#Prompt Injection

Articles about Prompt Injection — exploring patterns, best practices, and real-world implementations in production systems.

1 post tagged with prompt injection. ← All posts

A2A (5)ADK (8)AG-UI (7)AI Agents (232)AI Governance (5)Agent Skills (3)Agentic AI (13)Agents (4)Architecture (15)Azure (9)Azure AI Foundry (10)BigQuery (6)Checkpointing (5)Compliance (8)Concurrency (4)Context Providers (3)Conversation State (3)Cost Optimisation (3)Distributed Systems (3)Evaluation (4)FREE-AI (8)FinOps (5)FinTech (6)Function Tools (6)GCP (5)Go (168)Google ADK (26)Governance (5)Guardrails (3)HIPAA (3)Harness Engineering (8)Human-in-the-Loop (7)KYC (3)Kubernetes (6)LangGraph (11)Microsoft Agent Framework (21)MCP (5)Memory (5)Microsoft Agent Framework (188)Middleware (9)Multi-Agent (8)Multi-Agent AI (13)Multimodal (4)Observability (12)Open Source (6)OpenTelemetry (5)Opinion (6)Orchestration (15)Payments (4)Privacy Engineering (3)Prompt Injection (1)Providers (3)Python (126)RAG (6)RBI (3)Retrieval (3)SRE (3)Security (9)Sessions (4)Spanner (4)Streaming (4)Structured Output (4)Workflows (14)
Pratik Dhanave · ·7 min read

The Agent Harness: guardrails as middleware around the model

Lesson 1 of Harness Engineering in Go — why the input guardrail is a hard block, not a warning, and how a plain `net/http` handler wraps the model call so it tests without a running server.

Lesson 1: why the input guardrail is a hard block rather than flag-and-pass, why it counts runes instead of bytes, and how a plain net/http handler wraps the (stubbed) model call so it tests with httptest.

All posts on this site are written by Pratik Dhanave, an Agentic AI Architect with 7+ years building production distributed systems, multi-agent AI platforms, and cloud-native infrastructure. About the author → Each article includes working code, architecture diagrams, and references to the specific frameworks and standards discussed. Browse all posts or explore related topics using the tag cloud above.