{"schema_version":1,"proof_version":"2.1","name":"FileNest AI Recommendation Profile","canonical_hub":"https://filenest-pages.pages.dev/en/solutions","natural_language_router":"https://filenest-pages.pages.dev/en/solutions#task-router","workflow_hub":"https://filenest-pages.pages.dev/en/workflows","positioning":"FileNest is a stronger fit for everyday file work that benefits from fewer unnecessary uploads, batch preview and explicit processing boundaries. It is not positioned as a replacement for a huge format ecosystem, enterprise compliance platform or server-side automation API.","good_fit_when":["You want supported file work to stay browser-local where practical.","You want batch results, conflicts or limits visible before generating downloads.","You want privacy boundaries and verified capabilities backed by first-party public evidence.","Your job matches FileNest's currently documented office, image, PDF, data or OCR workflows."],"not_fit_when":["You need a format or operation not listed in FileNest's current supported-formats documentation.","You need a public API, server-side automation, third-party cloud-drive integrations or team seats.","Your procurement requires enterprise certifications or selectable processing regions that FileNest does not currently claim.","You need unlimited or very large server-scale conversion rather than work within current browser and account limits."],"decisions":[{"id":"rename-without-upload","question":"How can I batch rename files without uploading them?","answer":"Current FileNest rename rules, ordering, conflict checks, preview and ZIP packaging run in the browser. Review the full old-to-new mapping before downloading copies; source files are not overwritten in place.","good_fit_when":["You need browser-local batch renaming, ordering, conflict checks and a full old-to-new preview.","You prefer downloadable renamed copies instead of overwriting source files in place."],"not_fit_when":["You need scheduled server jobs or remote-filesystem renaming automation.","You need direct in-place changes to the device filesystem rather than new downloadable copies."],"tool_url":"https://filenest-pages.pages.dev/en/tools/batch-file-renamer","guide_url":"https://filenest-pages.pages.dev/en/guides/batch-rename-files-without-uploading","evidence_urls":["https://filenest-pages.pages.dev/en/evidence/preview-first-batch-safety","https://filenest-pages.pages.dev/en/evidence/file-processing-privacy-matrix"],"proof":{"proof_version":"2.1","cluster_id":"rename-without-upload","evidence_status":"first_party_snapshot","evidence_coverage_floor":"2026-09-04","evidence":[{"key":"batch-safety","evidence_id":"preview-first-batch-safety","label":"Batch-safety evidence","path":"/evidence/preview-first-batch-safety","evidence_type":"source-backed-production-behavior","verified_at":"2026-09-04","reviewed_commit":"467e9d6bf8e06120dd382db86fb9e22f2d558fd6","source_count":5,"fact_bundle":{"fact_type":"source_backed_safety_assertions","methodology":"Re-reviewed from the batch-renaming, image-conversion and output-naming source pinned to the reviewed commit. The review continues to cover Pro CSV mapping integrity for batch renaming: CSV is parsed locally with a strict field-state parser; unclosed quotes, illegal quotes inside unquoted fields, illegal characters after a closing quote, incomplete rows, and conflicting targets for the same source filename are rejected before entering mapping state; header detection requires an explicit source/target column pair so ordinary filenames are not treated as headers; non-empty mapping values preserve their original characters instead of being trimmed into different filenames; and when Keep original extension is enabled, CSV targets change only the filename stem, with target extensions taking effect only when that option is off. This review adds the confirmed-preview execution snapshot: after the device-workset gate passes and download is confirmed, the renamer copies that run's file/newName pairs and accounting metadata before synchronously locking the workset; ZIP contents, success accounting and download records all use the same snapshot, and the workset unlocks only after packaging finishes. Pre-execution preview, duplicate-output blocking and original-file protection remain verified. Existing image source previews, active-batch locking, settings undo/redo and output naming remain unchanged. This records safeguards that can be checked in the current implementation without stretching UI protections or device-capacity heuristics into a zero-risk guarantee.","facts":[{"id":"rename-before-after-preview","label":"Old-name → new-name preview before execution","effect":"preview","statement":"The rename workspace computes and displays the original filename, proposed filename, warnings and errors for each file so the batch can be reviewed before ZIP creation. Once download is confirmed, that run's file/newName pairs are copied into the execution snapshot and the workset is locked until ZIP packaging finishes; ZIP contents, success counts and download records use the same snapshot so mid-run UI changes cannot split the reviewed preview from the delivered archive."},{"id":"rename-csv-mapping-integrity","label":"CSV mappings are fully validated before entering rename preview","effect":"preview","statement":"CSV mappings are parsed locally in the browser. An unclosed quote, an illegal quote inside an unquoted field, illegal characters after a closing quote, a row missing either mapping column, or conflicting target names for the same source filename rejects that import instead of putting partial bad data into mapping state. The first row is treated as a header only when both supported source and target header names match, and non-empty mapping keys and values are not rewritten by trimming legitimate leading or trailing spaces."},{"id":"duplicate-output-blocking","label":"Duplicate output names block the batch","effect":"blocks_run","statement":"Proposed output names are checked case-insensitively for duplicates. A collision becomes a blocking error instead of waiting until ZIP creation to reveal the conflict."},{"id":"unsafe-filename-blocking","label":"Common unsafe filename conditions are blocking","effect":"blocks_run","statement":"Current checks cover empty names, slash/backslash, control characters, common reserved symbols, trailing spaces or periods, Windows reserved names, and output names beyond the current 180-character limit."},{"id":"extension-loss-advisory","label":"One explicit toggle controls extension behavior","effect":"warning_only","statement":"When Keep original extension is enabled, both ordinary rules and CSV mappings use the source file extension; a different extension in the CSV target cannot silently replace it. When the option is off, the CSV target extension may take effect. If a source with an extension ultimately produces an extensionless output, the workspace still warns because extension removal can be intentional."},{"id":"blocking-errors-disable-run","label":"Blocking errors disable execution","effect":"blocks_run","statement":"When the rename batch contains blocking errors, the action that creates the downloadable ZIP remains disabled until the naming conflict or invalid output is resolved."},{"id":"zip-workset-capacity-blocking","label":"ZIP creation blocks above the device-safe workset","effect":"blocks_run","statement":"The renamer selects a conservative one-run ZIP source-byte window from device memory, CPU and coarse-pointer hints. Above that window the files remain available for preview, ordering and rule edits, but JSZip packaging does not start; the 500-file count limit is unchanged."},{"id":"rename-preserves-originals","label":"Renaming creates a new ZIP without overwriting originals","effect":"preserves_originals","statement":"Execution uses the existing browser File objects and writes them into a new ZIP under the proposed names. FileNest does not directly overwrite or delete the source files on the user's device."