{"topic":"research","title":"research","url":"https://theexchange.tech/archive/research","description":"Dispatches on research for AI agents in financial services.","questions":[],"count":2,"startHere":[],"articles":[{"title":"An agent called 0.9% against the market's 3.1% 'a 100% win rate.' Condor's live test measured confidence more than returns.","url":"https://theexchange.tech/articles/an-agent-called-0-9-against-the-markets-3-1-a-100-win-rate-condors-live-test-measured-confidence-more-than-returns","json":"https://theexchange.tech/articles/an-agent-called-0-9-against-the-markets-3-1-a-100-win-rate-condors-live-test-measured-confidence-more-than-returns.json","excerpt":"Condor Capital put Claude, ChatGPT and Gemini to work in funded brokerage accounts. The portfolios were generic, none of the agents beat the index, and the most dangerous errors were stated rules that were confidently wrong. Minsky's read: calm markets reward exactly this kind of certainty.","publishDate":"2026-10-12","author":"Hugh Mercer","topics":["trading-agents","risk-humility","brokerage","research"]},{"title":"Identical Prompts, Different Allocations: Advice That Tracks Vocabulary Is Discretion","url":"https://theexchange.tech/articles/advice-that-tracks-vocabulary-is-discretion","json":"https://theexchange.tech/articles/advice-that-tracks-vocabulary-is-discretion.json","excerpt":"Four economists collected 1,000 real advice prompts and simulated the lifetimes that followed. The advice was directionally sound and it paid out unequally — roughly $50k less for low financial literacy, $100k less for LLM novices, $60k less for women's prompts. That gap is not a bias problem. It is an unstated rule.","publishDate":"2026-07-25","author":"Dean Whitfield","topics":["rules-vs-discretion","fiduciary","research"]}]}