Investigative journalism is hard, expensive, time-consuming, and often dangerous. I’ve been sued, jailed in Cuba for spying, and even kidnapped over my 40-year career.

But AI is turning the tables and putting new powers in my hands. I’d go so far as to say it’s democratising investigative journalism by giving those powers to anyone.

It’s a big claim, so let me break it down in a literal field report and reveal how I’m doing the accountability reporting of an entire newsroom with a laptop and a $30-a-month subscription. AI has been crucial in how I was able to build a 19,000-strong newsletter audience in 99 countries, which led to me being invited to address the UN and advise multiple governments… in less than three years.

Let’s begin by busting a myth. This isn’t getting the AI to write 1,700 versions of the same article and blasting it across the socials. Nope, this is the opposite. Using the AI to do the grunt work, freeing me up to do the rest.

Used the right way, AI shifts the asymmetry in publishers’ favour. For decades, Big Tech has sent armies of lawyers, comms teams, and lobbyists to control the narrative. Journalists have been left to fight with notebooks and deadline pressure. The information gap was a moat, and tech knew it.

But now, it’s draining. A reporter with the right prompts can now process documents at a speed that used to require billion-dollar resources. Journalists can now do the digging they were trained for, and use the tech to turn it into hard-hitting reporting.

Now a single journalist can hold Google or Meta, Iran or Russia, history or political doublespeak to account—and still have time for lunch.

Finding the needle

I have sources like journalists always have, but many of mine are no longer human. I have alerts set up in search, and notifications on court papers and SEC filings. My tipoffs come in as a steady stream 24 hours a day. Many are nothing, but then one is a trigger. It happened the other week.

The judge in charge of breaking Google’s search monopoly ruled that a technical committee must be established to do the job. Everyone wants to know who they are.

An alert popped up on my phone from an obscure automated court reporting AI that the three had been named. The link gave me the court papers. I was off.

I dropped the committee members a line on LinkedIn, used AI to research their careers and found years-old articles that hinted at their personalities. Within an hour, I profiled them and broke the story. Then I sat down to write it. Boom. Job done.

An antitrust lawyer whose name had been linked with the role rang me from New York saying he’d scoured the court papers and couldn’t find the names. They were buried, I told him. Deep. Even with all his resources he couldn’t find it with his team. Now we’re connected too.

Financial forensics

Apples and pears. That’s journalists and accountants. Journos do words and geeks do maths. Only I love both, because you need to follow the money to find the truth.

Every quarter, the tech firms report their earnings to the US Securities and Exchange Commission. They are interminable—dull and data-laden, but full of gold. Best of all, the tech titans who love nothing more than privacy have to put these numbers out in the open to satisfy their obligations to shareholders.

It’s a goddam turkey shoot. I have uploaded years of financial filings, shareholder updates, Wall Street earnings calls into my own small language model. I’ve trained it on my historic reporting, so it knows what I am looking for. For example, is the 90.5%* of advertising Google sends to its own search and YouTube rising or falling? Spoiler: It’s always rising.

That’s why the open web is in danger of collapsing. It’s why publishers have no money to fund newsrooms. It’s also why experienced single operators like me can strike.

Apple’s numbers told me it’s reliant on China amid a tariff war. Meta’s told me 97.6% of its income relies on ads. Snap showed it relies on selling ads to the youngest teens.

These data points that justify headlines are often buried in footnotes, YOY comparisons that used to take weeks and geeks to reveal—but not now.

The fact-checking machine

AI’s a brilliant sub-editor after you’ve taught it your style.

My SLM—I call it RoboRicky—then reads the draft and alerts me if I’ve forgotten a relevant fact in a previous article. It even suggests charts and images. My newsletter contains more than three million words of investigative journalism now, but there’s more than 10 million words of source material in RoboRicky.

It checks every word against the source material to confirm it’s accurate and flags anything that it thinks is wrong.

I’ve also had fun using Google’s Gemini to punch holes in its CEO’s fibs, and had OpenAI run an analysis on whether its deals to buy content were fair. (They weren’t.)