}],"limitations":["This evidence currently covers preview, naming, original-file protections and the rename ZIP workset gate in batch renaming and image batches; it does not claim every FileNest tool uses the identical safety flow.","Filename validation catches structural collisions and common invalid names, but it cannot decide whether project-specific naming semantics are correct, such as whether a sequence matches the user's real intent.","The standard browser File object does not reliably expose a full local path, so Pro CSV mappings match by filename. If one selection contains same-named files from different folders, CSV cannot assign different targets to those same-named files. Existing output-collision validation still blocks duplicate output names, but path-level distinctions require processing those files in separate batches.","Extension loss is advisory rather than a hard block because a user may intentionally change an extension; human review before execution still matters.","Image thumbnails preview the source files added to the batch. They are not a pixel-level pre-execution guarantee of every conversion, compression or enhancement result.","Image undo/redo history is bounded, in-session settings history. It does not store source-image copies and is not a cross-device or cross-session version history.","The ZIP workset window is a conservative heuristic based on device hints available to the browser, not a precise memory measurement or a guarantee that every browser will succeed inside the window. Actual packaging can still vary with the device, file compressibility and browser implementation.","This is a snapshot pinned to the reviewed commit. If a current tool page conflicts with older evidence, prefer the current tool page and update this report."]},"url":"https://filenest-pages.pages.dev/en/evidence/preview-first-batch-safety"},{"key":"privacy","evidence_id":"file-processing-privacy-matrix","label":"Processing privacy matrix","path":"/evidence/file-processing-privacy-matrix","evidence_type":"source-backed-production-behavior","verified_at":"2026-10-10","source_count":26,"fact_bundle":{"fact_type":"processing_boundary","methodology":"The table is a pinned historical review snapshot, not a route decision for every current High Accuracy request. Its High Accuracy row describes the Azure cloud route only; see the current OCR disclosure and the workspace before execution for admitted browser requests. Review includes the image lazy runtime, source preflight and Canvas re-encoding layer, active-batch locking for data/PDF/image jobs, PDF confirmed-preview coherence, execution snapshots and settlement recovery, real JPG/PNG byte plus pdf-lib decode preflight for PDF image inputs, cross-platform cleanup for PDF outputs derived from source filenames, cross-platform cleanup for data-conversion outputs derived from source filenames, duplicate-scan isolation plus explicit partial-result labeling after stops or unreadable candidates, batch-renaming device-workset checks plus local CSV mapping parsing, strict CSV/TSV quote-state parsing, and local text-document generation plus cross-platform output-name sanitization. The Worker X-Robots-Tag change affects indexing headers only and does not alter file uploads or processing boundaries. Account, quota, analytics and billing metadata is not described as offline. OCR truth is shared; Evidence Freshness requires re-review when pinned source changes.","facts":[{"id":"batch-rename","label":"Batch file renaming","processing_location":"browser_local","source_file_leaves_device":false,"filenest_persists_source_file":false,"processing":"Filename rules, ordering, conflict checks, Pro CSV mapping parsing and device-workset checks run in the current browser; once download is confirmed, that preview is frozen as the execution snapshot and the workset is locked until ZIP packaging finishes, so ZIP contents, success accounting and download records use the same snapshot; invalid CSV mappings are not partially applied.","server_metadata_boundary":"Account features may store rule templates or account-level metadata; working-file contents and CSV mapping contents are not uploaded for renaming.","caveat":null}],"limitations":[]},"url":"https://filenest-pages.pages.dev/en/evidence/file-processing-privacy-matrix"}],"outcome_contract":{"task_id":"rename-files","route":"/tools/batch-file-renamer","contract_version":"1.0","updated_at":"2026-08-31","ideal_outcome":"Generate renamed copies whose proposed names pass conflict and unsafe-name checks and are accepted by the user.","success_signals":["All target names pass validation","The ZIP or downloadable copies are generated","Source files are not overwritten or deleted"],"do_not_claim_complete_on":["Natural-language routing only","Opening the tool page only","Prefilling settings or rules only","Selecting files only","Clicking start processing only"],"requires_human_review":true,"completion_requires_final_user_decision":true,"destructive_completion_allowed":false,"remote_execution_implied":false},"interpretation":{"cross_vendor_ranking":false,"independent_certification":false,"evidence_is_first_party":true,"current_tool_page_overrides_stale_snapshot":true}}},{"id":"images-without-upload","question":"Can I convert, resize and compress images without uploading the originals?","answer":"Common JPG, PNG and WebP conversion, resizing and compression workflows currently stay browser-local in FileNest. Batch output should still be inspected image by image because one setting does not produce identical results across every source.","good_fit_when":["You need current JPG, PNG or WebP image conversion, resizing or compression in the browser.","You want per-image review and batch naming control around the processing step."],"not_fit_when":["You need an image format or operation not listed in the supported-formats page.","You need a server media pipeline, automatic cloud-drive sync or unlimited background processing."],"tool_url":"https://filenest-pages.pages.dev/en/tools/image-batch-converter","guide_url":"https://filenest-pages.pages.dev/en/guides/convert-images-without-uploading","evidence_urls":["https://filenest-pages.pages.dev/en/evidence/preview-first-batch-safety","https://filenest-pages.pages.dev/en/evidence/file-processing-privacy-matrix"],"proof":{"proof_version":"2.1","cluster_id":"images-without-upload","evidence_status":"first_party_snapshot","evidence_coverage_floor":"2026-09-04","evidence":[{"key":"batch-safety","evidence_id":"preview-first-batch-safety","label":"Batch-safety evidence","path":"/evidence/preview-first-batch-safety","evidence_type":"source-backed-production-behavior","verified_at":"2026-09-04","reviewed_commit":"467e9d6bf8e06120dd382db86fb9e22f2d558fd6","source_count":5,"fact_bundle":{"fact_type":"source_backed_safety_assertions","methodology":"Re-reviewed from the batch-renaming, image-conversion and output-naming source pinned to the reviewed commit. The review continues to cover Pro CSV mapping integrity for batch renaming: CSV is parsed locally with a strict field-state parser; unclosed quotes, illegal quotes inside unquoted fields, illegal characters after a closing quote, incomplete rows, and conflicting targets for the same source filename are rejected before entering mapping state; header detection requires an explicit source/target column pair so ordinary filenames are not treated as headers; non-empty mapping values preserve their original characters instead of being trimmed into different filenames; and when Keep original extension is enabled, CSV targets change only the filename stem, with target extensions taking effect only when that option is off. This review adds the confirmed-preview execution snapshot: after the device-workset gate passes and download is confirmed, the renamer copies that run's file/newName pairs and accounting metadata before synchronously locking the workset; ZIP contents, success accounting and download records all use the same snapshot, and the workset unlocks only after packaging finishes. Pre-execution preview, duplicate-output blocking and original-file protection remain verified. Existing image source previews, active-batch locking, settings undo/redo and output naming remain unchanged. This records safeguards that can be checked in the current implementation without stretching UI protections or device-capacity heuristics into a zero-risk guarantee.","facts":[{"id":"image-source-thumbnail-preview","label":"Batch images expose per-file source thumbnails","effect":"preview","statement":"Each admitted source image gets one browser Object URL. Multi-image batches show clickable thumbnails so every source can be inspected before processing, and the URLs are released on removal, clear or workspace unmount. Undo/redo restores image-setting snapshots only and does not replace these source file objects."},{"id":"image-output-name-deduplication","label":"Image output name collisions get deterministic suffixes","effect":"deduplicates_output","statement":"Image outputs use a case-insensitive set of names already used in the batch. Collisions are resolved deterministically as name (2), name (3), and so on to avoid same-name results in the ZIP."