MCP vs API: why the third AI agent costs more than the first
MCP vs API in plain English for department heads and CXOs. One remote per device against one USB-C port, and the sum that decides what your agents cost.
Agentic in Production
I help enterprises take agentic AI from demo to production.
I have watched the same agent project fail the same three ways in company after company. Since 2017 I have built Ailoitte into a 70-engineer AI studio that has shipped 300+ products, and lately Leverge AI, with 306 agents running in production across 13 business functions. This site is where I write down what works, what breaks, and how to run agents you can trust with real work.
The ideas
Three names for things I kept having to explain. Each has a page of its own.
Agentic in Production
Agentic in Production is the practice of running AI agents on real enterprise work, every day, with bounded failures, an audit trail, a named owner and a budget.
AI Velocity Pods
An AI Velocity Pod is a small senior team that takes an agentic AI outcome from definition to production for a fixed price, owning the evaluation set, the refusal list and the runbook as deliverables.
AI-DLC
AI-DLC (AI Development Lifecycle) is a software lifecycle in which agents do a large share of the writing, testing and operating, and humans own the definition of done, the review of intent, and the decision to release.
Essays
Forward deployed engineers are a symptom, not a cure
Gartner's guide to forward deployed engineering says the quiet part - vendors embed engineers because their platforms cannot ship alone. What to demand instead.
What 306 agents in production taught me about enterprise AI
Leverge runs 306 agents across 13 functions. Where they cluster, why the process is the unit rather than the agent, and the rule that makes enterprises say yes.
Playbooks
SDLC vs AI-DLC: why technology leaders are switching
A working guide to AI-DLC for CTOs and VPs of Engineering - what changes at each stage, what it returns, what goes wrong, and how to explain it to your board.
Agentic AI reference architecture for enterprise
A six-layer reference architecture for enterprise AI agents - work definition, orchestration, tools, memory, guardrails, operations - with steps and checklists.
Latest field note
The pull request nobody could review
An agent's 3,100-line pull request passed every test and was approved in 25 minutes. It had quietly changed how money rounds. Why AI-DLC caps the unit of work.