<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Kepler Blog</title><description>Insights and updates from the Kepler team.</description><link>https://kepler.ai/</link><item><title>What year is it?</title><link>https://kepler.ai/blog/2026/11/11/what-year-is-it/</link><guid isPermaLink="true">https://kepler.ai/blog/2026/11/11/what-year-is-it/</guid><description>A journey through fiscal years in SEC filings</description><pubDate>Wed, 11 Nov 2026 00:00:00 GMT</pubDate></item><item><title>Build vs Buy AI in Finance</title><link>https://kepler.ai/blog/2026/11/03/build-vs-buy-ai-in-finance/</link><guid isPermaLink="true">https://kepler.ai/blog/2026/11/03/build-vs-buy-ai-in-finance/</guid><description>Buy what every firm needs, then build your edge. Where the build vs buy line sits for hedge funds, private equity, credit, allocators and banks.</description><pubDate>Tue, 03 Nov 2026 00:00:00 GMT</pubDate></item><item><title>Deterministic AI: What It Means, Where It Breaks, and Where It Belongs</title><link>https://kepler.ai/blog/2026/10/27/deterministic-ai/</link><guid isPermaLink="true">https://kepler.ai/blog/2026/10/27/deterministic-ai/</guid><description>Enterprise AI vendors all promise determinism. Here&apos;s what the word actually covers, why everyone is talking about it, and which parts of an AI system should be deterministic.</description><pubDate>Tue, 27 Oct 2026 00:00:00 GMT</pubDate></item><item><title>The Compiler That Never Says No</title><link>https://kepler.ai/blog/2026/10/06/the-compiler-that-never-says-no/</link><guid isPermaLink="true">https://kepler.ai/blog/2026/10/06/the-compiler-that-never-says-no/</guid><description>English is now a programming language whose compiler runs unclear instructions as readily as clear ones. Clear writing is the scarcest skill in technical work.</description><pubDate>Tue, 06 Oct 2026 00:00:00 GMT</pubDate></item><item><title>Your Mistakes Are a Dataset</title><link>https://kepler.ai/blog/2026/10/01/your-mistakes-are-a-dataset/</link><guid isPermaLink="true">https://kepler.ai/blog/2026/10/01/your-mistakes-are-a-dataset/</guid><description>When a system gets something right for the 10,000th time, you learn little. When it&apos;s wrong for the first time, you may have found what nobody knew to test for.</description><pubDate>Thu, 01 Oct 2026 00:00:00 GMT</pubDate></item><item><title>Kepler in Claude: A Working Guide for Analysts</title><link>https://kepler.ai/blog/2026/09/02/kepler-in-claude/</link><guid isPermaLink="true">https://kepler.ai/blog/2026/09/02/kepler-in-claude/</guid><description>Claude does the reasoning and Kepler does the retrieval and arithmetic, with every figure one click from the filing.</description><pubDate>Wed, 02 Sep 2026 00:00:00 GMT</pubDate></item><item><title>From Zero Context to Shipping</title><link>https://kepler.ai/blog/2026/08/24/from-zero-context-to-shipping/</link><guid isPermaLink="true">https://kepler.ai/blog/2026/08/24/from-zero-context-to-shipping/</guid><description>AI is collapsing the cost of understanding unfamiliar systems. The bottleneck moves to separating what you&apos;ve observed from what you&apos;ve inferred.</description><pubDate>Mon, 24 Aug 2026 00:00:00 GMT</pubDate></item><item><title>Two Forms of a Table</title><link>https://kepler.ai/blog/2026/06/30/two-forms-of-table/</link><guid isPermaLink="true">https://kepler.ai/blog/2026/06/30/two-forms-of-table/</guid><description>Three frontier models can&apos;t agree on the average of one column in a clean table. Why the form you read and the form you compute on differ, and why both matter.</description><pubDate>Tue, 30 Jun 2026 00:00:00 GMT</pubDate></item><item><title>The Real Painkiller for Financial Analysts: Kepler on the GameStop-eBay Deal</title><link>https://kepler.ai/blog/2026/06/17/painkiller-gamestop-ebay/</link><guid isPermaLink="true">https://kepler.ai/blog/2026/06/17/painkiller-gamestop-ebay/</guid><description>Using the GameStop-eBay bid, we run Kepler through four workflows that give analysts headaches, and show verifiable, accurate analysis in minutes, not days.</description><pubDate>Wed, 17 Jun 2026 00:00:00 GMT</pubDate></item><item><title>Elegant and Wrong</title><link>https://kepler.ai/blog/2026/06/03/elegant-and-wrong/</link><guid isPermaLink="true">https://kepler.ai/blog/2026/06/03/elegant-and-wrong/</guid><description>49.8% of an S-1&apos;s cells are empty. The clean data model you reach for first is a hypothesis the data can reject, and that shaped how we built citations.</description><pubDate>Wed, 03 Jun 2026 00:00:00 GMT</pubDate></item><item><title>How Quartr Helps Kepler Build Citation-Grade Earnings Research</title><link>https://kepler.ai/blog/2026/06/02/how-quartr-helps-kepler-build-citation-grade-earnings-research/</link><guid isPermaLink="true">https://kepler.ai/blog/2026/06/02/how-quartr-helps-kepler-build-citation-grade-earnings-research/</guid><description>How Kepler cites earnings answers across the SEC filing, the Quartr transcript, and the IR deck, with the language model never touching the numbers.</description><pubDate>Tue, 02 Jun 2026 00:00:00 GMT</pubDate></item><item><title>Why Data Pipelines Need Stronger Guardrails in the AI Era</title><link>https://kepler.ai/blog/2026/05/28/developing-pipelines-faster-in-the-ai-era/</link><guid isPermaLink="true">https://kepler.ai/blog/2026/05/28/developing-pipelines-faster-in-the-ai-era/</guid><description>AI can help you build faster than ever, but without the right guardrails it can silently erode trust and drive you off a cliff.