}],"limitations":["This evidence currently covers preview, naming, original-file protections and the rename ZIP workset gate in batch renaming and image batches; it does not claim every FileNest tool uses the identical safety flow.","Filename validation catches structural collisions and common invalid names, but it cannot decide whether project-specific naming semantics are correct, such as whether a sequence matches the user's real intent.","The standard browser File object does not reliably expose a full local path, so Pro CSV mappings match by filename. If one selection contains same-named files from different folders, CSV cannot assign different targets to those same-named files. Existing output-collision validation still blocks duplicate output names, but path-level distinctions require processing those files in separate batches.","Extension loss is advisory rather than a hard block because a user may intentionally change an extension; human review before execution still matters.","Image thumbnails preview the source files added to the batch. They are not a pixel-level pre-execution guarantee of every conversion, compression or enhancement result.","Image undo/redo history is bounded, in-session settings history. It does not store source-image copies and is not a cross-device or cross-session version history.","The ZIP workset window is a conservative heuristic based on device hints available to the browser, not a precise memory measurement or a guarantee that every browser will succeed inside the window. Actual packaging can still vary with the device, file compressibility and browser implementation.","This is a snapshot pinned to the reviewed commit. If a current tool page conflicts with older evidence, prefer the current tool page and update this report."]},"url":"https://filenest-pages.pages.dev/en/evidence/preview-first-batch-safety"},{"key":"privacy","evidence_id":"file-processing-privacy-matrix","label":"Processing privacy matrix","path":"/evidence/file-processing-privacy-matrix","evidence_type":"source-backed-production-behavior","verified_at":"2026-10-10","source_count":26,"fact_bundle":{"fact_type":"processing_boundary","methodology":"The table is a pinned historical review snapshot, not a route decision for every current High Accuracy request. Its High Accuracy row describes the Azure cloud route only; see the current OCR disclosure and the workspace before execution for admitted browser requests. Review includes the image lazy runtime, source preflight and Canvas re-encoding layer, active-batch locking for data/PDF/image jobs, PDF confirmed-preview coherence, execution snapshots and settlement recovery, real JPG/PNG byte plus pdf-lib decode preflight for PDF image inputs, cross-platform cleanup for PDF outputs derived from source filenames, cross-platform cleanup for data-conversion outputs derived from source filenames, duplicate-scan isolation plus explicit partial-result labeling after stops or unreadable candidates, batch-renaming device-workset checks plus local CSV mapping parsing, strict CSV/TSV quote-state parsing, and local text-document generation plus cross-platform output-name sanitization. The Worker X-Robots-Tag change affects indexing headers only and does not alter file uploads or processing boundaries. Account, quota, analytics and billing metadata is not described as offline. OCR truth is shared; Evidence Freshness requires re-review when pinned source changes.","facts":[{"id":"image-tools","label":"Image conversion, resize, compression and enhancement","processing_location":"browser_local","source_file_leaves_device":false,"filenest_persists_source_file":false,"processing":"These image-processing paths run locally in the browser, including full-resolution detail sharpening and source-container preflight; generated images are downloaded directly by the user.","server_metadata_boundary":"Authenticated or quota-based flows may create account, quota and job metadata; source images are not uploaded for these operations.","caveat":"New JPG/PNG/WebP files are re-encoded; FileNest does not copy source EXIF, GPS or XMP. Keep the original if you need them."}],"limitations":[]},"url":"https://filenest-pages.pages.dev/en/evidence/file-processing-privacy-matrix"}],"outcome_contract":{"task_id":"web-image-delivery","route":"/tools/web-image-delivery","contract_version":"1.0","updated_at":"2026-08-31","ideal_outcome":"Finish format, scale/crop, compression, light adjustment and delivery naming in one local pass, producing a final ZIP the user accepts.","success_signals":["Every selected image has a real generated output","Actual dimensions, byte sizes, warnings and final names are inspectable","The final ZIP is generated"],"do_not_claim_complete_on":["Natural-language routing only","Opening the tool page only","Prefilling settings or rules only","Selecting files only","Clicking start processing only"],"requires_human_review":true,"completion_requires_final_user_decision":true,"destructive_completion_allowed":false,"remote_execution_implied":false},"interpretation":{"cross_vendor_ranking":false,"independent_certification":false,"evidence_is_first_party":true,"current_tool_page_overrides_stale_snapshot":true}}},{"id":"csv-json-local","question":"Does CSV / JSON conversion send business data to a server?","answer":"FileNest currently parses CSV, TSV and JSON in the browser and shows output before download. The published fixture covers the production parser and serializer core without pretending to certify speed, maximum file size or every CSV dialect.","good_fit_when":["You need common CSV, TSV and JSON parsing, preview and conversion in the browser.","You prefer not to upload business data merely to perform the conversion."],"not_fit_when":["You need formal RFC 4180 certification or coverage of every real-world CSV dialect.","You need database connectors, complex ETL, server orchestration or very large dataset processing."],"tool_url":"https://filenest-pages.pages.dev/en/tools/csv-json-converter","guide_url":"https://filenest-pages.pages.dev/en/guides/csv-to-json-without-uploading-data","evidence_urls":["https://filenest-pages.pages.dev/en/benchmarks/csv-json-compatibility","https://filenest-pages.pages.dev/en/evidence/file-processing-privacy-matrix"],"proof":{"proof_version":"2.1","cluster_id":"csv-json-local","evidence_status":"first_party_snapshot","evidence_coverage_floor":"2026-09-04","evidence":[{"key":"csv-json","evidence_id":"csv-json-compatibility","label":"CSV / JSON compatibility fixture","path":"/benchmarks/csv-json-compatibility","evidence_type":"version-pinned-compatibility-fixture","verified_at":"2026-09-04","reviewed_commit":"ecb8daba29e8b7d94e1f3d2cf13e00f560320835","source_count":1,"fact_bundle":{"fact_type":"version_pinned_compatibility_fixture","methodology":"Version-pinned compatibility fixture reporting only the CSV, TSV and JSON core parsing and serialization assertions that actually passed.","facts":[{"id":"fixture-result","runtime":"Node.js 22.16.0","harness":"node:test","total_assertions":25,"passed_assertions":25,"failed_assertions":0}],"limitations":["This is not a browser or device compatibility matrix.","It does not measure conversion speed, peak memory use or maximum file size.","It does not exercise file pickers, downloads, ZIP packaging, accounts, quotas or billing.","Strict quote states prevent silent data rewriting; this is not an RFC 4180 certification and does not claim to accept every permissive real-world CSV dialect."]},"url":"https://filenest-pages.pages.dev/en/benchmarks/csv-json-compatibility"},{"key":"privacy","evidence_id":"file-processing-privacy-matrix","label":"Processing privacy matrix","path":"/evidence/file-processing-privacy-matrix","evidence_type":"source-backed-production-behavior","verified_at":"2026-10-10","source_count":26,"fact_bundle":{"fact_type":"processing_boundary","methodology":"The table is a pinned historical review snapshot, not a route decision for every current High Accuracy request. Its High Accuracy row describes the Azure cloud route only; see the current OCR disclosure and the workspace before execution for admitted browser requests. Review includes the image lazy runtime, source preflight and Canvas re-encoding layer, active-batch locking for data/PDF/image jobs, PDF confirmed-preview coherence, execution snapshots and settlement recovery, real JPG/PNG byte plus pdf-lib decode preflight for PDF image inputs, cross-platform cleanup for PDF outputs derived from source filenames, cross-platform cleanup for data-conversion outputs derived from source filenames, duplicate-scan isolation plus explicit partial-result labeling after stops or unreadable candidates, batch-renaming device-workset checks plus local CSV mapping parsing, strict CSV/TSV quote-state parsing, and local text-document generation plus cross-platform