RoboRicky + my brain + my instincts + a superhumanly unwise amount of coffee now power my one-man newsroom. No team. No budget. Me, a laptop, and my killer AI pal.

*Footnote: RoboRicky corrected an error. I’d said Google sent 89% of its ads to search and YouTube. The actual number from the Q4 SEC filing last month (and not reported but calculable by doing the complex maths) was even more, 90.5%.

The post AI is making the one-man newsroom a reality appeared first on The Media Copilot.

Google Pinpoint and DocumentCloud both offer free document analysis for journalists, but they solve different newsroom problems. Investigative newsrooms drowning in FOIA dumps face a tool selection problem. Traditional filing methods collapse under document volume. Spreadsheet indexes don’t scale. Manual review takes weeks. Small outlets need organizational capacity they typically can’t afford.

Two free platforms address this gap: Google’s Pinpoint and DocumentCloud from the MuckRock Foundation. Both understand newsrooms need more than generic document storage—they need search capabilities, collaboration features and workflows designed for journalism rather than general business use.

Pinpoint, developed through Google’s News Initiative, emphasizes machine learning-powered search across large document collections. DocumentCloud, built explicitly for journalism by MuckRock, prioritizes annotation, public sharing and newsroom-specific collaboration tools. Both offer free access. Both support FOIA-heavy investigations.

The question for small newsrooms becomes: Do you need maximum search power or maximum annotation flexibility?

Google Pinpoint advantages: Machine learning search and entity extraction

Pinpoint’s architecture leverages Google’s machine learning infrastructure. The platform’s entity extraction automatically identifies names, organizations, locations and dates across uploaded documents. Google’s knowledge graph enables sophisticated searches—searching “JFK” surfaces references to John F. Kennedy, not just exact letter matches.

For Blue Ridge Public Radio’s investigation tracking developer fraud across 125 Los Angeles court cases plus North Carolina government records, this search capability proved essential. Documents arrived sporadically across months. “We’re sitting in that line for months,” News Director Laura Lee notes about public records request timelines. When new materials arrived, reporters needed instant connections to earlier findings.

“Having it all in that one space and having it searchable… that’s the big leap that Pinpoint makes,” Lee explains. Following obscure company names or minor dates through thousands of pages would have required hours manually. Pinpoint returned results in seconds.

The optical character recognition handles scanned documents and images that would otherwise remain locked in non-searchable formats. Court filings, government memos, handwritten notes—materials arriving as image files become fully searchable text. This matters particularly for historical documents or materials from agencies providing only scanned PDFs.

Pinpoint’s unlimited user access means collaboration doesn’t increase costs. When BPR’s investigation expanded statewide, the team shared their collection with partner newsrooms WFDD and CityView. Multiple outlets coordinated investigation without per-seat licensing constraints.

The platform’s capacity—100,000 documents per collection with unlimited collections—accommodates investigations at any scale. BPR’s award-winning series used a fraction of this capacity, but disaster recovery reporting for Hurricane Helene will likely push limits as the team tracks government response across multiple agencies.

DocumentCloud advantages: Annotation tools and public document sharing

DocumentCloud differentiates through annotation tools designed specifically for journalism workflows. The platform enables highlighting, commenting and note-taking directly on documents—functionality journalists need when marking up source materials for editorial review or fact-checking.

Public sharing capabilities address a use case Pinpoint doesn’t prioritize: making source documents available to readers alongside published stories. DocumentCloud lets newsrooms embed documents directly in articles, allowing audiences to review primary sources. This transparency builds trust and enables other journalists to build on published work.

Self-hosted deployment options provide control for newsrooms with strict data security requirements. Organizations handling sensitive materials—confidential sources, pre-publication investigations, embargoed reports—can run DocumentCloud on their own servers rather than cloud hosting. This architectural choice addresses concerns that make cloud platforms untenable for some investigative work.

The newsroom-specific collaboration model reflects how journalists actually work. Features designed explicitly for editorial workflows—annotation, fact-checking markers, collaborative note-taking—provide structure general document platforms lack. For newsrooms prioritizing annotation over search speed, this specialization delivers value.

