from prototype to solution design to ship.
FastAPI·LangGraph·Agno·Pydantic·Arize
Working with 300M+ Datapoints
Unified metadata architecture at Kariyer.net with DataHub governance and real-time pipelines. Large-scale salary normalization, unstructured position text classification, and taxonomy preparation. Foundation for all AI/LLM deployments.
DataHub·Azure Synapse·BigQuery·Pipelines
About
The person behind the systems.
Education
03- M.A. Economics — Ibn Haldun University
- Thesis: Real-Time Labor Market Analysis
- Teaching Asst., Econometrics I
Certifications
03- Google Generative AI Leader
- Anthropic — MCP, Agents, Claude API, Claude Code
- LangChain — LangGraph, LangSmith
Languages
05- Turkish — Native
- English — C1
- Spanish — Instructor
- Portuguese — Basic
- Japanese — Learning
Teaching
03- 18h Applied AI Course — Techcareer
- AI Career Mentor — TEV Foundation
- Enterprise prompt engineering — Universities