</description><pubDate>Thu, 28 May 2026 00:00:00 GMT</pubDate></item><item><title>The Yardstick Problem</title><link>https://kepler.ai/blog/2026/05/20/the-yardstick-problem/</link><guid isPermaLink="true">https://kepler.ai/blog/2026/05/20/the-yardstick-problem/</guid><description>You can&apos;t unit-test a probability distribution. In our double-entry evals, code grades numbers, an LLM grades prose, and most value is where they disagree.</description><pubDate>Wed, 20 May 2026 00:00:00 GMT</pubDate></item><item><title>Eagerness solves most problems. Judgement solves the ones we work on.</title><link>https://kepler.ai/blog/2026/05/18/eagerness-vs-judgement/</link><guid isPermaLink="true">https://kepler.ai/blog/2026/05/18/eagerness-vs-judgement/</guid><description>Why building infrastructure for AI rewards pattern recognition over effort, and how that has reshaped how Kepler hires and operates.</description><pubDate>Mon, 18 May 2026 00:00:00 GMT</pubDate></item><item><title>FDEs in the Dark</title><link>https://kepler.ai/blog/2026/04/23/fdes-in-the-dark/</link><guid isPermaLink="true">https://kepler.ai/blog/2026/04/23/fdes-in-the-dark/</guid><description>The Forward Deployed Engineer was built to close the gap between software and reality. AI broke that model: an FDE without traceability can&apos;t find the answer.</description><pubDate>Thu, 23 Apr 2026 00:00:00 GMT</pubDate></item><item><title>How Parallel Helps Kepler Build AI That Finance Professionals Can Actually Trust</title><link>https://kepler.ai/blog/2026/03/17/how-parallel-helps-kepler-build-trustworthy-ai-for-finance/</link><guid isPermaLink="true">https://kepler.ai/blog/2026/03/17/how-parallel-helps-kepler-build-trustworthy-ai-for-finance/</guid><description>Kepler uses Parallel&apos;s Search API for discovery, pairing AI&apos;s grasp of open-ended questions with deterministic infrastructure for accuracy and auditability.</description><pubDate>Tue, 17 Mar 2026 00:00:00 GMT</pubDate></item><item><title>The Context Wall</title><link>https://kepler.ai/blog/2026/03/05/the-context-wall/</link><guid isPermaLink="true">https://kepler.ai/blog/2026/03/05/the-context-wall/</guid><description>Source-cited chat hits four walls: latency, cost, prompt-following degradation, and a context limit. Solving them meant rethinking what a conversation is.</description><pubDate>Thu, 05 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Equity Research in the Age of AI: What Actually Needs to Change</title><link>https://kepler.ai/blog/2026/02/27/equity-research-in-the-age-of-ai/</link><guid isPermaLink="true">https://kepler.ai/blog/2026/02/27/equity-research-in-the-age-of-ai/</guid><description>Equity research is built on precision. AI doesn&apos;t need to replace judgment; it needs to remove operational drag and keep every number verifiably correct.</description><pubDate>Fri, 27 Feb 2026 00:00:00 GMT</pubDate></item><item><title>Context Is the Easy Part</title><link>https://kepler.ai/blog/2026/02/13/context-is-the-easy-part/</link><guid isPermaLink="true">https://kepler.ai/blog/2026/02/13/context-is-the-easy-part/</guid><description>Everyone&apos;s talking about context engineering. Context engineering isn&apos;t a context problem. It&apos;s an engineering problem.</description><pubDate>Fri, 13 Feb 2026 00:00:00 GMT</pubDate></item><item><title>Trust in the Age of AI</title><link>https://kepler.ai/blog/2026/02/10/trust-in-the-age-of-ai/</link><guid isPermaLink="true">https://kepler.ai/blog/2026/02/10/trust-in-the-age-of-ai/</guid><description>What does it mean to trust AI? Accuracy, security, and credulity are three related challenges, and forcing AI to show its work changes the output itself.</description><pubDate>Tue, 10 Feb 2026 00:00:00 GMT</pubDate></item><item><title>The AI Era of Finance: A Practitioner&apos;s View</title><link>https://kepler.ai/blog/2026/02/06/the-ai-era-of-finance/</link><guid isPermaLink="true">https://kepler.ai/blog/2026/02/06/the-ai-era-of-finance/</guid><description>LLMs excel at summarizing but struggle with the one thing finance can’t compromise on: numerical truth. Without traceability, AI risks accelerating errors.</description><pubDate>Fri, 06 Feb 2026 00:00:00 GMT</pubDate></item><item><title>Why I Joined Kepler</title><link>https://kepler.ai/blog/2026/02/03/why-i-joined-kepler/</link><guid isPermaLink="true">https://kepler.ai/blog/2026/02/03/why-i-joined-kepler/</guid><description>After Meta and four seed-stage startups, Susannah, Kepler’s Founding Engineer, shares why building fully traceable AI was a challenge she couldn’t pass up.</description><pubDate>Tue, 03 Feb 2026 00:00:00 GMT</pubDate></item><item><title>Introducing Kepler</title><link>https://kepler.ai/blog/2026/01/30/introducing-kepler/</link><guid isPermaLink="true">https://kepler.ai/blog/2026/01/30/introducing-kepler/</guid><description>We&apos;re building the infrastructure that gives AI a foundation of verified data, traceable to its source and precise enough to follow wherever it leads.</description><pubDate>Fri, 30 Jan 2026 00:00:00 GMT</pubDate></item></channel></rss>