DocumentCloud’s development community—funded by MuckRock Foundation and built specifically for journalism—means feature requests reflect newsroom needs directly rather than competing priorities within a tech company’s broader product portfolio.

Which tool for your newsroom: Search speed vs annotation flexibility

Documentation suggests different use case priorities. Pinpoint appears better suited for investigations where search speed and entity extraction provide the primary value—tracking names across jurisdictions, following complex corporate structures, managing document volumes too large for manual review.

Blue Ridge Public Radio’s experience illustrates this profile: thousands of court records arriving sporadically, requiring instant search across months of accumulated materials, needing collaborative access for partner newsrooms. The investigation succeeded because reporters could surface connections buried in document volume.

DocumentCloud’s annotation focus suggests suitability for newsrooms prioritizing markup and public sharing. Investigations requiring detailed document annotation for editorial review, fact-checking workflows involving multiple editors or public transparency through embedded source materials might find DocumentCloud’s feature set more aligned with their process.

Newsrooms should evaluate their primary bottleneck. If search and organization constrain investigations, Pinpoint’s machine learning provides high-impact leverage. If annotation and public sharing matter most, DocumentCloud’s journalism-specific features deliver specialized value.

Technical differences: Cloud deployment, search capabilities, and security options

The fundamental architectural difference involves deployment and hosting. Pinpoint operates exclusively as cloud service through Google’s infrastructure. DocumentCloud offers both cloud hosting and self-hosted options for organizations requiring complete data control.

This deployment distinction determines security posture. Pinpoint requires comfort with Google-level security—essentially the same standards as Gmail or Google Docs. For most newsrooms handling public records, government documents or materials they’d send via email anyway, this proves sufficient. DocumentCloud’s self-hosted option addresses stricter requirements.

Search capabilities differ in implementation. Pinpoint leverages Google’s knowledge graph and machine learning for entity extraction and semantic search. DocumentCloud provides document search but documentation doesn’t specify comparable semantic capabilities or automated entity extraction at Pinpoint’s scale.

Annotation and markup tools represent DocumentCloud’s differentiation. While both platforms support notes and organization, DocumentCloud’s annotation features designed explicitly for journalism workflows—collaborative markup, fact-checking tools, public embedding—exceed Pinpoint’s capabilities in this dimension.

Frequently Asked Questions

The post Google Pinpoint vs. DocumentCloud: Which is right for your newsroom? appeared first on The Media Copilot.

Document-heavy investigations generate two competing pressures for small newsrooms. FOIA dumps, court records and government emails arrive in volumes that overwhelm traditional organization methods. But those same materials often contain sensitive information—confidential source identities, unpublished findings, materials that could compromise investigations if exposed.

Google’s Pinpoint addresses the organizational challenge through machine learning that makes thousands of documents instantly searchable. Blue Ridge Public Radio used the platform to win an Edward R. Murrow Award investigating developer fraud. But the tool operates as cloud service hosted by Google—raising questions about data security for investigations involving materials newsrooms can’t risk compromising.

What security controls protect uploaded documents? What risks remain even with Google’s infrastructure? What due diligence should newsrooms conduct before processing investigation materials through cloud-based analysis platforms?

Security risks when using Google Pinpoint for investigations

The primary risk with cloud-based document analysis involves unintended data exposure—whether through inadequate access controls, service provider security breaches or government data requests. Investigative newsrooms routinely handle material that cannot be compromised: confidential source identities, unpublished investigation details, embargoed reports coordinated across outlets.

Google states that data uploaded to Pinpoint isn’t used as training data and maintains security standards equivalent to Gmail or Google Docs. This assurance addresses one exposure vector—submitted materials won’t surface in other users’ results the way general-purpose AI tools might leak training data. However, the practical security threshold becomes: If you’re comfortable sending a document via email, it’s appropriate for Pinpoint.

