Agents as customers: your business is built to keep them out
AI agents already buy, book and ask for support on people's behalf. Most businesses stop them at the door. What an agent needs from you, and what to do now.
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 test
Is your agent in production, or in a demo? Five questions, one number, a card you can post. Two minutes, no sign-up, nothing stored.
The ideas
Three names for things I kept having to explain. Each has a page of its own.
Forward deployed engineer (FDE)
A forward deployed engineer (FDE) is a vendor's engineer embedded in a customer's environment to take a product, usually an AI agent, from a signed contract to a running process, measured on the outcome rather than on hours.
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
AI SRE agents: Uber's Debug Assist, and how to adopt one
An AI SRE agent finds the root cause of a production issue and proposes the fix. How Uber's Debug Assist works, how Ailoitte runs it, and how to adopt one.
Single agent vs multi-agent AI: how CTOs should choose
Single agent or multi-agent? Atallah says ten specialists beat one superagent. Masad runs one agent across Replit. Here's how CTOs should choose.
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 approver who said yes 1,900 times
A payables agent stopped and asked a human 1,900 times in three weeks. By week three the human said yes in four seconds, once to a changed bank account.