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.
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.”
Watch it work a real case
Sourcebase scanning a collection of federal court documents for reporting angles, showing every search it runs along the way.
Why not a general chatbot?
A typical chatbot's answer sounds plausible and confident. Plausible isn’t the standard when the work is reporting.
Even when it links to sources, you’re re-reading whole articles to check a single claim.
One click opens the exact page, paragraph, or timestamp behind every answer.
A summary of the document — or, in tools like NotebookLM, a messy extract of its text.
The real, original document, in full context. You read what Sourcebase reads.
You invent your own prompts and repeat yourself every time you start a new thread.
Tools already built for a reporter’s workflow, on collections tested past 20,000 files.
The tools inside Sourcebase
Two ways to work the same sources, from a quick cited answer to a finished draft, plus the tools to build the collection they run on.
Research
Ask a question to a collection and get an answer cited to the exact page, paragraph, or timestamp.
See ResearchFoundry
A guided pipeline that turns your sources into a fully cited first draft.
See FoundryBuild 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, plus all 34,000+ of his Truth Social posts, with timestamped citations. Updated daily.
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.
Research 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
- Turn on web search to check the open web
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
- Share structured-data citations or export them as CSV
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.
Built for the way journalists work
Reporters don’t have time to stitch together a dozen AI tools for journalism. Foundry is one end-to-end workflow that takes you from an idea to a finished, published story, with CMS integration and a dedicated agent at every step.
Choose your sources
Foundry only writes from sources you choose. Bring your own interviews, notes, recordings, and documents, and mix them with our curated public collections. From there, Foundry’s suite of purpose-built tools does the heavy lifting at every step.
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.
Choose your assisted mode
Foundry assists the way you work. Choose how closely you want to stay involved, and change it from one story to the next.
You review the work at every step. Foundry checks in before it moves from one stage to the next, so nothing advances without your say.
Foundry runs the pipeline and checks in at key checkpoints. You approve the direction at each one, and it handles the work in between.
Set how much effort Foundry should spend on the story, then start. When something needs human judgment, Foundry escalates to a journalist.
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.
Custom draft
A first draft in the voice you chose, with every claim cited to its source. Ready for you to edit and publish.
Let it run, then take it away
A full run, all the way to a finished draft, can take an hour or more. You don’t have to sit and watch it work, and everything you take away links back to where it came from.
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, statement, and all 34,000+ Truth Social posts with timestamped citations. Updated daily.

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 identifiable source material, with a human in charge at every step.
What AI is good at
Searching and comparing far more material than any person could read unaided, and turning that research into useful work.
Where it fails
It can miss important records, misread context, repeat the errors in its sources and reach conclusions the evidence does not support. For work that depends on getting it right, that is a liability.
What we built
A system that captures the first without asking anyone to take its assertions on faith. Outputs connect to identifiable material, and that material stays open for inspection.
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.
“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.”
A source is not the same thing as the truth.
A citation establishes where information came from. It does not establish that the information is correct.
Sources can be wrong, incomplete, outdated, partisan or disputed. A complaint contains allegations. A witness can be mistaken. An official statement may present one side. Even authoritative databases carry bad entries.
So we separate two jobs: representing a source accurately, and deciding whether what it says is true. Sourcebase is built to do the first well and to be honest that it cannot do the second.
Credibility, corroboration and significance stay with the person doing the work. Traceability makes verification faster. It does not make verification unnecessary.
How the system is built
Six principles we design and test against.
Evidence before assertion
Answers and drafts are grounded in identifiable material rather than a model's general memory. Citations lead to the passage, page, record or timestamp behind a claim. When adequate support isn't there, the system is built to say so rather than invent it.
Curation is an editorial act
What a system can find is bounded by what it was given to search. For every Sourcebase collection you can see what it holds, the period it covers, how it was assembled and where the known gaps are. A well-supported answer can still be incomplete.
Conflict is preserved, not resolved
When significant sources disagree, the system surfaces the disagreement instead of quietly adopting the version that reads cleaner. Qualifications in the evidence are kept. Analysis is presented as analysis, not as another sourced fact.
Distinctions that matter are held
An allegation does not become fact because it appears in an official document. A prediction does not become an outcome. Where the evidence permits several readings, the uncertainty stays visible rather than getting written away.
Checks you can inspect
Source grounding, citation verification, review by separate agents, contradiction detection and preserved workflow histories. These reduce risk rather than remove it, which is why every output exposes the evidence it rests on.
Judgment stays human
Agents can run parts of a workflow on their own. Autonomy in performing a task is not authority over the decision. Story selection, fairness, characterization of disputed facts and the call to publish remain yours.
For every Foundry output, we give the publisher a record of how that output was produced, so disclosure decisions are theirs to make with the facts in hand.
Get in touch
Questions, press, enterprise, or a collection you think we should build.
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 research turns (lifetime)
- 20MB uploads
- 1 Foundry story
- All Sourcebase collections
- 1,000 research turns / 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.