This threshold matters significantly for determining use case boundaries. For BPR’s investigation, security considerations proved straightforward. The documents—public records, court filings, government emails—were already public domain or would become so through reporting. No confidential sources required protection. No unpublished materials risked compromising the investigation if exposed.

But newsrooms handling different material types face different risk calculations. Investigations involving confidential sources, documents obtained through whistleblowers or materials that could endanger sources if exposed require security beyond email-level protections. Cloud hosting—regardless of provider—introduces exposure vectors self-hosted solutions avoid.

Documentation doesn’t specify data retention periods beyond Google’s general policies. Newsrooms with strict document destruction requirements—mandated timelines for purging source materials, regulatory obligations around data retention—need clarity on exactly how long uploaded files persist and under what circumstances Google purges them.

How Google Pinpoint protects uploaded documents

Pinpoint operates within Google’s broader security infrastructure—the same systems protecting Gmail, Google Docs and Google Drive. This infrastructure employs industry-standard controls: encryption in transit protects documents during upload, encryption at rest protects stored files and access controls restrict viewing to authorized account holders.

The platform’s access model supports collaborative investigations through sharing controls. Account holders can grant specific users access to document collections without exposing materials publicly. This enables the multi-newsroom coordination BPR used for statewide fraud investigation—three outlets sharing document collections without duplicating public records requests or manual organization.

Google’s infrastructure undergoes third-party security audits and maintains compliance certifications for enterprise services. While Pinpoint-specific certifications aren’t documented, the underlying Google Cloud platform meets standards many enterprise newsrooms require for vendor relationships.

The stated policy against using uploaded documents as training data addresses one AI-specific risk. Unlike general-purpose language models that might incorporate submitted materials into training datasets, Pinpoint commits to keeping investigation documents separate from model training—preventing the exposure vector where confidential material submitted for analysis might eventually surface in unexpected contexts.

However, these controls operate within cloud hosting constraints. Google’s security protects against unauthorized access by external actors but doesn’t eliminate exposure to Google itself or government data requests. Newsrooms requiring absolute isolation—materials that never touch third-party servers—need self-hosted alternatives regardless of cloud provider security measures.

Security checklist for Pinpoint users

Before uploading investigation documents to Pinpoint, verify the following:

• Are all documents already public or will become public through your reporting?
• Do materials contain any confidential source identities or information that could identify protected sources?
• Would email-level security (Gmail/Google Docs equivalent) meet your organization’s policy for these materials?
• Do you handle documents subject to specific data residency requirements (geographic storage restrictions)?
• Are materials embargoed or coordinated with other outlets in ways that require absolute access control?
• Does your organization maintain formal document destruction policies requiring guaranteed purge timelines?
• Would exposure of these materials through cloud provider breach or government request endanger sources or compromise investigations?

Organizations answering “yes” to confidential source questions, data residency requirements or embargoed material concerns should evaluate self-hosted alternatives like DocumentCloud or Datashare that keep sensitive documents under complete organizational control.

Publications handling particularly sensitive investigations—organized crime coverage, national security reporting, human rights documentation in hostile jurisdictions—should consult information security professionals before processing any materials through cloud platforms regardless of provider security measures.

Newsrooms comfortable with cloud hosting for appropriate material types can apply for Pinpoint access at journaliststudio.google.com/pinpoint. The platform works best for public records, court filings and government documents where security requirements align with email-level protections.

Frequently Asked Questions

The post What are Google Pinpoint’s security risks for investigative newsrooms? appeared first on The Media Copilot.

Laura Lee sent a reporter to check on an empty Ramada Inn expecting a quick beat story. Twenty-two months after Asheville approved a motel conversion for homeless housing, all 113 rooms sat vacant. Early reporting raised more questions than answers.

When Blue Ridge Public Radio discovered the California developer facing 125 similar cases in Los Angeles courts, documents flooded in: court records, government emails, financial statements. A seven-person newsroom suddenly needed organizational capacity they didn’t have. Traditional methods—filing folders, spreadsheet indexes—would have crumbled.

