# Coatue's Frank Long Says Agents Hit Investing Next _Frank Long told AI Engineer agents will upend investing more than coding, laying out Coatue's function for turning news and positions into selection, size and timing._ **Published:** 2026-11-06 **Source:** https://www.startuphub.ai/ai-news/investors-news/2026/coatue-s-frank-long-says-agents-hit-investing-next --- Frank Long told [AI Engineer](https://www.youtube.com/watch?v=AYFcmnQrZCg) that agents will hit investing harder than coding and he demoed how Coatue is wiring that bet into its hedge fund workflow. Agents Hit InvestingDriverFrom the articleFrank Long told AI Engineer that agents will hit investing harder than coding and he demoed how Coatue is wiring that bet into its hedge fund workflow.redefinesFund As FunctionContextFrom the article 2 mentionsHe described a fund as a function that ingests external context like news, prices and filings and internal context like positions, liquidity and past notes, then outputs selection, size and timing as a portfolio time series.requiresKorean Media PipelineEffectFrom the articleUsing Korean media on semis as his case study, Long broke gathering into collect, dedupe, filter, translate, extract and cross check, treating chunking, image handling and model choice as hyperparameters to hill climb.revealsNo Single PromptDriverno prompt can compress all context into selection size timing tupleFrom the articleHe was blunt that no single prompt can compress all context into the tuple, that many steps still want deterministic code or a person in the meeting, and that LLMs still fail at mapping news to portfolio impact without human judgment plus search tools.causesLLMs Fail MappingOutcomeFrom the articleHe was blunt that no single prompt can compress all context into the tuple, that many steps still want deterministic code or a person in the meeting, and that LLMs still fail at mapping news to portfolio impact without human judgment plus search tools.Agents Hit InvestingDriverFrom the articleFrank Long told AI Engineer that agents will hit investing harder than coding and he demoed how Coatue is wiring that bet into its hedge fund workflow.redefinesFund As FunctionContextFrom the article 2 mentionsHe described a fund as a function that ingests external context like news, prices and filings and internal context like positions, liquidity and past notes, then outputs selection, size and timing as a portfolio time series.needsEvery Pixel Via APICoreFrom the articleLong said every pixel a human sees should be reachable by an agent via API, and he credited a decade of KKR led data discipline at Coatue for filing every trade note to make that exposure possible.enablesKorean Media PipelineEffectFrom the articleUsing Korean media on semis as his case study, Long broke gathering into collect, dedupe, filter, translate, extract and cross check, treating chunking, image handling and model choice as hyperparameters to hill climb.tuned asHyperparameters Hill ClimbContextFrom the articleUsing Korean media on semis as his case study, Long broke gathering into collect, dedupe, filter, translate, extract and cross check, treating chunking, image handling and model choice as hyperparameters to hill climb.showsNo Single PromptDriverno prompt can compress all context into selection size timing tupleFrom the articleHe was blunt that no single prompt can compress all context into the tuple, that many steps still want deterministic code or a person in the meeting, and that LLMs still fail at mapping news to portfolio impact without human judgment plus search tools.needsHuman Plus CodeEffectFrom the article 2 mentionsHe was blunt that no single prompt can compress all context into the tuple, that many steps still want deterministic code or a person in the meeting, and that LLMs still fail at mapping news to portfolio impact without human judgment plus search tools.stillLLMs Fail MappingOutcomeFrom the articleHe was blunt that no single prompt can compress all context into the tuple, that many steps still want deterministic code or a person in the meeting, and that LLMs still fail at mapping news to portfolio impact without human judgment plus search tools. He described a fund as a function that ingests external context like news, prices and filings and internal context like positions, liquidity and past notes, then outputs selection, size and timing as a portfolio time series. Long said every pixel a human sees should be reachable by an agent via API, and he credited a decade of KKR led data discipline at Coatue for filing every trade note to make that exposure possible. Using Korean media on semis as his case study, Long broke gathering into collect, dedupe, filter, translate, extract and cross check, treating chunking, image handling and model choice as hyperparameters to hill climb. He was blunt that no single prompt can compress all context into the tuple, that many steps still want deterministic code or a person in the meeting, and that LLMs still fail at mapping news to portfolio impact without human judgment plus search tools. The practical consequence he flagged is not one agent but an effectively infinite graph of nodes, each with at least ten hyperparameters and four runner types of code, stats, LLM and human, across every data source. --- Original analysis from [startuphub.ai](https://www.startuphub.ai), the #1 AI startup directory. © StartupHub.ai. All rights reserved. You may not republish this article in full without a license. Search engines and AI research tools may crawl and summarize for reference. Bulk reproduction or model training on this content requires a license. See https://www.startuphub.ai/terms.