Village
Log in

Proprietary questions over public data.

Every workspace opens with datasets built for investment questions, kept as the raw material other providers summarize away, and the connections to bring in what your firm already has.

Contact sales

  • Technographics

    The technology behind 25 million websites, kept as raw evidence.

    Dataset

    A weekly crawl of 25.7 million hosts: every origin in Google’s Chrome UX Report plus five million responsive hosts from Cloudflare’s rankings. Village keeps what the browser saw rather than a vendor label, so detection is written as SQL at query time and you decide what counts as evidence.

    What is captured
    Up to ten rendered pages per host with every network request, JSON response, cookie, and script global. Per host: DNS records, TLS certificate names, robots.txt, ads.txt, and .well-known files.
    Refresh
    Weekly crawl, 400-day archive, queried in SQL.
    Limits
    A host is not a company, and a missing signal is not a missing tool. Embeds and platforms can inflate counts, and the index measures terms on pages, not share of a site.
    Ask it
    • “Which sites run PostHog alongside Amplitude, and is that share growing?”
    • “How many stores built on Lovable sell through Shopify?”
    • “Which observability vendor is gaining among the 10,000 most-visited sites?”

  • Podcasts

    Shows and episodes across the open podcast ecosystem, searchable.

    Dataset Talk to sales

    A catalog of shows and episodes from public RSS feeds, built for the questions that only make sense once a language model can read show notes and transcripts: who appeared where, and what they said before the market cared.

    What is captured
    Show and episode metadata: titles, descriptions, guests named in show notes, publish dates, and transcript links where publishers provide them.
    Refresh
    Feeds re-crawled every five minutes.
    Limits
    Transcripts come from publishers that post them; audio is not transcribed. Episode text is read by the agent when you ask, not indexed ahead of time.
    Ask it
    • “Which podcasts has this founder appeared on this year?”
    • “Find every episode that discussed this company before its IPO.”
    Talk to sales about Podcasts

  • Subprocessors and trust centers

    Who every software company runs on, from their own trust centers.

    Dataset Talk to sales

    Subprocessor disclosures collected from public trust centers, so vendor relationships can be counted across the software industry instead of read one page at a time.

    What is captured
    Vendor, purpose, location, and scope for each listed subprocessor, with the trust center page it came from, across trust centers hosted on Vanta, Drata, SafeBase, Secureframe, and Oneleet.
    Refresh
    Weekly.
    Limits
    A trust center is self-reported and updated on the company’s own schedule. Counts are per disclosure, not per verified customer relationship.
    Ask it
    • “Which companies list Snowflake as a subprocessor, and when did they add it?”
    • “Did anyone replace Datadog with a rival this quarter?”
    Talk to sales about Subprocessors and trust centers

  • Web archive

    How any page looked on any date, back to the 1990s.

    Dataset

    The Internet Archive’s Wayback Machine, reachable from the agent, so a pricing page, a careers page, or a customer list can be read as it stood on a given date and compared with today.

    What is captured
    Archived snapshots of public pages, with the capture timestamps the archive recorded for each one.
    Refresh
    Live, from the archive’s own index.
    Limits
    Coverage depends on what the archive captured. Pages behind logins and content loaded by scripts are often missing or incomplete.
    Ask it
    • “What did this vendor’s pricing page say in 2024?”
    • “When did this careers page stop listing roles in Austin?”
    • “Which customer logos has this company removed from its homepage?”

  • Satellite imagery

    A site’s progress from orbit, as a timeline you can revisit.

    Dataset Talk to sales

    Optical and radar scenes from public satellite catalogs, found and compared by the agent so visible change at a plant, a mine, or a data center sits beside the filings and announcements about it.

    What is captured
    Sentinel-2 optical and Sentinel-1 radar scenes for a location, assembled into a dated timeline with the imagery it came from.
    Refresh
    New scenes as the satellites pass, typically every few days.
    Limits
    Cloud cover, revisit rate, and ten-meter resolution bound what is visible. Imagery is one line of evidence, not a measurement of output.
    Ask it
    • “How has construction at this site progressed since the announcement?”
    • “Compare this fab’s footprint today with a year ago.”
    Talk to sales about Satellite imagery

  • SEC EDGAR

    Every SEC filing, in full text.