Google’s free Pinpoint platform became BPR’s backbone, transforming document chaos into searchable archives. The resulting investigation won an Edward R. Murrow Award and prevented fraud schemes in other cities. This quick reference covers how they managed the scale.

The gist

BPR’s systematic document organization turned overwhelming volume into award-winning journalism:

• Platform is free for verified journalists with unlimited document capacity
• Automated entity extraction surfaced connections across thousands of pages instantly
• Collaborative features enabled statewide investigation preventing additional fraud

How they did it

BPR’s implementation prioritized searchability and institutional memory from the start:

• Created dedicated collection: Established single Pinpoint workspace for all investigation materials, ensuring centralized access as documents arrived sporadically across months of public records requests.
• Uploaded systematically: Added court filings, government emails and financial records as received, using optical character recognition to make scanned documents fully searchable.
• Leveraged entity extraction: Let automated tagging identify names, organizations, locations and dates across the growing archive without manual indexing.
• Shared with collaborators: When investigation expanded statewide, granted partner newsrooms access to shared collection, enabling coordination without duplicating document requests.
• Maintained searchability: Used platform as institutional memory—reporters could instantly locate details from documents reviewed months earlier when new materials revealed their significance.

Key numbers

• Cost: Free for verified journalists and academics through Google News Initiative
• Document capacity: Up to 100,000 documents per collection with unlimited collections
• Court cases tracked: Approximately 125 Los Angeles cases involving same developer
• Newsrooms collaborating: Three outlets (BPR, WFDD, CityView) coordinating statewide investigation
• Award: Edward R. Murrow Award for investigative reporting, October 2023
• Fraud prevented: Similar schemes in Winston-Salem, Fayetteville stopped after collaborative series

What to watch for

Implementation considerations and limitations BPR encountered:

• Cloud-based hosting: Google hosts all documents, requiring comfort with cloud storage—unsuitable for newsrooms handling materials too sensitive for email-level security.
• Manual analysis still required: Pinpoint organizes and searches but doesn’t interpret—reporters must still read documents and draw conclusions from patterns surfaced.
• Beta AI features unreliable: Generative AI capabilities remain experimental with unclear accuracy—better served using established tools like NotebookLM for AI-assisted analysis.

Small newsrooms facing document-heavy investigations can apply for Pinpoint access at journaliststudio.google.com/pinpoint. Verification typically granted within days for working journalists and academics.

Frequently Asked Questions

The post How a Small Newsroom Used Google Pinpoint for Investigative Journalism appeared first on The Media Copilot.

Investigative journalism drowns in documents. FOIA dumps arrive with thousands of pages. Court databases yield hundreds of cases. Government email archives span years of correspondence. Small newsrooms face an organizational nightmare: How to find the needle-in-haystack detail that breaks a story open when you’re drowning in PDF files?

Traditional methods—filing folders, spreadsheet indexes, manual notes—collapse under volume. Larger news organizations deploy dedicated data teams with custom tools. But seven-person newsrooms like Blue Ridge Public Radio lack those resources. When Laura Lee’s team uncovered 125 Los Angeles court cases involving the same developer defrauding Asheville, they needed organizational capacity they didn’t have.

Google’s Pinpoint addresses this resource gap through three elements: zero-cost access removing budget barriers, machine learning that transforms chaos into searchable archives, and collaborative features enabling multi-newsroom investigations without duplicating work.

1. Free access removes the primary adoption barrier

Investigative tools typically require subscriptions small newsrooms can’t justify. Specialized document analysis platforms cost thousands annually. Even general productivity software adds up when multiplied across team members. Budget constraints force cash-strapped outlets to choose between tools and reporting capacity.

Pinpoint eliminates this barrier entirely. Google offers the platform free to verified journalists and academics through its News Initiative. Each account includes up to 100,000 documents per collection with unlimited collections, optical character recognition for scanned materials, audio transcription and collaborative sharing with unlimited users.