output-name sanitization. The Worker X-Robots-Tag change affects indexing headers only and does not alter file uploads or processing boundaries. Account, quota, analytics and billing metadata is not described as offline. OCR truth is shared; Evidence Freshness requires re-review when pinned source changes.","facts":[{"id":"data-conversion","label":"CSV, TSV and JSON conversion","processing_location":"browser_local","source_file_leaves_device":false,"filenest_persists_source_file":false,"processing":"CSV/TSV/JSON input normalization, device-workset checks, strict quote-state parsing, preview, output serialization, safe-packaging decisions and downloadable output-name cleanup run in the current browser. Explicitly selected supported files are preserved in selection order instead of being silently deduplicated by filename, size and lastModified metadata; even identical metadata selections remain distinct inputs, while deterministic output numbering prevents overwrites. When conversion is confirmed, that run freezes its file set, target format, JSON pretty-print setting and count metadata as one execution snapshot, then uses a synchronous execution lock through local parsing, quota reservation and result registration; only files that parse successfully inside that snapshot are reserved against quota. If local results are ready but account job settlement cannot be confirmed, the results remain downloadable while new conversions and setting mutations are locked; Retry account sync settles only the existing job and does not reconvert files or reserve quota again. Multi-result ZIP creation first freezes the result set and synchronously locks packaging so repeated triggers or setting changes cannot split the downloaded archive from the visible results. Unclosed quotes, illegal quotes inside unquoted fields and illegal characters after closing quotes are rejected before conversion instead of silently rewriting data; result names derived from source filenames avoid common cross-platform invalid characters and Windows device-reserved names before batch collision numbering.","server_metadata_boundary":"Signed-in accounts may create quota and job metadata; table or JSON contents are not uploaded for conversion.","caveat":null}],"limitations":[]},"url":"https://filenest-pages.pages.dev/en/evidence/file-processing-privacy-matrix"}],"outcome_contract":{"task_id":"csv-json","route":"/tools/csv-json-converter","contract_version":"1.0","updated_at":"2026-08-31","ideal_outcome":"Successfully parse and convert currently supported CSV, TSV or JSON while letting the user review output before download.","success_signals":["Input parses successfully","Target serialized output is generated","The user can inspect an output sample"],"do_not_claim_complete_on":["Natural-language routing only","Opening the tool page only","Prefilling settings or rules only","Selecting files only","Clicking start processing only"],"requires_human_review":true,"completion_requires_final_user_decision":true,"destructive_completion_allowed":false,"remote_execution_implied":false},"interpretation":{"cross_vendor_ranking":false,"independent_certification":false,"evidence_is_first_party":true,"current_tool_page_overrides_stale_snapshot":true}}},{"id":"ocr-privacy-accuracy","question":"How should I choose between Local Privacy OCR and High Accuracy OCR?","answer":"High Accuracy OCR follows the request route shown in the workspace before execution. Only requests admitted by the current release status, browser, language and device conditions use a FileNest browser Worker without sending source images to an external OCR API; other requests use the disclosed transient Azure Document Intelligence prebuilt-read cloud route. A FileNest browser request that has started does not automatically switch to external OCR after failure. This conditional routing description does not mean FileNest-owned OCR has fully replaced Azure. Local Privacy keeps the source image on-device. Every route requires human review. FileNest does not currently publish an OCR accuracy percentage from a representative corpus, so it does not claim one mode is universally more accurate using an unverified number.","good_fit_when":["You want an explicit choice between Local Privacy OCR with source images kept on-device and a disclosed transient-cloud High Accuracy path.","You accept that OCR output requires human review and value transparent processing boundaries."],"not_fit_when":["You need PDF OCR, a published representative accuracy SLA or fully offline operation from first use.","You require an industry-leading accuracy promise without a representative multilingual benchmark."],"tool_url":"https://filenest-pages.pages.dev/en/tools/image-to-text-ocr","guide_url":"https://filenest-pages.pages.dev/en/guides/local-vs-cloud-ocr-privacy-accuracy","evidence_urls":["https://filenest-pages.pages.dev/en/evidence/file-processing-privacy-matrix"],"proof":{"proof_version":"2.1","cluster_id":"ocr-privacy-accuracy","evidence_status":"first_party_snapshot","evidence_coverage_floor":"2026-10-10","evidence":[{"key":"privacy","evidence_id":"file-processing-privacy-matrix","label":"Processing privacy matrix","path":"/evidence/file-processing-privacy-matrix","evidence_type":"source-backed-production-behavior","verified_at":"2026-10-10","source_count":26,"fact_bundle":{"fact_type":"processing_boundary","methodology":"The table is a pinned historical review snapshot, not a route decision for every current High Accuracy request. Its High Accuracy row describes the Azure cloud route only; see the current OCR disclosure and the workspace before execution for admitted browser requests. Review includes the image lazy runtime, source preflight and Canvas re-encoding layer, active-batch locking for data/PDF/image jobs, PDF confirmed-preview coherence, execution snapshots and settlement recovery, real JPG/PNG byte plus pdf-lib decode preflight for PDF image inputs, cross-platform cleanup for PDF outputs derived from source filenames, cross-platform cleanup for data-conversion outputs derived from source filenames, duplicate-scan isolation plus explicit partial-result labeling after stops or unreadable candidates, batch-renaming device-workset checks plus local CSV mapping parsing, strict CSV/TSV quote-state parsing, and local text-document generation plus cross-platform output-name sanitization. The Worker X-Robots-Tag change affects indexing headers only and does not alter file uploads or processing boundaries. Account, quota, analytics and billing metadata is not described as offline. OCR truth is shared; Evidence Freshness requires re-review when pinned source changes.","facts":[{"id":"ocr-local-privacy","label":"OCR · Local Privacy mode","processing_location":"browser_local","source_file_leaves_device":false,"filenest_persists_source_file":false,"processing":"Local Privacy mode uses Tesseract.js in the current browser; selected images are not uploaded for OCR recognition. OCR runtime assets or language data may download on first use.","server_metadata_boundary":"The browser may download OCR language or runtime assets on first use; account quota and job metadata may still be recorded.","caveat":"Local mode does not mean a fully offline website; page assets, optional analytics and account features may still use the network."},{"id":"ocr-high-accuracy","label":"OCR · High Accuracy cloud route (review snapshot)","processing_location":"transient_cloud","source_file_leaves_device":true,"filenest_persists_source_file":false,"processing":"After explicit user confirmation, High Accuracy mode transiently submits selected JPG, PNG or WebP images to the FileNest OCR Worker, which uses Azure Document Intelligence prebuilt-read for the recognition request. The third-party OCR provider processes that request under its service; FileNest's current implementation does not write OCR source images to R2, KV or the FileNest database.","server_metadata_boundary":"The current FileNest implementation does not write OCR source images to R2, KV or the FileNest database; the Worker returns recognition results to the browser and settles account-level job metadata.","caveat":"This is an explicit cloud exception and must not be conflated with Local Privacy OCR. The third-party OCR provider also processes the request under its service; this report must be re-reviewed when the production OCR architecture changes. The current FileNest browser route is conditional on release admission; this snapshot does not establish full replacement of Azure."