Blog

All articles

• Equity research on UK-listed companies: what changes from the US 2026-10-31
  UK companies report twice a year, trade in pence, pay 0.5% on every share purchase and are bought under a takeover code with no US equivalent. What changes for an analyst covering London, and how Matterfact's agent keeps the UK's rules current.
• Equity research in Japan, Korea and Taiwan: what changes from the US 2026-10-31
  In Japan, Korea and Taiwan the fiscal calendar, the units, the takeover rules and the taxes a fund pays all differ from the US, often in ways that raise no error. What changes, and how Matterfact's agent keeps each market's rules current.
• How investors are generating alpha from podcasts 2026-10-31
  Our September webinar as 14 slides: executives speak more candidly on podcasts than in their releases, operators give you the channel check on tape, and an agent can place every strategist's call side by side.
• Harness Matters, Part 2: Why a leaderboard can point you to the wrong model 2026-10-31
  On Vals AI's finance leaderboard, Claude Opus 5.5 ranks 10th. Inside the agent our analysts use, it came first of four, and the fastest and cheapest. What we ran, what it suggests about choosing a model for finance, and what it can't prove.
• Harness Matters, Part 1: How to test the public-data tools behind an AI research agent 2026-10-31
  Public-data tools rarely throw an error; they hand your agent a believable wrong number. Here is the three-step test we ran on Matterfact's FINRA, economic and court-record tools, what it caught, and four questions to ask of any data tool behind an AI agent.
• The most comprehensive short-signal skills library: What generic red-flag checklists miss 2026-10-30
  A backlog, a jump in cash flow or an auditor change can mean opposite things in different industries, so Matterfact's short-signal skills give our research agent the industry-specific tells, primary records and short-killers that a specialist short seller checks.
• An Agent Swarm on CoreWeave 2026-10-29
  A Matterfact agent swarm researched CoreWeave for two weeks. It withdrew its own first-day long, committed a fair value of $44.21 with a small underweight, then paused. Here is what it found, and what it got right and wrong once the market tested it.
• An Agent Swarm on Hims & Hers 2026-10-28
  A Matterfact agent swarm spent seven weeks researching Hims & Hers ahead of its 9 November results. It puts fair value below the share price, and still sees no trade worth taking. Here is what it found, and why.
• An Agent Swarm on Borr Drilling 2026-10-27
  A Matterfact agent swarm researched Borr Drilling non-stop for more than three weeks. It valued the shares at less than half their price, and still advised against a short. Here is what it found, and why.
• Introducing Matterfact Agent Swarms 2026-10-26
  The frontier of AI in finance: autonomous research agents that build an investment case as a team and keep score. See what swarms found on Meta, Hims & Hers and Borr Drilling.
• Matterfact vs. Claude: What investment teams get beyond the model 2026-10-22
  Matterfact runs on Claude and builds the research desk around it: agent swarms that work around the clock, methods for every sector, answers that carry their evidence, and the fund's own data inside its own tenant.
• Introducing For You: Every name you cover, tracked automatically 2026-10-20
  For You, Matterfact's new home page, learns the names you cover from your own work and tracks the filings, calls, news, podcasts and broker research on them and on the companies around them, with no alerts to set up.
• A bank model is not a steel model: How Matterfact builds financial models industry by industry 2026-10-16
  Hoping Claude will give you an investing edge is not a strategy: every fund has the same model, and the last mile is specific to each industry, so Matterfact's agent builds every model in a harness of industry skills, data tools and checks that catch what a fluent model gets wrong.
• Production-grade evals for LLMs in finance: What leaderboards miss 2026-10-14
  Finance evals should test models inside the agent that will run them, and have practitioners review the rubrics that grade them.
• Introducing News Read-Throughs 2026-10-08
  The news that moves a stock is often about another company. Read-throughs, new in Matterfact News, find those stories for every name you cover, judge what each one means for that name, and show how the stock took it.
• What Minecraft taught us about hill climbing for AI in finance: A first look at our skills research 2026-10-06
  Game-playing AI climbed Minecraft's tech tree by keeping only the skills that passed a check; Matterfact hill-climbs toward a specialist's knowledge of every industry the same way, with primary records as the signal that markets do not give.
• Five problems with a plain Snowflake connector, and why finance needs a harness that verifies every answer 2026-09-30
  An LLM that writes and executes SQL against a fund's warehouse returns plausible wrong aggregates whenever a join fans out or drops rows; the fix is a harness that probes every join's cardinality against the data, learns the warehouse's semantics, and enforces read-only access at the role.
• Introducing Smart Highlight for Earnings Calls 2026-09-23
  Analysts read the whole transcript because a summary can put words in management's mouth. Smart Highlight, new in Matterfact Earnings, answers your question with the sentences management actually said, on one call or across quarters and competitors.