This pricing structure targets precisely the newsrooms that need document analysis most—small outlets tackling investigations beyond their normal capacity. Blue Ridge Public Radio’s Edward R. Murrow Award-winning series on Asheville’s failed motel conversion required analyzing thousands of court records, government emails and financial statements. The investigation would have been impossible without organizational tools, but impossible to budget for with paid alternatives.

The free tier doesn’t compromise capabilities. Pinpoint’s machine learning matches paid document analysis platforms in core functionality: entity extraction, pattern recognition, collaborative annotation. Small newsrooms get enterprise-grade capabilities without enterprise pricing.

2. Machine learning transforms document chaos into searchable archives

Manual document review doesn’t scale. Reading thousands of pages sequentially takes weeks. Manually indexing every relevant name, date and organization proves impractical. Following connections across jurisdictions requires hours tracing paper trails. Small newsrooms simply don’t have the time.

Pinpoint’s machine learning addresses this through automated entity extraction. The platform identifies names, organizations, locations and dates across uploaded documents automatically. Google’s knowledge graph enables sophisticated searches—searching “JFK” surfaces references to John F. Kennedy, not just the exact letters typed.

For BPR’s investigation, this capability proved essential. Documents arrived sporadically across months as public records requests yielded responses. “We’re sitting in that line for months,” Lee notes about North Carolina’s lack of response deadlines. When new materials arrived, reporters needed to connect them to earlier findings instantly.

“Having it all in that one space and having it searchable… that’s the big leap that Pinpoint makes,” Lee explains. “Especially as you get more and more volume, it’s really like a needle in a haystack. There are times you think, ‘I know this exists because I read it, but it was three days ago, and now I can’t remember which document it’s in.'”

The optical character recognition handles scanned documents and images that would otherwise remain locked in non-searchable formats. Court filings, government memos, handwritten notes—materials that arrive as image files become fully searchable text. This matters particularly for historical documents or materials from agencies that don’t provide text-based files.

3. Collaborative features enable multi-newsroom investigations

Complex investigations often span jurisdictions. Developers defrauding one city may target others. Environmental violations cross state lines. Corporate malfeasance involves multiple subsidiaries. Small newsrooms covering limited geographies can’t track these patterns alone.

BPR’s investigation illustrates this challenge. As reporting progressed, the team discovered Shangri-La Industries pitching similar motel conversion projects in Winston-Salem and Fayetteville—using Asheville as false credibility. “‘Oh, they’re doing this in Winston-Salem and Fayetteville, too,'” Lee recalls realizing.

This discovery prompted collaboration with WFDD in the Piedmont Triad and CityView in Fayetteville. Three newsrooms began tracking the same developer’s activities statewide. Pinpoint’s sharing features enabled this coordination. BPR shared their document collection through the platform’s access controls. Partner newsrooms could search the archive, identify patterns and cross-reference findings without duplicating document requests or manual organization.

The resulting collaborative series, “Sold on a Promise,” prevented additional cities from entering fraudulent agreements. “Most of those have fallen through,” Lee says. Without centralized document access, coordinating three separate newsrooms investigating related schemes across different jurisdictions would have overwhelmed the small teams involved.

Pinpoint’s unlimited user access means newsrooms don’t face per-seat licensing constraints. Adding collaborators doesn’t increase costs. This flexibility matters for investigations that expand scope unexpectedly—exactly what happened when BPR’s local story became statewide.

Who should consider Pinpoint

Document-heavy investigations represent Pinpoint’s ideal use case. Newsrooms handling FOIA dumps, court filings, government email archives or any scenario involving hundreds of pages benefit from automated organization and entity extraction. The platform works particularly well for investigations spanning months where institutional memory becomes crucial—details from documents reviewed weeks earlier suddenly gain significance as new materials arrive.

Small to medium newsrooms lacking dedicated data teams gain the most value. Organizations comfortable with Google Workspace and cloud-based tools will find adoption straightforward. Investigations requiring collaboration across multiple outlets benefit from sharing features that enable coordination without technical complexity.

Newsrooms should evaluate whether document analysis addresses their primary bottleneck. If investigations fail due to organizational challenges rather than reporting capacity, Pinpoint provides high-impact leverage. If constraints involve access rather than analysis, other tools may serve better.