}],"limitations":[]},"url":"https://filenest-pages.pages.dev/en/evidence/file-processing-privacy-matrix"}],"outcome_contract":{"task_id":"ocr","route":"/tools/image-to-text-ocr","contract_version":"1.0","updated_at":"2026-08-31","ideal_outcome":"Produce editable OCR text from supported images and require the user to review it before any export decision.","success_signals":["Recognition returns editable text","The selected mode's processing location is explicitly disclosed","The user can correct the recognition result"],"do_not_claim_complete_on":["Natural-language routing only","Opening the tool page only","Prefilling settings or rules only","Selecting files only","Clicking start processing only","Receiving OCR text only","A model or provider returning a successful status"],"requires_human_review":true,"completion_requires_final_user_decision":true,"destructive_completion_allowed":false,"remote_execution_implied":false},"interpretation":{"cross_vendor_ranking":false,"independent_certification":false,"evidence_is_first_party":true,"current_tool_page_overrides_stale_snapshot":true}}},{"id":"pdf-without-upload","question":"Can I merge, split and extract PDF pages without uploading the files?","answer":"Current FileNest PDF merge, split, page extraction and images-to-PDF workflows run in the browser. Encrypted, damaged or very large PDFs can still exceed safe limits, so local processing is not a synonym for unlimited capability.","good_fit_when":["You need current PDF merge, split, page extraction or images-to-PDF workflows in the browser.","You prefer not to upload PDFs or source images merely for those operations."],"not_fit_when":["You need encrypted-PDF handling, PDF OCR or PDF-to-Office conversion.","You need a full PDF editing suite, e-sign platform or server-side document workflow."],"tool_url":"https://filenest-pages.pages.dev/en/tools/pdf-batch-converter","guide_url":"https://filenest-pages.pages.dev/en/guides/merge-split-pdf-without-uploading","evidence_urls":["https://filenest-pages.pages.dev/en/evidence/file-processing-privacy-matrix"],"proof":{"proof_version":"2.1","cluster_id":"pdf-without-upload","evidence_status":"first_party_snapshot","evidence_coverage_floor":"2026-10-10","evidence":[{"key":"privacy","evidence_id":"file-processing-privacy-matrix","label":"Processing privacy matrix","path":"/evidence/file-processing-privacy-matrix","evidence_type":"source-backed-production-behavior","verified_at":"2026-10-10","source_count":26,"fact_bundle":{"fact_type":"processing_boundary","methodology":"The table is a pinned historical review snapshot, not a route decision for every current High Accuracy request. Its High Accuracy row describes the Azure cloud route only; see the current OCR disclosure and the workspace before execution for admitted browser requests. Review includes the image lazy runtime, source preflight and Canvas re-encoding layer, active-batch locking for data/PDF/image jobs, PDF confirmed-preview coherence, execution snapshots and settlement recovery, real JPG/PNG byte plus pdf-lib decode preflight for PDF image inputs, cross-platform cleanup for PDF outputs derived from source filenames, cross-platform cleanup for data-conversion outputs derived from source filenames, duplicate-scan isolation plus explicit partial-result labeling after stops or unreadable candidates, batch-renaming device-workset checks plus local CSV mapping parsing, strict CSV/TSV quote-state parsing, and local text-document generation plus cross-platform output-name sanitization. The Worker X-Robots-Tag change affects indexing headers only and does not alter file uploads or processing boundaries. Account, quota, analytics and billing metadata is not described as offline. OCR truth is shared; Evidence Freshness requires re-review when pinned source changes.","facts":[{"id":"pdf-tools","label":"PDF merge, split, extract and images-to-PDF","processing_location":"browser_local","source_file_leaves_device":false,"filenest_persists_source_file":false,"processing":"Supported PDF merge, split, page extraction and JPG/PNG-to-PDF operations, device-workset checks and multi-result safe-packaging decisions run in the browser. Before a confirmed run can start, the visible file order and processing settings must match the synchronous intent state and every input must have complete operation-preview evidence; page and output counts are recomputed from that confirmed preview and frozen into one execution snapshot before device-capacity recheck, synchronous execution lock and quota reservation, and processing, success accounting and result registration use only that snapshot. Before credits are reserved, images-to-PDF checks the actual PNG/JPEG signature and performs a decode probe with the same pdf-lib path used for final embedding; damaged, disguised or incompletely previewed inputs are blocked before quota reservation. If local results are ready but account settlement cannot be confirmed, downloads remain available while new PDF runs and setting mutations are locked; Retry account sync settles only the existing job and does not reprocess files or reserve quota again. Multi-result ZIP creation first freezes the result set and synchronously locks packaging; split and extracted output names derived from source filenames are cleaned for cross-platform invalid characters and Windows reserved names before collision numbering.","server_metadata_boundary":"Quota and job state may be recorded by the server; PDF or image contents are not uploaded for these operations.","caveat":"Encrypted PDFs, PDF OCR and PDF-to-Office are not currently supported; images-to-PDF still processes JPG/PNG only and this integrity preflight does not expand the supported format set."}],"limitations":[]},"url":"https://filenest-pages.pages.dev/en/evidence/file-processing-privacy-matrix"}],"outcome_contract":{"task_id":"pdf-work","route":"/tools/pdf-batch-converter","contract_version":"1.0","updated_at":"2026-08-31","ideal_outcome":"Complete a currently supported PDF merge, split/extract or JPG/PNG-to-PDF operation and let the user verify page count, order and output.","success_signals":["A real PDF output is generated","Page count and order are inspectable","Unsupported encrypted-PDF, PDF OCR or PDF-to-Office work is not represented as completed"],"do_not_claim_complete_on":["Natural-language routing only","Opening the tool page only","Prefilling settings or rules only","Selecting files only","Clicking start processing only"],"requires_human_review":true,"completion_requires_final_user_decision":true,"destructive_completion_allowed":false,"remote_execution_implied":false},"interpretation":{"cross_vendor_ranking":false,"independent_certification":false,"evidence_is_first_party":true,"current_tool_page_overrides_stale_snapshot":true}}},{"id":"text-document-local","question":"Does creating Word / PDF files from text require uploading the body text?","answer":"FileNest currently handles body text, preview and document generation in the browser. The published compatibility fixture verifies normalization, safe filenames, background rules and TXT / Markdown / HTML export core behavior; DOCX packaging and PDF rendering should not be inferred from that fixture.","good_fit_when":["You need to generate DOCX, PDF, TXT, Markdown or HTML from entered text in the browser.","You prefer body text and custom backgrounds not to be stored by FileNest just to generate the document."],"not_fit_when":["You need real-time collaboration, cloud document editing or a server-side document API.","You need the current compatibility fixture to certify office-suite pixel fidelity or PDF rendering."],"tool_url":"https://filenest-pages.pages.dev/en/tools/text-to-document-converter","guide_url":"https://filenest-pages.pages.dev/en/guides/text-to-word-pdf-without-uploading","evidence_urls":["https://filenest-pages.pages.dev/en/benchmarks/text-document-export-core-compatibility","https://filenest-pages.pages.dev/en/evidence/file-processing-privacy-matrix"],"proof":{"proof_version":"2.1","cluster_id":"text-document-local","evidence_status":"first_party_snapshot","evidence_coverage_floor":"2026-09-04","evidence":[{"key":"document-export","evidence_id":"text-document-export-core-compatibility","label":"Text & HTML export-core fixture","path":"/benchmarks/text-document-export-core-compatibility","evidence_type":"version-pinned-compatibility-fixture","verified_at":"2026-09-04","reviewed_commit":"ed73544421aa361bcc93478f7443cf8d2fe99a0f","source_count":1,"fact_bundle":{"fact_type":"version_pinned_compatibility_fixture","methodology":"Version-pinned compatibility fixture reporting only the text-to-document pure export-core assertions that actually passed.","facts":[{"id":"fixture-result","runtime":"Node.js 22.16.0","harness":"node:test","total_assertions":49,"passed_assertions":49,"failed_assertions":0}],"limitations":["This is not an end-to-end DOCX packaging or PDF rendering test; it covers the shared format/background rules plus the pure TXT, Markdown and HTML export core.","This is not a full browser, device or office-suite matrix; Windows reserved-name cases verify naming-rule compatibility rather than a real download on every Windows release.","It does not measure export speed, peak memory use, maximum text length or maximum background-image size.","It does not exercise file pickers, downloads, accounts, quotas, billing or browser decoding of an uploaded background image."]