
Long-form article source balance desk
Transparent coverage gaps without forced equivalence.
- For
- Independent journalists
- Solves
- Drafts rely heavily on a narrow source set.
- Delivers
- Editor-reviewed source coverage report
- Built in
- about 2 weeks of creation time, MVP in 2 days
- Investment
- $12,500 for the MVP, $42,500 for the full product
- Run it
- Inside your business, or as part of your offer to clients
What it does
For independent journalists, turn authorized interview notes and research records into editor-reviewed source coverage report.
- Map source contributions.
- Flag missing perspectives.
- Draft reporting questions.
- Link proposed outputs to original source records.
- Capture reviewer corrections and approval.
- Export a versioned editor-reviewed source coverage report.
What goes in, what comes out
- Authorized interview notes
- Research records
AI drafts, people review. Evidence review and quality assurance workspace.
- Editor-reviewed source coverage report
How it works
The workflow
- InStart with
Authorized interview notes and research records
- 1
The buyer creates a project
- 2
Supplies authorized interview notes and research records
- 3
Confirms scope and access
- OutFinish with
Editor-reviewed source coverage report
AI does the heavy lifting, people stay in charge
AI assists these bounded tasks: map source contributions; flag missing perspectives; draft reporting questions. Use only authorized interview notes and research records and preserve uncertainty in editor-reviewed source coverage report. Keep model suggestions separate from verified facts. Link factual outputs to authorized input evidence and show missing information explicitly. Use deterministic checks for counts, dates, identifiers and arithmetic where applicable. A designated reviewer validates consequential outputs and signs off the delivered result.
What your team sees
Key screens: Brief and sources, Long-form article source balance desk, Review and delivery. Open on a review queue ordered by reviewer-selected priorities. Show each finding beside the original evidence and applicable rule. Provide accept, dismiss and needs-information controls with reasons. A separate report view summarizes confirmed findings and unresolved items, not raw AI flags. Open with brief and sources; move into long-form article source balance desk for the detailed task; finish in review and delivery for review and handoff. Show the source record, uncertainty and approval status beside each proposed output.
Accounts and administration
Versioned review criteria, evidence links, reviewer decisions, disagreement handling, correction assignments, recheck status and exportable review history. Include organization-scoped access, named project owners, review queues, usage limits, export history and retention settings. Never reuse private customer material for other accounts without permission.
Integrations and data access
Author-owned manuscripts, authorized interviews and permitted research sources. Source repositories, task trackers and report exports. Keep findings as review proposals until authorized owners accept the resulting actions. Begin with uploads and exports of authorized interview notes and research records. Any named system or connector is a candidate requiring current access and compatibility checks; no live connection is included by default.
How we build it
We build with our own AI software development factory, so most implementations take days to a few weeks of creation time, not months. You see working software at every step, and exact timing depends on availability.
- 1
Scoping call
Day 1Thirty minutes on your process, your data and how you want to run it: for your own team, or for your clients. You get a fixed scope and price for the MVP.
- 2
MVP
2 daysOne buyer segment, one recurring use case; first modules: map source contributions; flag missing perspectives. Manual review in the loop. Built by our AI software factory.
- 3
Paid pilot
3 daysAccounts, roles, review states, audit trail and the first integration, hardened for two to three paying pilot customers.
- 4
Full product
6 daysSelf-serve onboarding, billing, monitoring and the wider integration set.
- 5
Run and improve
MonthlyWe host, monitor and improve it for a fixed monthly fee, or hand it over to your team. How the retainer works.
Why we start with an MVP
An MVP, or minimum viable product, is the smallest version that your users can actually work with. It is not a cheap version of the full solution. It is a test, built to answer the questions that decide whether the rest is worth building.
- Pick the riskiest assumption. Here: will independent journalists use it to solve "drafts rely heavily on a narrow source set"?
- Build only what tests it. One team, one use case, a few core modules. People do the rest by hand for now.
- Run a paid pilot. Agree the acceptance criteria, input limits and reviewer responsibilities before starting.
- Measure, then decide. Track unanswered reporting questions; reviewer correction minutes; buyer acceptance and repeat purchase. Then expand, change course or stop, with evidence instead of opinions.
MVP scope for this solution. Costed pilot: One organization, one defined input format and one representative pilot batch using authorized interview notes and research records. Professional judgment, physical inspections, live external actions and production certification remain outside this prototype. Start with one buyer organization and a bounded set of representative inputs. Implement the first two modules: map source contributions; flag missing perspectives. Support the third task through an assisted review queue: draft reporting questions. Handle the remaining required functions manually until validated. Include input upload, source references, user correction, a reviewer approval step and export of editor-reviewed source coverage report. Authentication, account isolation, deletion controls and basic operational logging are included. Specialized production certification, live write integrations and broader rollout are not included unless explicitly stated.
After the MVP. After paying customers repeatedly accept editor-reviewed source coverage report, automate link proposed outputs to original source records; capture reviewer corrections and approval; export a versioned editor-reviewed source coverage report. Add one tested read integration, reusable customer configuration and scheduled repeat delivery. Increase supported formats or teams only when evaluation cases and reviewer capacity cover the new scope. One organization, one defined input format and one representative pilot batch using authorized interview notes and research records. Professional judgment, physical inspections, live external actions and production certification remain outside this prototype.
What the build depends on. Evidence coordinates, versioned rules, reviewer decisions and a representative reference set. Measure misses as well as confirmed findings before scaling. Obtain representative authorized inputs, an agreed review rubric and a buyer-side owner. Specific scope: One organization, one defined input format and one representative pilot batch using authorized interview notes and research records. Professional judgment, physical inspections, live external actions and production certification remain outside this prototype.
