Tag: AI agents
-
Prompt Injection and the Security Model of an LLM Application (AI Engineering Series, Part 24)
Prompt injection is not a filtering problem. Here is how an instruction hidden in a support ticket made my assistant fire 63 escalations, and the tool permission model that took attack success from 71.7 percent down to 3.3 percent.
-
Human in the Loop and Approval Gates for LLM Agents (AI Engineering Series, Part 19)
Pausing an agent for approval is the easy half. This part builds an approval gate in the OpenAI Agents SDK and in LangGraph, then explains why the gate has to be enforced at the service that moves the money rather than inside the agent process.
-
Multi Agent Patterns and Their Coordination Cost (AI Engineering Series, Part 18)
Subagents, handoffs, router and skills compared on measured token and model call counts, plus the coordination ratio I use to decide whether a split is worth paying for. Includes the handoff bug that returns a 400 and how to avoid it.
-
Multi Step Workflows, State and Memory in LLM Applications (AI Engineering Series, Part 17)
A checkpointer is a crash recovery log, not memory, and confusing the two is how a support assistant ends up carrying 47,000 tokens of unrelated history into every request. Threads, checkpoints, stores and compaction, with runnable LangGraph code.
-
Model Context Protocol and Standardising Tool Access, With a Working Python Server (AI Engineering Series, Part 16)
Part 14 gave the support assistant a working tool loop. This part turns those hand wired functions into an MCP server any client can discover, with the transport choice, the failure modes and the context cost measured rather than assumed.
-
Agent Loops and Planning, and When an Agent Is the Wrong Answer (AI Engineering Series, Part 15)
An agent loop is a cost decision before it is an architecture decision. This part covers how the loop works, why per step accuracy compounds against you, the four workflow patterns that beat an agent in production, and the decision table I use to choose between them.
-
Tool Calling From First Principles, With Python and a Real Loop (AI Engineering Series, Part 14)
Tool calling is a protocol, not a capability the model gains. Here is the full loop in Python, the schema decisions that cut wrong calls, and the two errors every tool calling app hits in its first week.
-
watsonx Reference Architectures for RAG, Agentic, and Regulated Workloads (IBM Gen AI Series, Part 23)
The three watsonx reference architectures that recur in real builds: enterprise RAG on watsonx.data, agentic systems on watsonx Orchestrate, and a watsonx.governance overlay for regulated work. Which to build first, what each costs, and where they break.
-
Building Agents on watsonx Orchestrate with the ADK (IBM Gen AI Series, Part 15)
How to build a native agent on watsonx Orchestrate with the ADK, wire its tools, collaborators, and knowledge, pick the right agent style, and keep multi-agent routing from wrecking your bill.
-
Gemini Enterprise and Agentspace, Enterprise Agents for Every Employee (Google Cloud Gen AI Series, Part 22)
Google Agentspace is now Gemini Enterprise, the per seat front door that puts search and a gallery of agents in front of every employee. What it includes, how a request flows, what a seat costs, and when to buy it instead of building your own.
-
Multi-Agent Systems on Vertex AI with ADK and Agent Engine (Google Cloud Gen AI Series, Part 21)
One big agent with twenty tools rots fast. Here is how to split it into a coordinator and typed sub-agents with the ADK, choose deterministic versus LLM-driven flows, connect across boundaries with A2A, and deploy to Vertex AI Agent Engine.
-
Vertex AI Agent Builder and the ADK, From Local Agent to Managed Runtime (Google Cloud Gen AI Series, Part 13)
Build an agent in code with the ADK, deploy it to the managed runtime, and see what the always-on replica really costs before your first user shows up.
Architect’s Toolkit
PJ’s Tools
- Infra 360 Hub – All Series
- VCF 9 Interactive Walkthroughs
- VCF Design Cheatsheet
- VCF Upgrade Planner
- VCF 9 Series Hub
- VCF Deployment Hub
- AI Stack Hub
- AI Infra Sizing & Cost Calculator
- LLM & RAG Cost Calculator
- DrJhaGPT – Ask Pranay
VMware Cloud Foundation
- VCF Documentation
- VCF 9 Planning & Preparation Workbook
- VCF Bill of Materials (BoM)
- VMware Compatibility Guide
- VMware Interoperability Matrix
- VMware Configuration Maximums
- VMware Ports & Protocols
- VMware Hands-on Labs
- RVTools Download
Nutanix
AI & Cloud-Native Platform
- NVIDIA Build (Model Catalog)
- NVIDIA AI Enterprise Reference Architecture
- NVIDIA NIM Performance Benchmarking
- NVIDIA NGC Catalog
- NeMo Microservices Helm Chart
- Helm Charts Repository
- Hugging Face Models
Architecture & Design
About the Author
Dr Pranay Jha
Dr. Pranay Jha is a Cloud and AI Consultant with 18+ years of experience in hybrid cloud, virtualization, and enterprise infrastructure transformation. He specializes in VMware technologies, multi-cloud strategy, and Generative AI solutions. He holds a PhD in Computer Applications with research focused on Cloud and AI, has published multiple research papers, and has been a VMware vExpert since 2016 and a VMUG Community Leader.
You May Have Missed
DrJha