# Brendan Bondurant

Content Manager

## Bio

Brendan Bondurant is the Content Manager at WunderGraph, owning technical content across GraphQL Federation, API tooling, and developer experience. He partners with leadership on product and company messaging and works cross functionally to align positioning, terminology, and content strategy across channels.

He previously spent over a decade teaching and writing, and now focuses on turning complex platform and federation problems into practical guidance for engineering leaders.

> I spent almost 20 years as a professional musician and teacher before making a career change, and WunderGraph has been the right place to land. It's always interesting here: things move quickly, but there's real space to grow and build something. I came in as a technical content writer and shaped my way into a content manager role, which says a lot about how the company actually treats ownership and ambition. The people are smart, talented, fun to work with, and have become great friends. The international retreats are a pretty great perk, too.

[LinkedIn](https://www.linkedin.com/in/brendanbondurant/) [GitHub@brendanbondurant](https://github.com/brendanbondurant) [Website](https://brendanbondurant.com/)

**Understanding the N+1 Problem in GraphQL (and Why It’s Not Just GraphQL)**  
The N+1 problem can turn one request into hundreds of backend calls. Learn why it shows up in GraphQL, how DataLoader fixes it, and when to use alternatives like joins or eager loading.  
[Read post](/content/blog/graphql-n-plus-1-problem/index.html)

**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.  
[Read post](/content/blog/llm-cost-control/index.html)

**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.  
[Read post](/content/blog/rag-cost-optimization/index.html)

**The State of Federation 2026 Survey Is Open**  
Share how your team adopts, operates, and scales GraphQL Federation—including AI and LLM workloads—in the vendor-neutral State of Federation 2026 survey.  
[Read post](/content/blog/2026-state-of-federation-call-for-response/index.html)

**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.  
[Read post](/content/blog/ai-non-compliance-costs/index.html)

**What a Year at WunderGraph Looks Like**  
A year at WunderGraph, what ownership really means in a fast scaling company, and how roles are shaped rather than assigned.  
[Read post](/content/blog/1-year-at-wundergraph/index.html)

**From 10+ Seconds to Under One: Solving Their Slowest Operation**  
A personal finance marketplace reduced planning latency by roughly 90–95 percent and made its slowest queries 12–18× faster after replacing an aging Apollo Gateway with WunderGraph Cosmo and enabling the Cache Warmer.  
[Read post](/content/blog/casestudy-anon-10-sec-to-under-1/index.html)

**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.  
[Read post](/content/blog/prompt-injection-for-real/index.html)

**Cosmo Connect Tutorials for Router Plugins and gRPC Services**  
Step-by-step tutorials for Cosmo Connect: build Router Plugins, deploy gRPC services, and integrate subgraphs into a federated GraphQL API.  
[Read post](/content/blog/cosmo_connect_three_tutorials/index.html)