Investment
A planning range to start the conversation, not a quote. You pay per phase, so you can stop after the MVP.
- Phase 1
MVP
One buyer segment, one recurring use case; first modules: map source contributions; flag missing perspectives. Manual review in the loop.
- Phase 2
Paid pilot
Accounts, roles, review states, audit trail and the first integration, hardened for two to three paying pilot customers.
- Phase 3
Full product
Self-serve onboarding, billing, monitoring and the wider integration set.
Indicative total, MVP to full product$42,500about 2 weeks of creation time · start with the MVP from $12,500
Running costs per month
A rough indication of monthly hosting and AI model costs once it is live, not tested. Real costs depend on usage, file sizes and the models chosen.
| Stage | Hosting and infrastructure | AI usage | Total per month |
|---|---|---|---|
| MVP and paid pilotabout 3 customers | $30–$60 | $80–$160 | $110–$220 |
| Full productabout 50 customers | $110–$210 | $880–$1,750 | $990–$1,960 |
Run it or resell it
For your own team
Independent journalists run it inside the business: authorized interview notes and research records in, editor-reviewed source coverage report out, reviewed by your people.
As part of your offer
Agencies, consultancies and software companies can offer it to their own clients under their brand. We build and maintain it; you sell and deliver it.
Your brand, or this one
Run it under your own brand, or start from this concept style.
- primary
#91272e - accent
#54bcc9 - surface
#f1e4e5 - ink
#22201e
- Headings
- Archivo
- Text
- Lora
- Voice
- Literate, generous, editorial
Selling it to your own clients: the go-to-market playbook
Pricing to test
Test USD 500-2,000 for a defined audit sample and report. Offer recurring review priced by reviewed items and specialist hours. Software-only access can follow a reliable reviewed service. All prices require validation. For this buyer, package the first sale around prepare a sample editor-reviewed source coverage report from a small authorized set of authorized interview notes and research records and the defined editor-reviewed source coverage report. Record actual review effort before offering a recurring allowance. The commercial pilot fee is distinct from the platform development budget.
Message to test
Transparent coverage gaps without forced equivalence. Demonstrate the result with prepare a sample editor-reviewed source coverage report from a small authorized set of authorized interview notes and research records for independent journalists. Use a concrete before-and-after example without promising unmeasured savings.
Where to find buyers
Author associations and specialist editorial networks
Lead magnet
Prepare a sample editor-reviewed source coverage report from a small authorized set of authorized interview notes and research records
The first 30 days
- Week 1: interview five prospective buyers from independent journalists and inspect how they handle drafts rely heavily on a narrow source set.
- Week 2: prepare prepare a sample editor-reviewed source coverage report from a small authorized set of authorized interview notes and research records using authorized or synthetic material.
- Week 3: share the demonstration through author associations and specialist editorial networks and seek one bounded paid pilot.
- Week 4: measure unanswered reporting questions; reviewer correction minutes; buyer acceptance and repeat purchase, review delivery effort and ask for a repeat purchase. This is a validation schedule, not a promise that the full product can be built in thirty days.
Paid pilot
Agree the acceptance criteria, input limits and reviewer responsibilities before starting. Run prepare a sample editor-reviewed source coverage report from a small authorized set of authorized interview notes and research records and deliver editor-reviewed source coverage report. Compare unanswered reporting questions; reviewer correction minutes; buyer acceptance and repeat purchase with the buyer's current process on comparable cases; include corrections, missed issues and reviewer time. Seek payment and repeat use. Stop or revise the scope if data access, accuracy or unit economics fail.
Success metrics
Unanswered reporting questions; reviewer correction minutes; buyer acceptance and repeat purchase
Retention and expansion
Build repeat use around editor-reviewed source coverage report. Save approved configurations and review decisions with permission, revisit unresolved exceptions and show progress on unanswered reporting questions; reviewer correction minutes; buyer acceptance and repeat purchase. Offer a recurring volume allowance after repeat demand; expand to adjacent tasks only when the buyer asks and delivery quality remains acceptable.
Why clients would pick it
A domain-specific review rubric and rights-cleared examples of confirmed defects, false alarms and reviewer reasoning. For this concept, accumulate permissioned examples and reviewer corrections around transparent coverage gaps without forced equivalence. The durable asset is reliable task-specific execution and trusted customer configuration, not access to a general-purpose AI model.
Alternatives and positioning
Manual reviewers, checklists, generic scanning tools and specialist audit services. Position this concept around transparent coverage gaps without forced equivalence. Compare it against the customer's current process on the same representative task. This is proposed differentiation; no exhaustive competitor study or uniqueness claim has been established.
Main delivery costs
Document or media processing, model evaluation, expert review, false-positive handling, rechecks and customer-specific rubric calibration. Initial validation additionally budgets for representative sample preparation, interviews with independent journalists, and buyer-side review of editor-reviewed source coverage report. Track model usage, storage, reviewer minutes, exception handling and customer support per accepted deliverable.
Safeguards
Preserve author voice, source attribution, quotation accuracy and usage permissions. Authors approve substantive changes and publication scope. One organization, one defined input format and one representative pilot batch using authorized interview notes and research records. Professional judgment, physical inspections, live external actions and production certification remain outside this prototype. Require appropriate access and publication approval. Preserve source material, label AI drafts and make corrections traceable. Measure false positives and missed cases alongside speed.