An editorial tool for reading articles and guiding newsrooms in constructive journalism.
ORLA (Optimized Reporting and Language Advisor) reads your article across three constructive journalism pillars (solutions, nuances, and democratic conversation) so you can strengthen it before publication.
What can be done?
Mechanisms, evidence, limitations, realism. Who should act, and does it work?
How complex is the story?
Historical context, causation discipline, affected voices, counter-narratives.
Who is in the conversation?
Named stakeholders, cross-dialogue, civic framing, paths to engagement.
Two tools, one feedback loop
Before filing an article, a journalist pastes it into ORLA. ORLA reads the article across three pillars and returns notes tied to specific passages. The journalist revises based on those notes and publishes.
An editor uploads the newsroom's published articles as a CSV. The batch report shows aggregate scores by section, topic, and time period, making it possible to spot where the team needs to focus.
Individual article feedback and newsroom-level patterns both use the same three criteria, making it possible to connect individual improvements to newsroom-wide trends.
How ORLA reads an article
The criteria come from research into, and practical use of, constructive journalism. The analysis is adapted to the article's genre and grounded in what is on the page.
ORLA reads the article and determines its genre, subject area, and language. The reading is adapted to the genre: a short news article is not held to the same standard as a feature.
Three pillars structure the analysis, each built on sub-questions from constructive journalism research: solutions coverage, nuance and complexity, and democratic conversation framing.
For each sub-question, ORLA first locates a passage or quote in the article, present or absent. What it reports for each pillar follows from those passages, not from a general impression.
A final pass turns those passages into two or three suggestions. Each one names what is missing and where: a note about this article, not a checklist.
From a suggestion to a name to call
Each of ORLA's suggestions comes with a Find sources button. Clicking it runs a search built from that suggestion, the article, and your outlet profile, and returns two or three named people or organisations to contact, each with a line explaining why they were suggested.
Web search
General search in the article's own language, expanded into English for stories with an international angle.
Academic sources
Researchers and studies via OpenAlex, for stories that need an expert or a citation rather than a spokesperson.
Your own archive
A search of your newsroom's own past reports, so a lead can point back to coverage and sources you already reached.
Find sources appears on every suggestion in ORLA, and on every coverage gap the Watchlist below finds. It draws on the newsroom's shared weekly allowance shown next to the button, and is included on paid plans.
Watchlist: how your coverage of a topic adds up
ORLA reads one article at a time. Watchlist looks at many. An editor adds a keyword the newsroom returns to regularly, for example a hospital's waiting times or a housing policy, and the system matches new and existing reports against it automatically, at no cost, showing a live count of matching articles.
Add a keyword to the Watchlist. Suggestions are drawn from articles already in your reports, or type your own.
New and existing reports are matched against the keyword automatically. The match count is free; no analysis runs until you ask for one.
Run a diagnosis. ORLA's three pillars are applied to a sample of the matching articles, and the result is added to that keyword's history rather than replacing the last one.
Follow up. Each diagnosis names a specific gap in the coverage, and Find sources can turn that gap into people to contact.
Watchlist has its own page in the app, open to everyone on the team, and is included on paid plans.
Email your draft, get ORLA's reading back as a reply
Not every draft starts in a browser tab. ORLA also works over email: paste the draft into the email body, or attach it as a Word document, and send it to orla@constructivenewsmirror.com from the address you use to sign in. A reply arrives in a couple of minutes with the same three-pillar reading ORLA gives on the web, written in the article's own language, along with a link back to the full result in the app.
Paste the draft into the email body, or attach it as a .docx file.
Send it to orla@constructivenewsmirror.com from your account's email address.
A reply arrives in a couple of minutes with the reading and a link to the full result in the app.
One draft per email. Plain text or .docx for now; PDF attachments are not read yet.
Three roles for your newsroom
Every workspace has three roles: owner, editor, and journalist. Roles decide who manages the account and who generates batch reports. Everyone, on any role, can use ORLA and Find sources on their own drafts, and can browse the shared watchlist for story ideas. ORLA results are private to the person who ran them, so no one else on the team, not even the owner, can open a colleague's analysis.
Owner
Runs the account. Invites and removes people, sets roles, manages billing, and edits the outlet profile. Can do everything editors and journalists can.
Editor
Generates and deletes batch reports from CSV files, and browses the shared report library alongside the watchlist. Uses ORLA and Find sources on their own drafts.
Journalist
Uses ORLA and Find sources on their own drafts and browses the shared watchlist for ideas. Does not generate batch reports or see the report library, and cannot change account settings.
Paid newsrooms share one weekly allowance for ORLA and Find sources across the whole team, shown as a counter next to each button. The allowance is set per newsroom and resets at the start of each week.
Developed by the Constructive Institute
The Constructive Institute is a Danish non-profit that trains journalists and newsrooms in constructive journalism. It works with media organisations in Scandinavia and internationally.
Constructive News Mirror is a tool developed in connection with that work.
Visit constructiveinstitute.orgMoving ORLA's processing to Europe
Today, the text you paste into ORLA is sent to OpenAI's API in the United States for analysis. We are moving that processing to Azure OpenAI's EU Data Zone, so article text is processed inside the EU instead of crossing to the US.
As part of that move we are applying for zero-retention handling with no human review of submitted text, and the switch also brings Microsoft's Customer Copyright Commitment, which covers content produced through the Azure OpenAI Service. The remaining step is a Data Processing Agreement with Microsoft, currently in progress. Article traffic moves over once it is signed.
This covers both the single-article reading and the batch report pipeline. It does not change what we store ourselves or who inside your workspace can see a result.
Questions about data handlingCreate an account to see how ORLA works. Access is opened newsroom by newsroom while ORLA is closed for maintenance. Write to cle@constructiveinstitute.org and we will set you up.