Discover the story in the sources.
Sourcebase searches troves of millions of documents and transcripts no team could read in a lifetime , answers any question with a citation down to the exact page, paragraph, or timestamp , reads documents, audio, video, and structured data together in one collection , and turns your sources into a fully cited first draft with Foundry .
Click any citation to learn more.
Ask a whole collection your question. Every answer links to the exact page, paragraph, or timestamp, so you can read the source yourself.
Used by newsrooms including
Latest updates
New and updated collections as they go live.
Built for the work of reporting
A two-minute deadline check and a six-month investigation run on the same source base.
Newsroom investigations
Dig through large collections for the details others miss. Track findings across every document with exact citations.
Daily reporting
Ask a quick question on deadline and get a cited answer in seconds, sourced from the material you trust.
Fact-checking and verification
Trace any claim back to the document, page, or timestamp behind it, and confirm what the source actually says.
Research and backgrounding
Build the full picture on a person, place, or topic from everything in the collection before you write.
“I’ve also been using this program called Sourcebase.ai. You could say, look, I want to know everything about this prison guard, for example, and they’ll find everything in a way that I might not have been able to find it.”
The tools inside Sourcebase
Three ways to work the same sources, from a quick cited answer to a finished draft.
Chat
Ask a question to a collection and get an answer cited to the exact page, paragraph, or timestamp.
See ChatDeep Research
Hybrid search that surfaces details buried across thousands of documents.
See Deep ResearchBuild and manage
Bring your own archive of text, audio, and data into one or many searchable collections.
See Build and manageFrom sources to a first draft
Foundry runs a guided pipeline over your sources. Stop at any step and take what it has produced, or let it run all the way through.
Not just documents
Spreadsheets, documents, and the open web sit in one collection. A single question searches across all of them.
Federal spending data
Six million rows across 300 columns of raw U.S. Treasury spending, queried alongside the reporting that explains it.
Match data and coverage
More than 100,000 rows of World Cup results sitting beside 17,000 articles, cross-referenced in one query.
Spreadsheets and filings
125 spreadsheets and 1,300 immigration reports, analyzed together into answers you can cite.
Collections in action
Our expertly curated public troves that are ready to search for free.
The Epstein Files
Over 3.5 million pages of court documents and emails, spanning the late 1990s through 2024, every answer cited to the page.
Ask Trump
Query transcripts from every speech and statement since 2007 with timestamp citations.
Put your sources to work
Open the console to search a public collection, or bring your own documents and start reporting.
Tools built for discovery
Sourcebase reads through collections too large to comb by hand. You point it at the question, check what it finds, and bring the editorial judgment.
Chat in plain language
Journalists and readers ask questions and get answers grounded in original sources, with citations that link to the exact page, paragraph, or timestamp.
Follow up, dig deeper, ask for clarification. Sourcebase keeps context across the conversation so you can explore a document set thoroughly.
- Answers always grounded in original sources
- Citations link directly to the source material
- Fast, Thinking, and Pro modes for any depth
Find the details that matter
Surface newsworthy information in any large trove of documents. Hybrid search combines semantic and keyword matching, with freshness ranking and query rewrite.
Match against individual passages with precision, then summarize entire collections of effectively unlimited size.
- Hybrid search across semantic and keyword
- Passage-level matching for precise citations
- Summarize collections at any scale
- Query structured datasets and tables, not just text
Build and manage your own collection
Our architecture scales on demand, holding video, audio, text, and images in one collection with full context. Tested past 20,000 files.
Curate your own collections, or have our team build custom ones for your organization. Enterprise ready with SSO, security, and governance.
- One collection for audio and text
- White-glove collection curation available
- Enterprise SSO, security, and governance
Foundry builds the story
When you are ready to go further, Foundry takes your sources from a story idea to a fully cited first draft.
Build a story with Foundry
Foundry works your sources into story ideas, a research guide, and a finished first draft, and you decide how far it goes. Here is the whole flow, step by step.
Choose your sources
Foundry only writes from sources you choose. Combine our public collections, your own interviews, notes, and recordings, and any documents you add just for this story.
Your source base
Use one, two, or all threePublic collections
Our curated public collections, ready to search on day one.
Your interviews, notes, and recordings
The original material you bring to the story.
Documents for this story
Files you add for now. Temporary and private, gone when you finish.
Whatever you include works together as one fully cited set of sources.
