Skip To Main Content
Francesco Marconi on Muck Rack

Francesco Marconi

New York
As seen in: LinkedIn, Medium, HuffPost, The Wall Street Journal, CNBC, The Toronto Star, Observer, LSE Connect, Nieman Lab, DEV Community and
Computational Journalist and CEO @AppliedXL | Prev @WSJ @AP | Author "Newsmakers: Artificial Intelligence and the Future of Journalism" @ColumbiaUP

Get in touch with Francesco

Contact Francesco, search articles and posts on X, monitor coverage, and track replies from one place.

Learn more about Muck Rack

Actions

Share this page

Francesco Marconi’s Biography

Read Full Bio →

Francesco Marconi is the manager of strategy and corporate development at the Associated Press, where he identifies new investment and partnership opportunities for the news agency. Francesco studied business and journalism at the University of Missouri and completed his post graduate work as a Chazen Scholar at Columbia Business School’s Media Program. In 2014 he joined Harvard University’s Berkman Center for Internet and Society as an affiliate researcher studying the impact of data in journa…

Articles

Compiling a Dungeon: A Real-World ISL Case Study

|
By Francesco Marconi
| DEV Community
Bonus chapter — Engineering Intent Series Live demo: dungeon-demo-isl.netlify.app Source: example/dungeon/ in the ISL repository The first four articles of this series argued, from different angles, that LLM-driven development becomes predictable only when you replace prompts with a compilable specification. That is a strong claim, and a small toy app is not enough to defend it.
Open in Who Shared Issue with article?

Part 4 of 4 — Engineering Intent Series : ISL v1.6.2: Evolution for Complex Systems

|
By Francesco Marconi
| DEV Community
Introduction This article is a standalone look at the 1.6.2 changes, but it also builds on the ideas introduced in earlier pieces of the series: Article 1: The Ambiguity Tax Article 2: The ISL Solution Article 3: The Tooling Engine Version 1.6.2 is not about redesigning ISL. It is about formalizing patterns that already exist in real projects and removing the ambiguity that emerges when those patterns are left implicit.
Open in Who Shared Issue with article?

Part 1 of 3 — Engineering Intent Series - Stop Prompting, Start Compiling: The Path to Predictable AI-Generated Code

|
By Francesco Marconi
| DEV Community
If you use LLMs to generate code, you are likely dealing with a "Slot Machine" workflow. You pull the lever with a prompt, get a great result, and then — two days later, on a different model, or with a different colleague — the same request produces something completely different. Different patterns, different variable names, different bugs. In software engineering, this inconsistency has a name: The Ambiguity Tax.
Open in Who Shared Issue with article?
See all 83 licensed articles (84 Total)