# Tanya Deputatova

Data Architect: GTM & MI

## Bio

Tanya brings cross-functional background in Data & MI, CMO, and BD director roles across SaaS/IaaS, data centers, and custom development in AMER, EMEA and APAC. Her work blends market intelligence, CRO and pragmatic LLM tooling teams actually adopts and analytics that move revenue.

[LinkedIn](https://www.linkedin.com/in/tanya-deputatova-8022002a/)

**Why your LLM bill exploded overnight (and how to regain control)**  
LLM bills spike overnight from retry storms, agent loops, and prompt bloat, not steady usage. Learn the guardrails: retry budgets, token caps, cost-aware routing, and unit-metric alerts, all enforced at one boundary.

**RAG Cost Control for AI Agents: How to Prevent AI Spend Drifts**  
RAG and agentic costs drift when retrieval, tools, API calls, and routing lack a shared control layer. Learn how to measure, audit, and reduce spend with API orchestration—without rebuilding from scratch.

**The Hidden Cost of Non-Compliance in AI**  
Learn how the EU AI Act, Colorado's AI Act, and California SB-53 impact engineering teams and how to build audit-ready AI systems.

**When Prompt Injection Gets Real: Use GraphQL Federation to Contain It**  
How GraphQL Federation helps protect AI systems from prompt injection by enforcing runtime boundaries, scoped access, and signed configurations.