Small newsrooms tackling document-heavy investigations can apply for Pinpoint access at journaliststudio.google.com/pinpoint. The platform requires verification as a journalist or academic, typically granted within days.

Frequently Asked Questions

The post Why small newsrooms are using Google Pinpoint for document-heavy investigations appeared first on The Media Copilot.

Laura Lee wasn’t planning an investigation when she sent reporter Laura Hackett to check on an empty Ramada Inn in Asheville. Twenty-two months after city officials approved a motel conversion project to house homeless residents, all 113 rooms sat vacant. Lee expected a quick beat story about municipal delays.

“I wasn’t thinking of this as an investigative project,” Lee says. “I was thinking of it like a standard story on the beat.”

Blue Ridge Public Radio serves 14 counties and 650,000 people across Western North Carolina with seven reporters plus a news director. As a nonprofit NPR affiliate focused primarily on daily coverage, major investigations strain resources the newsroom can’t easily spare. But early reporting on the Ramada Inn raised questions no daily story could answer. The rushed purchase agreement between Asheville and Shangri-La Industries, a California developer, looked increasingly suspicious.

When Hackett discovered the same developer facing legal troubles in Los Angeles, BPR began searching L.A. County court databases. They uncovered roughly 125 cases—many echoing patterns emerging in Asheville. Documents flooded in: email transcripts from city officials, court records, financial statements tracking shell corporations. Soon the small newsroom was drowning in files without the organizational systems larger news operations take for granted.

Google’s Pinpoint became BPR’s backbone—a free document analysis tool that transformed chaos into searchable archives. The resulting series, “Secret Sauce Expired’: The Ramada Inn Conversion for Asheville’s Unhoused,” won an Edward R. Murrow Award. More importantly, the reporting prevented similar fraud schemes from proceeding in other North Carolina cities.

Discovering Pinpoint while seeking transcription tools

Lee first encountered Pinpoint while searching for radio transcription capabilities. Blue Ridge Public Radio produces audio journalism daily, and transcription tools help reporters quote sources accurately and make broadcast content searchable. Only after experimenting with Pinpoint’s transcription features did Lee realize the platform offered broader document analysis capabilities.

Pinpoint, developed by Google’s News Initiative, uses machine learning and natural language processing to make scanned PDFs, emails, transcripts and other files fully searchable. Users can identify names, organizations, locations and key terms across thousands of pages in seconds. The platform supports bulk uploads, pattern searches, annotation and collaborative sharing.

For BPR’s expanding investigation, these features addressed practical problems immediately. North Carolina’s public records law doesn’t set response deadlines. “We’re sitting in that line for months,” Lee notes. Documents trickled in sporadically—sometimes arriving months after original requests. Traditional filing methods—folders, spreadsheets, manual notes—would have crumbled under the volume and timeline.

“Having it all in that one space and having it searchable… that’s the big leap that Pinpoint makes,” Lee explains. “Especially as you get more and more volume, it’s really like a needle in a haystack. There are times you think, ‘I know this exists because I read it, but it was three days ago, and now I can’t remember which document it’s in.'”

Building a searchable archive as documents accumulated

BPR created a dedicated Pinpoint collection for the investigation, uploading court filings, government emails and financial records as they arrived. The platform’s optical character recognition made scanned documents searchable. Automatic entity extraction identified names, organizations, locations and dates across the growing archive.

This organizational system proved crucial as the investigation stretched across months. When new documents arrived weeks or months after earlier materials, reporters could search the entire collection instantly rather than manually reviewing previous files. Details that seemed insignificant in isolation—obscure company names, minor dates, tangential references—became important when later documents revealed their significance.

The search functionality helped reporters surface connections buried across hundreds of pages. Following a name through court records spanning multiple jurisdictions would have required hours manually. Pinpoint returned results in seconds. “Any investigation is going to yield a lot of paper and not all of it is going to be that helpful,” Lee explains. “But you don’t know that until you go through it.”

