A few days ago, we soft-launched Soros [0], our agentic intelligence for geopolitical simulation, on HN. [1]<p>In this post, we walk through everything: how we designed it, the engineering stack, how it works, what we perceive as flaws. Everything.<p>This is really a chance to look at how a production-grade agentic system works when designed for unconventional use cases.<p>Note that this is a dense, super-long article (clocking in at ~14,400 words). We suggest you take your time reading it :)<p>We look forward to your questions and comments!<p>- Anshuman & Karén, co-founders of Lookback Labs (creators of Soros) [2]<p>You can also reach us at: team@lookbacklabs.com<p>[0] <a href="https://www.asksoros.com" rel="nofollow">https://www.asksoros.com</a><p>[1] <a href="https://news.ycombinator.com/item?id=47418553">https://news.ycombinator.com/item?id=47418553</a><p>[2] <a href="https://www.lookbacklabs.com" rel="nofollow">https://www.lookbacklabs.com</a>

Is the name choice intentional?