Blank white background with no objects or features visible.

Hello, EMEA! TrueFoundry is growing our footprint across Europe, the Middle East, and Africa. Read more. →

Boyu Wang

Head of Outcome Engineering

Boyu Wang is a technical author at TrueFoundry, focusing on modern AI and ML infrastructure topics. He writes in depth about AI gateway architectures, multi-agent systems, production AI tooling, platform comparisons, and the infrastructure challenges of deploying AI at scale. His articles explore both architectural patterns and practical workflows for enterprise-grade AI systems.

LinkedIn logo with lowercase letters i and n on blue background with white highlights present.

Boyu Wang

’s articles

October 15, 2026
|
5 min read
something

AI Gateway Guardrails, Explained: Hooks, Enforcement, and Failure Semantics

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

TrueFoundry Prompt Registry, Explained: Versioned Prompts as Production Artifacts

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

TrueFoundry Skills Registry, Explained: Versioning Procedural Knowledge Across Agents

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Context Compaction in TrueForge, Explained: What the Agent Forgets—and What the Session Retains

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

MCP Authentication, Explained: Inbound Identity, Outbound Credentials, and Delegation

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

MCP Tool Approvals, Explained: From Pending Call to Bounded Human Decision

White arrow pointing right on a blue circle background with solid white border edges.
September 18, 2026
|
5 min read
something

Agent Sandboxes, Explained: Why TrueForge Treats the Sandbox as a Tool

White arrow pointing right on a blue circle background with solid white border edges.
September 17, 2026
|
5 min read
something

Agent Resumability, Explained: Sessions, Turns, Pauses, and Reconnects in TrueForge

White arrow pointing right on a blue circle background with solid white border edges.
September 16, 2026
|
5 min read
something

From AI Governance to Continuous Assurance: Engineering Compliance Evidence for Agentic Systems

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Large Tool Responses, Explained: Keep Payloads Accessible Without Flooding Context

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

An Agent Identity Is Not an Authorization Decision: Designing Delegated Authority End to End

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Agents, Skills, and MCP Servers Are a Software Supply Chain: Build an Admission-Control Pipeline

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Deferred Tool Loading, Explained: Treat Tool Schemas as a Context Budget

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

From Token Spend to Workflow Economics: What BCG’s Return-on-AI Framework Requires

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Agent Events, Explained: The Runtime Contract Behind Reliable AI Agents

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

From AI Adoption to Agentic Operations: What HBS’s “AI in 2026” Collection Means for Enterprise AI

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Andrew Ng's AI Engineering Skills Map: What Enterprise Teams Should Standardize

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Agent Security Is a Systems Problem: From Prompt Injection to Runtime Control

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

From Agent Harness to System Intelligence: What Graph Engineering Changes in Production AI

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

From Agent to Loop to Graph: A Production Architecture for Agentic Systems

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Streamable HTTP, Three Eras and the Current Wire Contract

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

OpenTelemetry GenAI Conventions: A Common Vocabulary for AI Observability

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Graph Engineering for AI Agents: Govern the Connections

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

The Loop Is the New Middleware: Loop Engineering as an Enterprise Strategy

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Structured Outputs: Why Production AI Needs Schemas, Not Just Prose

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Semantic Caching: When Similar Questions Should Share an Answer

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Sandboxed Code Agents: Let Models Execute Without Letting Them Roam

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

The Human Gate: Designing MCP Tool Approvals at the Gateway Boundary

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

AI Agents Retire Too: A Decommissioning Playbook for Enterprise AI

White arrow pointing right on a blue circle background with solid white border edges.
August 6, 2026
|
5 min read
something

MCP 2026-07-28 Ships: Revisiting Apps, Tasks, and Gateway Governance Under the Largest Protocol Revision Since Launch

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Self-Evolving Agents, Governed: The Enterprise Playbook for Systems That Rewrite Themselves

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Governance Decay, Explained: How Context Compaction Erodes Agent Policy — and Where Enforcement Belongs

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Authorization Propagation, Explained: Why Request-Level Access Control Is Not Enough

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

The Agentic Software Factory, Explained: History, Architecture, and Enterprise Controls

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

From Prototype to Enterprise Production: Extending Andrew Ng's Three Loops

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Six AI Agent Architectures—and the Controls Each One Needs

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

ETCLOVG: The Seven-Layer Agent Harness Taxonomy, Mapped to a Production Runtime

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Agent Economics, No. 2: Mapping Firm-Scale AI Controls to Agent-Economy Institutions

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Agent Economics, No. 1: What Is the Agent Economy — and Who Gets to Design It?

White arrow pointing right on a blue circle background with solid white border edges.
Know everything about graph engineering
October 29, 2026
|
5 min read
something

Graph Engineering for Multi-Agent Systems: Architecture, Governance, and Observability

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Designing for Model Deprecations with Virtual Models and Staged Cutovers

White arrow pointing right on a blue circle background with solid white border edges.
July 16, 2026
|
5 min read
something

The Path to the Championship: Enterprise AI's Knockout Rounds Run Through the Gateway

White arrow pointing right on a blue circle background with solid white border edges.
July 15, 2026
|
5 min read
something

BCG Says Strategy Matters More Than Tools — Part 2: From Agent Adoption to Governed Tools and Runtimes

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

BCG Says Strategy Matters More Than Tools — Part 1: From Strategic Clarity to Gateway Controls

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

The Loop Gets a Passport and a Wallet: Loop Engineering Meets the Metered Web

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Mid-2026: The Agentic Convergence — Six Signals, and the Turn to Control

