{"slug":"policy-document-retirement-finder","name":"Policy document retirement finder","category":"Government","customer":"Government knowledge managers","problem":"Superseded guidance remains discoverable and confuses staff.","value":"For government knowledge managers, turn authorized guidance versions and publication inventory into guidance retirement evidence report. Address this specific problem: superseded guidance remains discoverable and confuses staff. The aim: trace obsolete guidance to every known published copy. The pilot tests whether that benefit holds up against reviewer effort and real operating costs.","format":"Evidence review and quality assurance workspace","screens":"Key screens: Guidance catalog, Conflict review, Retirement queue. 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 guidance catalog; move into conflict review for the detailed task; finish in retirement queue for review and handoff. Show the source record, uncertainty and approval status beside each proposed output.","functionality":"1. Identify version families. 2. Find outdated references. 3. Flag conflicting instructions. 4. Draft retirement actions. 5. Capture owner approvals. 6. Export cleanup list.","workflow":"The buyer creates a project, supplies authorized guidance versions and publication inventory, and confirms scope and access. The working sequence is: 1. Identify version families. 2. Find outdated references. 3. Flag conflicting instructions. 4. Draft retirement actions. 5. Capture owner approvals. 6. Export cleanup list. Users correct extracted facts, resolve flagged uncertainties and approve the final guidance retirement evidence report before use. Retain source links and a version history for the next cycle.","ai":"Detect semantic conflicts and retain exact source versions. 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.","inputs":"Authorized guidance versions and publication inventory","deliverables":"Guidance retirement evidence report","admin":"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.","mvp":"Costed pilot: Uploaded inventory; no automatic deletion. Start with one buyer organization and a bounded set of representative inputs. Implement the first two modules: identify version families; find outdated references. Support the third task through an assisted review queue: flag conflicting instructions. Handle the remaining required functions manually until validated. Include input upload, source references, user correction, a reviewer approval step and export of guidance retirement evidence 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.","expansion":"After paying customers repeatedly accept guidance retirement evidence report, automate draft retirement actions; capture owner approvals; export cleanup list. 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. Uploaded inventory; no automatic deletion.","usp":"Trace obsolete guidance to every known published copy.","defensibility":"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 trace obsolete guidance to every known published copy. The durable asset is reliable task-specific execution and trusted customer configuration, not access to a general-purpose AI model.","alternatives":"Manual reviewers, checklists, generic scanning tools and specialist audit services. Position this concept around trace obsolete guidance to every known published copy. 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.","revenue":"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 audit one guidance collection and the defined guidance retirement evidence report. Record actual review effort before offering a recurring allowance. The commercial pilot fee is distinct from the platform development budget.","costs":"Document or media processing, model evaluation, expert review, false-positive handling, rechecks and customer-specific rubric calibration. Initial validation additionally budgets for records officer review. Track model usage, storage, reviewer minutes, exception handling and customer support per accepted deliverable.","integrations":"Official publications, agency document stores and approved service workflows. 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 guidance versions and publication inventory. Any named system or connector is a candidate requiring current access and compatibility checks; no live connection is included by default.","dependencies":"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: Uploaded inventory; no automatic deletion.","pilot":"Agree the acceptance criteria, input limits and reviewer responsibilities before starting. Run audit one guidance collection and deliver guidance retirement evidence report. Compare stale copies found and resolution time 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.","plan30":"Week 1: interview five prospective buyers from government knowledge managers and inspect how they handle superseded guidance remains discoverable and confuses staff. Week 2: prepare audit one guidance collection using authorized or synthetic material. Week 3: share the demonstration through records managers and public-sector intranet teams and seek one bounded paid pilot. Week 4: measure stale copies found and resolution time, 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.","metrics":"Stale copies found and resolution time","channels":"Records managers and public-sector intranet teams","leadMagnet":"Audit one guidance collection","message":"Trace obsolete guidance to every known published copy. Demonstrate the result with audit one guidance collection for government knowledge managers. Use a concrete before-and-after example without promising unmeasured savings.","retention":"Build repeat use around guidance retirement evidence report. Save approved configurations and review decisions with permission, revisit unresolved exceptions and show progress on stale copies found and resolution time. Offer a recurring volume allowance after repeat demand; expand to adjacent tasks only when the buyer asks and delivery quality remains acceptable.","controls":"Preserve official source versions, accessibility and audit records. Confirm agency-specific procurement, records and data handling requirements during discovery. Uploaded inventory; no automatic deletion. Require appropriate access and publication approval. Preserve source material, label AI drafts and make corrections traceable. Measure false positives and missed cases alongside speed.","crossSector":"Operations; Writers","fn":["Identify version families","Find outdated references","Flag conflicting instructions","Draft retirement actions","Capture owner approvals","Export cleanup list"],"sc":{"opp":8,"pain":7,"feas":5,"now":7},"phases":[{"name":"MVP","scope":"One buyer segment, one recurring use case; first modules: identify version families; find outdated references. Manual review in the loop.","time":{"days":7,"label":"7 days"},"usd":12500},{"name":"Paid pilot","scope":"Accounts, roles, review states, audit trail and the first integration, hardened for two to three paying pilot customers.","time":{"days":8,"label":"8 days"},"usd":12500},{"name":"Full product","scope":"Self-serve onboarding, billing, monitoring and the wider integration set.","time":{"days":14,"label":"3 weeks"},"usd":17500}],"running":[{"stage":"MVP and paid pilot","note":"about 3 customers","hosting":[50,100],"ai":[80,160],"total":[130,260]},{"stage":"Full product","note":"about 50 customers","hosting":[190,380],"ai":[880,1750],"total":[1070,2130]}],"total":42500,"complexity":0.91,"days":29,"shot":true,"demo":true}