    Dataset

    The SEC’s filing archive, ingested as full documents rather than extracted fields. Agents list filings by company, form type, and date, then read the whole text or the rendered PDF.

    What is captured
    Full document text and rendered PDFs for every form type, grouped into categories such as periodic reports, 8-K news, insider trading, beneficial ownership, and exempt offerings.
    Refresh
    New filings within five minutes of posting; the daily archive every morning.
    Limits
    Filings are found by company, form, and date; there is no cross-filing full-text search yet, and XBRL financial facts are not extracted as tables.
    Ask it
    • “What changed in the risk factors between this 10-K and last year’s?”
    • “Which insiders on my watchlist sold in the last 30 days?”
    • “Pull every 8-K this quarter that mentions a data center lease.”

  • Investor relations materials

    Earnings calls, slide decks, and releases, as text.

    Dataset

    Transcripts, presentations, and releases from public companies’ investor events, licensed from Quartr and processed so an agent can quote them. Slides are read with OCR; transcripts carry timestamps.

    What is captured
    Call transcripts, slide decks, press and earnings releases, and annual and interim reports across earnings calls, capital markets days, AGMs, and deal announcements.
    Refresh
    New transcripts and slides within minutes of an event.
    Limits
    Coverage follows the licensed provider and audio is not retained. Documents the SEC already publishes come from EDGAR instead of being duplicated here.
    Ask it
    • “What has management said about pricing on the last four calls?”
    • “Does the capex guidance in the deck match what was said on the call?”
    • “Which companies in my coverage held a capital markets day this year?”

  • X

    What founders, analysts, and companies say on X, as searchable data.

    Integration Talk to sales

    Posts and accounts from X, brought into the workspace so an agent can search what was said, track who said it, and monitor the accounts that matter to a thesis.

    What is captured
    Posts, replies, and account details for the accounts and searches you choose to follow.
    Refresh
    Continuous for followed accounts.
    Limits
    Coverage follows X’s access terms and the accounts you select; it is not a full-firehose archive.
    Use it for
    • “What has this CEO posted about capacity in the last month?”
    • “Alert me when any of these accounts mentions a competitor.”
    Talk to sales about X

  • MCP for Claude and ChatGPT

    Your workspace’s data and monitors, from the assistants you already use.

    Integration

    Village’s MCP server puts a workspace’s files, datasets, and monitors to work inside Claude and ChatGPT, so research continues in whichever conversation you are already in.

    What it does
    Lets Claude and ChatGPT read workspace files and data, run the agent, and check monitors on your behalf.
    Setup
    Add Village’s MCP endpoint in Claude or ChatGPT and sign in with your Village account; no data leaves your workspace except what the assistant asks for.
    Use it for
    • “Ask Claude what changed in your monitors overnight.”
    • “Have ChatGPT pull a chart from your workspace into a memo.”

  • Email

    Start research from your inbox and get digests and alerts back.

    Integration

    Every workspace has an address. Email it a question and the agent replies in the thread; monitors send daily digests and alerts the same way.

    What it does
    Inbound questions and follow-ups, outbound digests, alerts, and scheduled reports.
    Setup
    Save the workspace address; replies come from it, so the thread stays in your inbox.
    Use it for
    • “Forward a filing and ask for the three things that changed.”
    • “Get the overnight digest before the open.”

  • Your own data services

    Connect the APIs your firm licenses, or ones you operate, with a key.

    Integration

    Add API keys for the data services you already pay for, and agents use them in research and recurring monitors without asking for the key again.

    What it does
    Any HTTP API with a key: market data, alternative data vendors, internal services.
    Setup
    Keys are submitted through a form that keeps them out of the chat transcript and stored on your workspace’s own machine.
    Use it for
    • “Join your vendor’s foot-traffic feed to the web crawl for the same stores.”
    • “Monitor an internal API and alert on a threshold.”