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Loops, Harnesses, and 6,000 Engineers: What the World's Fair Confirmed — and What Ships Today

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

TBAC: Task-Based Access Control for the Agent Age

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Enterprise-Grade Was the Subtext of the World's Fair

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Tool vs. Skill vs. Sub-agent: The Delegation Spectrum and Its Governance

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

The AI Agent Glossary, Mapped to Production Infrastructure

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Self-Hosting Open-Weight LLMs Behind the AI Gateway

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Seeing the Bill Before It Lands: Forecasting Enterprise AI Spend

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

MCP Apps and Tasks: Governing the New First-Class MCP Extensions

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Governing Multi-Agent Systems: Agent Identity, A2A, and the Agent Gateway

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

JIT Context: Why the Best Agents Load Late and Load Little

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Field Notes: When AI Cost Control Becomes a Switch — and Why It Should Be a Gateway

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Loop Engineering, Continued: From One Governed Loop to an Operable Fleet

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Online Evaluation and Quality Monitoring at the Gateway

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Spec-Driven Development for AI Agents, Done Right: Specs as Governed Artifacts

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Loop Engineering at Enterprise Grade: From Laptop Loops to Governed Runtimes

White arrow pointing right on a blue circle background with solid white border edges.
Everything you need to know about AI agent harness
November 2, 2026
|
5 min read
something

What is an Agent Harness? Running Governed Managed Agents in Production

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Intelligent LLM Routing: Cost-, Latency-, and Quality-Aware Model Selection at the Gateway

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

AI Governance and Audit for Enterprise LLMs: Virtual Keys, RBAC, and Compliance-Grade Logs

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Semantic Caching for LLMs: Cutting Cost and Latency Beyond Prefix Caching

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Prompt Injection Defense at the Gateway: Direct, Indirect, and Tool-Mediated Attacks

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Multi-Provider Failover and Load Balancing: Surviving LLM Provider Outages

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

PII Redaction at the Gateway vs. the Application Layer: A Performance and Correctness Analysis

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Context Engineering at the Gateway Layer: How Session Management Enables Long-Running Agents

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Separating Agent Logic from Runtime: The Case for a Managed Agent Layer

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Converting an OpenAPI Spec to an MCP Server: Architecture and Edge Cases

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Real-Time LLM Cost Attribution: From Token Counts to Team Budgets

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

OpenTelemetry for LLMs: How we instrument a multi-provider AI gateway

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Provider-Agnostic Prompt Caching: How an LLM Gateway Normalizes Anthropic, OpenAI, and Bedrock

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Stdio vs Streamable HTTP for MCP: What changes when you move from local development to enterprise deployment

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Designing a Centralized MCP Registry: Architecture Decisions for Enterprise Scale

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

The Agentic Token Explosion: Attributing, Budgeting, and Controlling LLM Costs in CI/CD

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

OAuth at the MCP Layer: How We Solved Enterprise Token Management for AI Agents

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Multi-Cloud GPU Orchestration with TrueFoundry: A Reference Architecture for Hyperscalers and Specialized Clouds

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Rate Limiting AI Agents: Preventing LLM API Exhaustion

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Air-Gapped AI: Deploying Enterprise LLMs in Highly Regulated Industries

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

TOKENMAXXING TRILOGY · PART 3 OF 3: Building the AI Leverage

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

TOKENMAXXING TRILOGY · PART 2 OF 3: The Architecture of Governed AI Usage

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

TOKENMAXXING TRILOGY · PART 1 OF 3: Tokenmaxxing is the New Lines-of-Code Metric

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Semantic Caching: When Text Stops Being the Right Cache Key

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Proxy, Router, Gateway: Three Words for Three Different Things

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

MCP Tool Poisoning: An Attack on the Channel the Model Trusts Most

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Controlling Claude Code in the Enterprise: MCP Tool Scoping and Audit Trails

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

The Agentic Token Explosion: Cost Attribution & Budgets for Claude Code in CI/CD

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

How to Host an AI Hackathon Without Losing Control of Your Keys or Budget: The TrueFoundry Architecture

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Orchestrating Bare-Metal AI: TrueFoundry Integration with Oracle Cloud Infrastructure

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

What is MCP Registry? And Why You Can’t Run Agents Without One

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Bringing OpenCode In-House: Secure Tool Usage on TrueFoundry

White arrow pointing right on a blue circle background with solid white border edges.
September 11, 2026
|
5 min read
something

Decoupling Control and Data: TrueFoundry's Strategy for Global AI/ML Data Residency

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

How to Detect Shadow AI and Turn Risk into Enterprise Advantage

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Why Production AI Needs Dedicated Prompt Management

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Beyond the Log File: Why Specialized Observability is Non-Negotiable for Production Voice AI

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Agent Gateway Series (Part 7 of 7) | Agent DevOps: CI/CD, Evals, and Canary Deployments

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Agent Gateway Series (Part 6 of 7) | Observability for Non-Deterministic Systems

White arrow pointing right on a blue circle background with solid white border edges.
October 15, 2026
|
5 min read
something

Agent Gateway Series (Part 4 of 7) | FinOps for Autonomous Systems

White arrow pointing right on a blue circle background with solid white border edges.
TrueForge
Agentic AI
Webinar
comparison
LLM Terminology
LLM Tools
New
Use Cases
Engineering and Product
True ML Talks
Thought Leadership
LLMs & GenAI
Kubernetes
GPU
Culture
Authentication

Subscribe to our newsletter

Latest news, articles, and resources sent to your inbox