Web search runs throughout. Confirm a fact on the open web at any point while you write.
Start the story
Choose how much effort Foundry should spend on the story, then start.
Stop wherever you want
Foundry moves through a pipeline, but you are never locked in. Take the output at any point and stop, or keep going. Each step builds on the one before it.
Story ideas
A clear angle with proposed structure, voice, and target length. Take it and write the piece yourself, or keep going.
Research guide
A research notebook of sourced facts and quotes, each citing the exact page, paragraph, or timestamp.
1:12:14:1Custom draft
A first draft in the voice you chose, with every claim cited to its source. Ready for you to edit and publish.
3:2Let it run, then pick it up
A full run, all the way to a first draft, can take an hour or more. You do not have to sit and watch it work.
Leave and come back whenever you like. Foundry keeps working in the background, and emails you the moment your story is ready.
Built to stay accurate
Every stage is checked and reversible, and the whole trail is yours to inspect. You stay in control from the first plan to the final draft.
- Every citation is verified against its source.
- Every action and output is checked by at least one other AI agent.
- Escalates to a journalist whenever judgment is needed.
- Full audit trail, with every version and edit preserved.
- Customizable to your organization’s workflow.
Start building with Foundry
Open the console and turn your sources into a fully cited first draft. Stop at the idea, the research, or the draft — it is always your call, and every claim links back to where it came from.
Our curated collections
Expertly curated public collections for reporters and researchers. Connect one and start working immediately, or build your own.
Featured collections
The Epstein Files
Over 1.3 million documents, emails, and filings, with every answer cited to the exact page.
Ask Trump
Query every speech and statement with timestamp citations.
Facebook Whistleblower Files
Explore internal Meta research documents and disclosures.
January 6th Investigation
The complete House Select Committee findings, fully searchable.
Browse by subject
Public collections grouped by subject, with new ones added regularly. Open any subject in the console for the full, current list.
50+ public collections·10M+ pages and transcripts·30+ datasets and spreadsheets·new ones added every week
U.S. Code, The Epstein Files, JFK Assassination Files, and more.
Trump v. United States, Loper Bright v. Raimondo, United States v. Skrmetti, and more.
Ask Trump, January 6th Investigation, Project 2025, and more.
Big Tech Antitrust, Facebook Whistleblower Files, Meta's Child Safety Research, and more.
Artificial Food Dyes, Fluoride in Drinking Water, “Forever Chemicals” Research, and more.
Upload your own archive of documents, audio, and data, or have our team curate a private collection for you.
Start a collectionSource-based and journalist led.
A team of media and technology veterans rebuilding how information is sourced, analyzed, and published.
Every output traces back to verified source material, with a human in charge at every step.
AI is going to reshape how information gets made and moved. Most tools today approximate knowledge and blur their sources together; some present fiction as fact. For anyone whose work depends on getting it right, that is not an inconvenience. It is a liability.
We rebuilt the workflow around that problem, so a human stays in charge at every step, even when the system is running on its own.
We design for the AI capabilities of the next few years, and the system can be adopted incrementally as practice evolves. Sourcebase ingests and analyzes content at scale, source by source.
The future of media will be built on its sources, with people still making the calls. We are building it.
Media and technology veterans
Ron Suskind
Pulitzer winner, award-winning author & film producer, 5 tech patents.
John Nguyen
Co-founded Vlingo, acquired by Samsung.
Winston Chen
Founder & CEO of Voice Dream, Apple Design Award winner.
Michael Caruso
Former CEO and Editor of Smithsonian and The New Republic.
Glenn Kessler
Editor and chief writer of The Washington Post Fact Checker.
What's new
New and updated collections as they go live.
Plans that scale with the work
Start free to prove the value on public collections. Step up to Pro for serious research and Foundry, or talk to us about a private deployment for your whole organization.
- Select public collections
- 40 chat turns (lifetime)
- 40 searches (lifetime)
- 20MB uploads
- 1 Foundry story
- All Sourcebase collections
- 1,000 chat turns / month
- 1,000 searches / month
- 1GB uploads / month
- 5 Foundry stories / month
- Full platform access
- Custom knowledge bases
- Private data ingestion
- White-label options
- Dedicated support & SLA
Bring Sourcebase to your newsroom
Private collections, your own archive at any scale, and security built for organizations. Tell us what you need.