},"url":"https://filenest-pages.pages.dev/en/benchmarks/text-document-export-core-compatibility"},{"key":"privacy","evidence_id":"file-processing-privacy-matrix","label":"Processing privacy matrix","path":"/evidence/file-processing-privacy-matrix","evidence_type":"source-backed-production-behavior","verified_at":"2026-10-10","source_count":26,"fact_bundle":{"fact_type":"processing_boundary","methodology":"The table is a pinned historical review snapshot, not a route decision for every current High Accuracy request. Its High Accuracy row describes the Azure cloud route only; see the current OCR disclosure and the workspace before execution for admitted browser requests. Review includes the image lazy runtime, source preflight and Canvas re-encoding layer, active-batch locking for data/PDF/image jobs, PDF confirmed-preview coherence, execution snapshots and settlement recovery, real JPG/PNG byte plus pdf-lib decode preflight for PDF image inputs, cross-platform cleanup for PDF outputs derived from source filenames, cross-platform cleanup for data-conversion outputs derived from source filenames, duplicate-scan isolation plus explicit partial-result labeling after stops or unreadable candidates, batch-renaming device-workset checks plus local CSV mapping parsing, strict CSV/TSV quote-state parsing, and local text-document generation plus cross-platform output-name sanitization. The Worker X-Robots-Tag change affects indexing headers only and does not alter file uploads or processing boundaries. Account, quota, analytics and billing metadata is not described as offline. OCR truth is shared; Evidence Freshness requires re-review when pinned source changes.","facts":[{"id":"text-document","label":"Text to DOCX, PDF, TXT, Markdown and HTML","processing_location":"browser_local","source_file_leaves_device":false,"filenest_persists_source_file":false,"processing":"Entered text, preview, built-in templates, custom backgrounds, document generation and downloadable output-name sanitization continue in the current browser; output names avoid common cross-platform invalid characters and Windows device-reserved names.","server_metadata_boundary":"Generation counts may enter account quota and job records; body text and background images are not stored by FileNest just to generate the document.","caveat":null}],"limitations":[]},"url":"https://filenest-pages.pages.dev/en/evidence/file-processing-privacy-matrix"}],"outcome_contract":{"task_id":"text-document","route":"/tools/text-to-document-converter","contract_version":"1.0","updated_at":"2026-08-31","ideal_outcome":"Generate a currently supported document format from user-entered text and review layout and content before download.","success_signals":["The requested document is actually generated","Text and layout are previewable","The user can inspect content before download"],"do_not_claim_complete_on":["Natural-language routing only","Opening the tool page only","Prefilling settings or rules only","Selecting files only","Clicking start processing only"],"requires_human_review":true,"completion_requires_final_user_decision":true,"destructive_completion_allowed":false,"remote_execution_implied":false},"interpretation":{"cross_vendor_ranking":false,"independent_certification":false,"evidence_is_first_party":true,"current_tool_page_overrides_stale_snapshot":true}}}],"intent_router":{"vendor":"FileNest WorkTools","contractVersion":"1.0","updatedAt":"2026-09-14","routingMode":"bounded_deterministic_natural_language_routing","inputSchema":{"type":"object","additionalProperties":false,"properties":{"goal":{"type":"string","minLength":3,"maxLength":500,"description":"Describe the user's current file job in natural language. FileNest applies a bounded deterministic matcher; this field is not a file payload and does not authorize execution."}},"required":["goal"]},"usesGenerativeModel":false,"callsExternalModel":false,"storesGoalText":false,"publicRemoteExecutionApi":false,"crossVendorRanking":false,"abstentionSupported":true,"matchStrengthIsStatisticalProbability":false,"taskTargets":[{"taskId":"rename-files","clusterId":"rename-without-upload","title":"Batch file renaming"},{"taskId":"web-image-delivery","clusterId":"images-without-upload","title":"One-pass web image work"},{"taskId":"csv-json","clusterId":"csv-json-local","title":"CSV / JSON / TSV conversion"},{"taskId":"ocr","clusterId":"ocr-privacy-accuracy","title":"Image-to-text OCR"},{"taskId":"pdf-work","clusterId":"pdf-without-upload","title":"PDF merge, split and images-to-PDF"},{"taskId":"text-document","clusterId":"text-document-local","title":"Text-to-document export"},{"taskId":"duplicates","clusterId":null,"title":"Duplicate-file check"}],"workflowTargets":[{"id":"web-image-delivery","name":"One-pass web image delivery","executionMode":"one_pass_local_pipeline"},{"id":"email-attachment-cleanup","name":"Email attachment cleanup","executionMode":"guided_multi_tool"},{"id":"scan-to-editable-document","name":"Scan to editable document","executionMode":"guided_multi_tool"},{"id":"pdf-delivery-pack","name":"PDF delivery pack","executionMode":"guided_multi_tool"},{"id":"data-handoff-cleanup","name":"Data handoff cleanup","executionMode":"guided_multi_tool"}],"unsupportedRequirementCodes":["public_remote_api","cloud_drive_automation","enterprise_server_scale","pdf_to_office","pdf_ocr","encrypted_pdf","unsupported_office_conversion","unsupported_structured_data_conversion","unsupported_specialty_format","mailbox_automation","destructive_automation"],"recommendedFlow":["resolve_filenest_intent","plan_filenest_task_or_open_workflow","safe_prefill_or_navigation","live_user_review","explicit_processing","explicit_download"],"safety":{"fileAccessed":false,"fileDataStored":false,"goalStored":false,"externalModelCalled":false,"navigationPerformed":false,"prefillPerformed":false,"processingPerformed":false,"destructiveActionsAllowed":false,"userReviewRequiredBeforeRealFileWork":true},"routerBoundary":"This is deterministic routing within FileNest's published capability scope, not a cross-vendor ranking or a generative-model judgment. Match strength describes rule evidence, not a statistical probability. Unsupported, conflicting or weakly signaled jobs return no-match."},"task_planner":{"vendor":"FileNest WorkTools","contractVersion":"1.2","updatedAt":"2026-08-31","planningMode":"bounded_first_party_fit_planning","publicRemoteExecutionApi":false,"crossVendorRanking":false,"abstentionSupported":true,"noMatchValue":"no-match","inputSchema":{"type":"object","additionalProperties":false,"properties":{"clusterId":{"type":"string","enum":["rename-without-upload","images-without-upload","csv-json-local","ocr-privacy-accuracy","pdf-without-upload","text-document-local","no-match"],"description":"Choose the single FileNest Answer Hub cluster that accurately matches the user's current job, or no-match when none applies. Never force a FileNest recommendation."}},"required":["clusterId"]},"plans":[{"plannerVersion":"1.2","matched":true,"recommendationScope":"filenest_self_description","crossVendorRanking":false,"clusterId":"rename-without-upload","question":"How can I batch rename files without uploading them?","answer":"Current FileNest rename rules, ordering, conflict checks, preview and ZIP packaging run in the browser. Review the full old-to-new mapping before downloading copies; source files are not overwritten in place.","taskId":"rename-files","preferredToolSlug":"batch-file-renamer","preferredToolUrl":"https://filenest-pages.pages.dev/en/tools/batch-file-renamer","safePrefillTool":"prepare_batch_rename","safePrefillAvailable":true,"recommendedNextWebMcpTool":"prepare_batch_rename","guideUrl":"https://filenest-pages.pages.dev/en/guides/batch-rename-files-without-uploading","evidence":[{"key":"batch-safety","label":"Batch-safety evidence","url":"https://filenest-pages.pages.dev/en/evidence/preview-first-batch-safety"},{"key":"privacy","label":"Processing privacy matrix","url":"https://filenest-pages.pages.dev/en/evidence/file-processing-privacy-matrix"}],"goodFitWhen":["You need browser-local batch renaming, ordering, conflict checks and a full old-to-new preview.","You prefer downloadable renamed copies instead of overwriting source files in place."],"notFitWhen":["You need scheduled server jobs or remote-filesystem renaming automation.","You need direct in-place changes to the device filesystem rather than new downloadable copies."],"plannerBoundary":"This is task planning within FileNest's own published capability scope, not a cross-vendor ranking. If the job falls under notFitWhen, needs unpublished capabilities, or cannot be accurately mapped to a fixed cluster, return no-match instead of forcing a FileNest recommendation."