During pre-publication legal review, Pinpoint’s archive provided immediate verification. When lawyers or editors asked “How do you know this?” or “Where exactly did that quote come from?”, reporters located original source material instantly. This documentation speed matter for small newsrooms where legal review can bottleneck publication.

Expanding statewide when patterns emerged elsewhere

As BPR’s reporting progressed, team members discovered Shangri-La Industries was pitching similar motel conversion projects in Winston-Salem and Fayetteville—using the Asheville contract as credibility despite making zero actual progress there.

“‘Oh, they’re doing this in Winston-Salem and Fayetteville, too,'” Lee recalls realizing. This discovery prompted collaboration with WFDD in the Piedmont Triad and CityView in Fayetteville. Multiple newsrooms began tracking Shangri-La’s activities across North Carolina.

Pinpoint’s collaborative features enabled this expanded investigation. BPR shared their document collection with partner newsrooms through the platform’s sharing controls. Different reporters could access the archive, search for patterns and cross-reference findings without duplicating work. As scope broadened beyond Asheville, details buried in earlier documents—previously obscure names, minor dates, contractual language—suddenly became significant in the statewide context.

The centralized, searchable archive let reporters surface those connections quickly. Without Pinpoint’s organizational system, coordinating three newsrooms investigating related fraud schemes across different jurisdictions would have overwhelmed the small teams involved.

Publishing findings that prevented additional fraud

In October 2023, BPR published “Secret Sauce’ Expired: The Ramada Inn Conversion for Asheville’s Unhoused”—a three-part series that earned the newsroom an Edward R. Murrow Award. It had immediate impact. Asheville formally cut ties with Shangri-La Industries in January 2024, ending a two-year partnership marked by delays and broken promises.

A local contractor filed suit against Shangri-La for nonpayment. The developer lost the Ramada Inn property to foreclosure. Around the same time, California’s Attorney General filed a $114 million fraud lawsuit against Shangri-La.

The collaborative statewide reporting, published as “Sold on a Promise,” examined how Shangri-La pitched similar deals in other communities using promotional materials showcasing Asheville project renderings—even though no real progress had been made there. “Most of those have fallen through,” Lee says. The reporting helped prevent additional cities from entering similar agreements.

Pinpoint’s role extended beyond organization. The platform became institutional memory for an investigation spanning multiple reporters across months of document collection. New team members could search the archive to understand previous reporting. Complex timelines involving multiple entities remained accessible rather than locked in individual reporters’ notes.

Preparing for Hurricane Helene coverage using lessons learned

BPR has begun investigative coverage of Hurricane Helene’s aftermath. The devastating storm caused billions in damage across Western North Carolina, leaving communities without water or power for weeks. Reporting involves multiple layers of local, state and federal agencies—each generating thousands of emails, contracts and budget records.

Lee thinks Pinpoint can help manage that scale and complexity. Document volumes will likely far exceed even the Ramada Inn investigation. “If you want to be able to tackle a project of this size and scope, you’re going to have to leverage tools,” Lee says. The goal remains freeing time for tasks only journalists can do—”having conversations and being in the community and witnessing things.”

With disaster recovery spanning months or years, having searchable archives will help BPR track whether promises made in crisis actually translate to action. Pinpoint’s organizational capacity addresses the practical challenge small newsrooms face: How to maintain institutional memory when resources barely cover daily reporting, let alone long-term investigations?

The team established their workflow through the Ramada Inn investigation—create collections early, upload documents systematically, use entity extraction to surface connections, collaborate through shared access. These practices will scale to larger investigations because Pinpoint’s architecture supports up to 100,000 documents per collection with unlimited collections per account.

Small newsrooms considering Pinpoint can explore the free platform at journaliststudio.google.com/pinpoint. The tool works best for document-heavy investigations where volume would overwhelm traditional filing systems—exactly the circumstances cash-strapped outlets face when major stories demand investigative depth.

Frequently Asked Questions

The post A 7-person newsroom used a free Google tool to win a Murrow Award and stop a $114 million fraud appeared first on The Media Copilot.