• What a million podcast transcripts reveal: How to read the commentary around a stock 2026-09-16
  Podcast discussion follows a stock’s price rather than leading it; the useful signal is in who is talking, how one-sided the room gets and which part of the argument turns first.
• Monitoring a Watchlist in the Age of AI 2026-09-01
  Holding one German automaker means tracking twenty-eight companies, and their own investor events would eat a full quarter of your time for that name. Here is what monitoring actually costs, and what agents change.
• Latency numbers every agent builder should know 2026-08-25
  Four token counts explain 97% of LLM-call latency. Across about 2,000 production calls on Claude Opus 4.8 and Sonnet 5, generated tokens drive 94–97% of the wait, so the way to cut latency is to generate less.
• Idea Generation in the Age of AI: Where Hedge Fund Ideas Come From 2026-08-18
  13Fs are stale, screens converge on the same names, and a conference pitch is crowded the moment it is delivered. Where analysts actually find non-consensus ideas now, and how AI agents mine podcasts and run screens nobody else has.
• Research: How AI Has Changed the Hedge Fund Analyst Due Diligence Workflow 2026-08-11
  AI has not removed hedge fund due diligence. It moved the bottleneck from finding documents to proving which evidence matters. Here is what changed.
• Pitching the PM: How AI Changed the Way Analysts Sell an Idea 2026-08-04
  You can read every filing, build the model, and still lose the name in ninety seconds on one question you did not anticipate. How AI agents change pitch prep.
• The six-part formula for a better prompt 2026-07-28
  Your AI is only as good as the context you give it. The analyst's guide to prompts that produce genuinely useful investment research: a six-part formula, a full worked example on Apple, and a checklist you can reuse on Monday morning.
• The Five Functions of a Long/Short Hedge Fund Analyst Have Changed Thanks to AI 2026-07-21
  More than 95% of hedge funds now run generative AI, up from 86% in 2023. Adoption stopped being an edge. Here is where it went, across all five analyst jobs.
• Connect Matterfact to Claude 2026-06-16
  Add Matterfact to the Claude app, claude.ai, or Claude Code and search investor podcasts and pull transcripts, just by asking. A simple setup guide and FAQ.
• Announcing the Matterfact Podcast MCP Server 2026-06-09
  Matterfact's podcast MCP server brings sentiment and whispers from a million investor podcasts into Claude and ChatGPT. Ask, and get sourced answers.
• The Financial Podcast Agent: Why Top Hedge Funds Use Them and How They Actually Work 2026-06-02
  Gavin Baker wants a financial podcast agent. Here's what that means, why generic transcription falls short, and how portfolio-aware signal extraction changes research.
• What Is an AI Investment Research Platform? A Buyer's Guide 2026-05-28
  What is an AI investment research platform? A buyer's guide covering the 5 core capabilities, evaluation criteria, and how it differs from terminals and chatbots.
• Sohn 2026 Pitches Scorecard: Who's Winning, Who's Bleeding 2026-05-26
  Live tracker of all 30 Sohn 2026 Investment Conference stock picks. The Core Index beat the S&P 500 by 1.20% in 7 trading days. See who's winning and who's bleeding.
• Hedge Funds Value Teamwork Over Python Skills, Even With Engineers 2026-05-22
  We parsed 1,165 hedge fund job descriptions. Teamwork is up 31 points, tech skills are down.
• How to Not Get Fired From a Hedge Fund: The Analyst's AI Playbook 2026-05-20
  Top hedge funds are rebuilding their research process around AI. Here's the playbook for analysts who want to be indispensable.
• Inside Playbooks: A Tutorial on the 217 Pre-Engineered Research Workflows Built for Institutional Investors 2026-05-18
  A tutorial on Playbooks: 217 pre-engineered research workflows across 12 categories, from morning briefs to sector-specific KPI math. The prompt does the thinking before you arrive.
• Hedge Funds Are Hiring Like Tech Companies (And AI Isn't Stopping Them) 2026-05-14
  44% of all open hedge fund roles are for engineers. We scraped 1,555 job postings across 102 funds to show how the buy side is quietly becoming a tech industry.
• I Built a Chipotle Dashboard in 4 Minutes With Matterfact 2026-05-11
  I asked Matterfact to build a full Chipotle research dashboard with peer comps, podcast-sourced bull/bear cases, valuation analysis, and scenario modeling. It took 4 minutes.
• How to Fail with AI: Pick 5 Best Stocks, Don't Make a Mistake 2026-05-07
  In 1986, Charlie Munger told Harvard graduates how to guarantee a life of misery. Inspired by this framework we show you exactly how to guarantee disastrous results with AI in your investment process. Invert, always invert.
• Why Podcasts: The Expert Network Investors Always Wanted 2026-04-24
  Top funds treat podcasts as a primary research input. 200M hours of expert conversation, often more candid than compliance-monitored calls, should be an input into your own investment research.