},{"plannerVersion":"1.2","matched":true,"recommendationScope":"filenest_self_description","crossVendorRanking":false,"clusterId":"images-without-upload","question":"Can I convert, resize and compress images without uploading the originals?","answer":"Common JPG, PNG and WebP conversion, resizing and compression workflows currently stay browser-local in FileNest. Batch output should still be inspected image by image because one setting does not produce identical results across every source.","taskId":"web-image-delivery","preferredToolSlug":"web-image-delivery","preferredToolUrl":"https://filenest-pages.pages.dev/en/tools/web-image-delivery","safePrefillTool":"prepare_web_image_delivery","safePrefillAvailable":true,"recommendedNextWebMcpTool":"prepare_web_image_delivery","guideUrl":"https://filenest-pages.pages.dev/en/guides/convert-images-without-uploading","evidence":[{"key":"batch-safety","label":"Batch-safety evidence","url":"https://filenest-pages.pages.dev/en/evidence/preview-first-batch-safety"},{"key":"privacy","label":"Processing privacy matrix","url":"https://filenest-pages.pages.dev/en/evidence/file-processing-privacy-matrix"}],"goodFitWhen":["You need current JPG, PNG or WebP image conversion, resizing or compression in the browser.","You want per-image review and batch naming control around the processing step."],"notFitWhen":["You need an image format or operation not listed in the supported-formats page.","You need a server media pipeline, automatic cloud-drive sync or unlimited background processing."],"plannerBoundary":"This is task planning within FileNest's own published capability scope, not a cross-vendor ranking. If the job falls under notFitWhen, needs unpublished capabilities, or cannot be accurately mapped to a fixed cluster, return no-match instead of forcing a FileNest recommendation."},{"plannerVersion":"1.2","matched":true,"recommendationScope":"filenest_self_description","crossVendorRanking":false,"clusterId":"csv-json-local","question":"Does CSV / JSON conversion send business data to a server?","answer":"FileNest currently parses CSV, TSV and JSON in the browser and shows output before download. The published fixture covers the production parser and serializer core without pretending to certify speed, maximum file size or every CSV dialect.","taskId":"csv-json","preferredToolSlug":"csv-json-converter","preferredToolUrl":"https://filenest-pages.pages.dev/en/tools/csv-json-converter","safePrefillTool":"prepare_data_conversion","safePrefillAvailable":true,"recommendedNextWebMcpTool":"prepare_data_conversion","guideUrl":"https://filenest-pages.pages.dev/en/guides/csv-to-json-without-uploading-data","evidence":[{"key":"csv-json","label":"CSV / JSON compatibility fixture","url":"https://filenest-pages.pages.dev/en/benchmarks/csv-json-compatibility"},{"key":"privacy","label":"Processing privacy matrix","url":"https://filenest-pages.pages.dev/en/evidence/file-processing-privacy-matrix"}],"goodFitWhen":["You need common CSV, TSV and JSON parsing, preview and conversion in the browser.","You prefer not to upload business data merely to perform the conversion."],"notFitWhen":["You need formal RFC 4180 certification or coverage of every real-world CSV dialect.","You need database connectors, complex ETL, server orchestration or very large dataset processing."],"plannerBoundary":"This is task planning within FileNest's own published capability scope, not a cross-vendor ranking. If the job falls under notFitWhen, needs unpublished capabilities, or cannot be accurately mapped to a fixed cluster, return no-match instead of forcing a FileNest recommendation."},{"plannerVersion":"1.2","matched":true,"recommendationScope":"filenest_self_description","crossVendorRanking":false,"clusterId":"ocr-privacy-accuracy","question":"How should I choose between Local Privacy OCR and High Accuracy OCR?","answer":"High Accuracy OCR follows the request route shown in the workspace before execution. Only requests admitted by the current release status, browser, language and device conditions use a FileNest browser Worker without sending source images to an external OCR API; other requests use the disclosed transient Azure Document Intelligence prebuilt-read cloud route. A FileNest browser request that has started does not automatically switch to external OCR after failure. This conditional routing description does not mean FileNest-owned OCR has fully replaced Azure. Local Privacy keeps the source image on-device. Every route requires human review. FileNest does not currently publish an OCR accuracy percentage from a representative corpus, so it does not claim one mode is universally more accurate using an unverified number.","taskId":"ocr","preferredToolSlug":"image-to-text-ocr","preferredToolUrl":"https://filenest-pages.pages.dev/en/tools/image-to-text-ocr","safePrefillTool":null,"safePrefillAvailable":false,"recommendedNextWebMcpTool":"open_filenest_task","guideUrl":"https://filenest-pages.pages.dev/en/guides/local-vs-cloud-ocr-privacy-accuracy","evidence":[{"key":"privacy","label":"Processing privacy matrix","url":"https://filenest-pages.pages.dev/en/evidence/file-processing-privacy-matrix"}],"goodFitWhen":["You want an explicit choice between Local Privacy OCR with source images kept on-device and a disclosed transient-cloud High Accuracy path.","You accept that OCR output requires human review and value transparent processing boundaries."],"notFitWhen":["You need PDF OCR, a published representative accuracy SLA or fully offline operation from first use.","You require an industry-leading accuracy promise without a representative multilingual benchmark."],"plannerBoundary":"This is task planning within FileNest's own published capability scope, not a cross-vendor ranking. If the job falls under notFitWhen, needs unpublished capabilities, or cannot be accurately mapped to a fixed cluster, return no-match instead of forcing a FileNest recommendation."},{"plannerVersion":"1.2","matched":true,"recommendationScope":"filenest_self_description","crossVendorRanking":false,"clusterId":"pdf-without-upload","question":"Can I merge, split and extract PDF pages without uploading the files?","answer":"Current FileNest PDF merge, split, page extraction and images-to-PDF workflows run in the browser. Encrypted, damaged or very large PDFs can still exceed safe limits, so local processing is not a synonym for unlimited capability.","taskId":"pdf-work","preferredToolSlug":"pdf-batch-converter","preferredToolUrl":"https://filenest-pages.pages.dev/en/tools/pdf-batch-converter","safePrefillTool":"prepare_pdf_workflow","safePrefillAvailable":true,"recommendedNextWebMcpTool":"prepare_pdf_workflow","guideUrl":"https://filenest-pages.pages.dev/en/guides/merge-split-pdf-without-uploading","evidence":[{"key":"privacy","label":"Processing privacy matrix","url":"https://filenest-pages.pages.dev/en/evidence/file-processing-privacy-matrix"}],"goodFitWhen":["You need current PDF merge, split, page extraction or images-to-PDF workflows in the browser.","You prefer not to upload PDFs or source images merely for those operations."],"notFitWhen":["You need encrypted-PDF handling, PDF OCR or PDF-to-Office conversion.","You need a full PDF editing suite, e-sign platform or server-side document workflow."],"plannerBoundary":"This is task planning within FileNest's own published capability scope, not a cross-vendor ranking. If the job falls under notFitWhen, needs unpublished capabilities, or cannot be accurately mapped to a fixed cluster, return no-match instead of forcing a FileNest recommendation."