I spent more than four decades building and leading software systems. I have retired from corporate life and now work as an independent advisor, author, and researcher focused on distributed systems, desktop architectures using local LLMs, and software engineering in the age of AI. I am the author of several O'Reilly books and have spoken at numerous industry conferences, and am currently completing a practitioner's guide to applying spec-surface engineering in the construction of LLM-assisted systems.
My current research centers on how engineering discipline must adapt when implementation tools are probabilistic. I am building a production financial planning system as a primary research instrument — a working system that makes the question of correctness in LLM-assisted development concrete and measurable. The core claim: LLMs don't break software correctness — they relocate where it must be governed.
Availability
I am available for speaking engagements, advisory work, and consulting on software engineering discipline in the age of AI, natural language interface architecture, and LLM-assisted system design. If you are building systems where correctness under probabilistic generation matters, I am interested in the conversation. Reach me at robert.englander@gmail.com.
Recent Writing
-
Engineering Natural Language Interfaces: Compiling Intent
A practitioner survey of approaches for compiling natural language into validated commitments — classical pipelines, constrained decoding, structured outputs, logprob overlays, and judge-based confidence mechanisms.
-
The Future of Software May Be Conversational Rather Than Autonomous
The most durable role for LLMs may not be replacing deterministic systems — it may be reducing the friction between people and those systems.
-
Conversational Software Engineering: Compiling Intent
A concrete approach to LLM-assisted engineering: conversation as the control surface, specifications compiled into a validated artifact, and the compiled spec as the center of gravity everything else derives from.
-
AI Didn't Simplify Software Engineering: It Just Made Bad Engineering Easier
AI tools lower the barrier to producing code, not to building reliable systems. The hard part — maintaining alignment between specifications, tests, and implementation — has not gone away. Expertise still matters.
-
Engineering Alignment in Probabilistic Generation
A structural model for achieving and maintaining correctness in LLM-assisted systems, grounded in the construction of a production financial planning system.
-
Governing Correctness in LLM-Assisted Development
LLMs don't break software correctness — they relocate where correctness must be governed. A practitioner account of boundary drift and how to prevent it.
Books
- Developing Java Beans
- Java & Soap
Speaking
- Atlassian's Lithium Platform: Dynamic Self-Hosted and Distributed Ephemeral
- Atlassian's Lithium Platform: Dynamic Self-Hosted and Distributed Ephemeral
- Sun Grid Demo — James Gosling's Toy Show Keynote