Context Is Code: A Tour of APM and AgentRC
Table of Contents 1. The problem: agent context drifts2. The idea: what if agent context had a package.json?3. The 3 strong guaranteesPortable by manifestSecure by defaultGoverned by policy4. What an APM package can contain5. The five commands you'll actually use6. ...
-
Tiberius: A Security Testing Framework for LLM Applications in Java
Table of Contents 1. The Problem2. What Tiberius Does2.1 Fixture-Based Regression Testing2.2 Guardrail Validation Against Real Attack Data2.3. Probabilistic Security Contracts2.4. Bias Testing2.5. Model Fingerprinting3. Attack Coverage3.1 Buff Mutations4. Integration5. The Case for Shared Attack Datasets6. Security Testing as a …
-
BoxLang AI 3.2.0 — Image Generation, Web Search, Fluent Audio, Agent Registry & MCP Observability
BoxLang AI 3.2.0 is here, and it’s a landmark release. We’re shipping five major features: image generation, web search, a fluent audio builder API, a centralized agent registry, and deep MCP observability along with a suite of analytics improvements and …
-
Context Is a Budget — Eight levers and three workflow patterns
Table of Contents Where the tokens actually goThe Eight LeversA. Context engineering — scope your asksB. Prompt caching — order mattersC. Tool & MCP hygiene — every schema is a taxD. Custom instructions & skills — codify it onceE. Model …
-
Introducing skills.boxlang.io — The Open Agent Skills Ecosystem for BoxLang & the Ortus World
Table of Contents 🤔 The Problem: AI Knowledge Doesn’t Scale by Copy-Paste🎓 What Is a Skill?📥 Install in Seconds: Two Paths, One Standard⚡ Option 1 — npx skills (works everywhere)🥊 Option 2 — ColdBox CLI (deep BoxLang/ColdBox integration)🔷 Core Repositories …
-
How to Develop AI Agents Using BoxLang AI: A Practical Guide
Table of Contents What we’ll CoverPrerequisitesStep 1 — Install BoxLangStep 2 — Install the bx-ai ModuleStep 3 — Set Up Your .env FileStep 4 — Configure config/boxlang.jsonStep 5 — Run Your First ScriptWhat Are AI Agents?What Is BoxLang AI?Core Concept …
-
BoxLang AI Deep Dive — Part 7 of 7: MCP — The Protocol That Connects Everything
Table of Contents 🔌 Consuming MCP Servers — The Client SideSeeding Agents with MCP ServersHow MCPTool Works🖥️ Building MCP Servers — The Server SideSimple ServerHTTP Transport for WebWeb Application Integration🔒 Enterprise Security FeaturesCORSRequest Body Size LimitsAPI Key ValidationAutomatic Security HeadersSecurity …
-
BoxLang AI Deep Dive — Part 6 of 7: Memory Systems & RAG — Building AI That Remembers
Table of Contents 🧠 Two Categories of Memory📋 Standard Memory TypesSummary Memory — How It Actually Works🔍 Vector Memory TypesHybrid Memory — The Best of Both🏢 Per-Call Multi-Tenant Identity Routing📚 Document Loaders🔗 Building a Complete RAG PipelineStep 1: IngestStep 2: …
-
BoxLang AI Deep Dive — Part 2 of 7: Building a Production-Grade AI Tool Ecosystem
Table of Contents 🏗️ The Tool Hierarchy🧱 BaseTool — The Abstract FoundationFluent Schema Description⚡ ClosureTool — Zero-Boilerplate Tool CreationTools Get the Full Chat Request🗄️ The Global AI Tool RegistryModule Namespacing@AITool Annotation ScanningTwo-Step Resolution🔧 Built-In Core Tools — now@bxai🔌 MCPTool — …
-
BoxLang AI Deep Dive — Part 1 of 7: The Skills Revolution 🎓
Table of Contents 🧠 What Is a Skill?📄 The SKILL.md File Format🔧 Creating Skills⚡ Two Injection ModesAlways-On SkillsLazy / Available SkillsThe loadSkill Tool — Auto-Registered, Not MagicPromoting Lazy Skills Mid-Session🌍 Global Skills Pool🎨 How Skills Render🔍 Introspection📋 Full Skills API …
-
JC-AI Newsletter #15
Over the past two weeks, the field of artificial intelligence has continued its remarkable pace of advancement. As AI becomes increasingly woven into the fabric of daily life, shaping how we work, communicate, and make decisions, it is both timely …