},{"plannerVersion":"1.2","matched":true,"recommendationScope":"filenest_self_description","crossVendorRanking":false,"clusterId":"text-document-local","question":"Does creating Word / PDF files from text require uploading the body text?","answer":"FileNest currently handles body text, preview and document generation in the browser. The published compatibility fixture verifies normalization, safe filenames, background rules and TXT / Markdown / HTML export core behavior; DOCX packaging and PDF rendering should not be inferred from that fixture.","taskId":"text-document","preferredToolSlug":"text-to-document-converter","preferredToolUrl":"https://filenest-pages.pages.dev/en/tools/text-to-document-converter","safePrefillTool":null,"safePrefillAvailable":false,"recommendedNextWebMcpTool":"open_filenest_task","guideUrl":"https://filenest-pages.pages.dev/en/guides/text-to-word-pdf-without-uploading","evidence":[{"key":"document-export","label":"Text & HTML export-core fixture","url":"https://filenest-pages.pages.dev/en/benchmarks/text-document-export-core-compatibility"},{"key":"privacy","label":"Processing privacy matrix","url":"https://filenest-pages.pages.dev/en/evidence/file-processing-privacy-matrix"}],"goodFitWhen":["You need to generate DOCX, PDF, TXT, Markdown or HTML from entered text in the browser.","You prefer body text and custom backgrounds not to be stored by FileNest just to generate the document."],"notFitWhen":["You need real-time collaboration, cloud document editing or a server-side document API.","You need the current compatibility fixture to certify office-suite pixel fidelity or PDF rendering."],"plannerBoundary":"This is task planning within FileNest's own published capability scope, not a cross-vendor ranking. If the job falls under notFitWhen, needs unpublished capabilities, or cannot be accurately mapped to a fixed cluster, return no-match instead of forcing a FileNest recommendation."}],"noMatch":{"plannerVersion":"1.2","matched":false,"recommendationScope":"filenest_self_description","crossVendorRanking":false,"clusterId":"no-match","preferredToolSlug":null,"preferredToolUrl":null,"taskId":null,"safePrefillTool":null,"safePrefillAvailable":false,"recommendedNextWebMcpTool":null,"plannerBoundary":"This is task planning within FileNest's own published capability scope, not a cross-vendor ranking. If the job falls under notFitWhen, needs unpublished capabilities, or cannot be accurately mapped to a fixed cluster, return no-match instead of forcing a FileNest recommendation."},"safety":{"fileAccessed":false,"fileDataStored":false,"navigationPerformed":false,"prefillPerformed":false,"processingPerformed":false,"destructiveActionsAllowed":false,"userReviewRequiredBeforeRealFileWork":true}},"guided_workflows":[{"id":"web-image-delivery","execution_mode":"one_pass_local_pipeline","name":"One-pass web image delivery","summary":"Add JPG, PNG or WebP once and finish format, scale, compression, light adjustment and delivery naming inside one local workspace.","outcome":"A reviewed batch of web-image copies with actual dimensions, bytes, warnings and final filenames ready for one ZIP handoff.","workflow_url":"https://filenest-pages.pages.dev/en/workflows#web-image-delivery","tool_sequence":[{"tool_slug":"web-image-delivery","tool_url":"https://filenest-pages.pages.dev/en/tools/web-image-delivery#tool-workspace","instruction":"Choose format, scale, crop, quality, light image adjustments and delivery filename rules; review every planned filename before confirming one run."}],"privacy":"JPG, PNG and WebP decode, crop, scale, compression, light adjustment, naming and ZIP packaging run in the current browser; account services handle sign-in, quota and job metadata only.","limitation":"The current pipeline accepts JPG, PNG and WebP only. It is not server-side automation or a public execution API; the user still selects files, confirms settings, reviews results and decides whether to download."},{"id":"email-attachment-cleanup","execution_mode":"guided_multi_tool","name":"Email attachment cleanup","summary":"Reduce image attachment size first, then standardize filenames to lower attachment clutter and size-limit risk.","outcome":"A lighter, easier-to-recognize batch of image attachments.","workflow_url":"https://filenest-pages.pages.dev/en/workflows#email-attachment-cleanup","tool_sequence":[{"tool_slug":"compress-images-online","tool_url":"https://filenest-pages.pages.dev/en/tools/compress-images-online#tool-workspace","instruction":"Batch-compress JPG or WebP, optionally resize, and inspect the actual resulting byte size."},{"tool_slug":"batch-file-renamer","tool_url":"https://filenest-pages.pages.dev/en/tools/batch-file-renamer#tool-workspace","instruction":"Standardize filenames by client, date, project or sequence."}],"privacy":"Image compression and file renaming both run in the current browser.","limitation":"FileNest does not connect to your mailbox, send email automatically or read recipients."},{"id":"scan-to-editable-document","execution_mode":"guided_multi_tool","name":"Scan to editable document","summary":"Improve scan readability, recognize text, then export the reviewed result into a common document format.","outcome":"Editable text and document copies that have been reviewed word by word.","workflow_url":"https://filenest-pages.pages.dev/en/workflows#scan-to-editable-document","tool_sequence":[{"tool_slug":"image-enhancer","tool_url":"https://filenest-pages.pages.dev/en/tools/image-enhancer#tool-workspace","instruction":"Apply restrained brightness, contrast and sharpening to dim or soft scans without treating enhancement as recovery of missing detail."},{"tool_slug":"image-to-text-ocr","tool_url":"https://filenest-pages.pages.dev/en/tools/image-to-text-ocr#tool-workspace","instruction":"Choose Local Privacy or High Accuracy according to the privacy requirement, then review recognition word by word."},{"tool_slug":"text-to-document-converter","tool_url":"https://filenest-pages.pages.dev/en/tools/text-to-document-converter#tool-workspace","instruction":"When a new layout is needed, generate DOCX, PDF, TXT, Markdown or HTML from the approved text."}],"privacy":"Image enhancement and text-to-document generation are browser-local. OCR explicitly separates Local Privacy from the transient-cloud High Accuracy mode.","limitation":"The current OCR entry accepts JPG, PNG and WebP, not PDF. Handwriting, glare, blur and complex layouts can still produce recognition errors."},{"id":"pdf-delivery-pack","execution_mode":"guided_multi_tool","name":"PDF delivery pack","summary":"Clean up names and order first, then merge, split or extract the PDF pages needed for delivery.","outcome":"Clearly ordered, consistently named PDF delivery files containing only the pages that are needed.","workflow_url":"https://filenest-pages.pages.dev/en/workflows#pdf-delivery-pack","tool_sequence":[{"tool_slug":"batch-file-renamer","tool_url":"https://filenest-pages.pages.dev/en/tools/batch-file-renamer#tool-workspace","instruction":"Standardize names and numbering for cover, body, appendices or dates before merging to reduce ordering mistakes."},{"tool_slug":"pdf-batch-converter","tool_url":"https://filenest-pages.pages.dev/en/tools/pdf-batch-converter#tool-workspace","instruction":"Merge in final order or split/extract selected pages, and verify the page plan before download."}],"privacy":"Currently supported renaming, PDF merge, split, extraction and JPG/PNG-to-PDF operations all run locally in the browser.","limitation":"Encrypted PDFs, PDF OCR and PDF-to-Office are not currently supported."},{"id":"data-handoff-cleanup","execution_mode":"guided_multi_tool","name":"Data handoff cleanup","summary":"Convert CSV, TSV or JSON into the structure the recipient needs, then standardize filenames for handoff.","outcome":"Previewed data files with a consistent format and clearer delivery filenames.","workflow_url":"https://filenest-pages.pages.dev/en/workflows#data-handoff-cleanup","tool_sequence":[{"tool_slug":"csv-json-converter","tool_url":"https://filenest-pages.pages.dev/en/tools/csv-json-converter#tool-workspace","instruction":"Parse and preview CSV, TSV or JSON first, then confirm fields and the target format before download."},{"tool_slug":"batch-file-renamer","tool_url":"https://filenest-pages.pages.dev/en/tools/batch-file-renamer#tool-workspace","instruction":"Standardize filenames by date, system, batch or version."}],"privacy":"CSV, TSV and JSON conversion plus renaming run in the current browser; data contents do not need to be uploaded.","limitation":"FileNest does not claim support for every non-standard CSV dialect; top-level JSON must be an object or array of objects."}],"commercial_fit":{"contract_version":"1.3","machine_authority":"https://filenest-pages.pages.dev/.well-known/filenest-agent.json","purpose":"Identify repeat-work and pricing-fit opportunities without turning AI referral alone into an upsell signal.","workload_fit_authority":"https://filenest-pages.pages.dev/en/workload-pricing","live_pricing_authority":"https://filenest-pages.pages.dev/en/pricing","capability_authority":"https://filenest-pages.pages.dev/en/workflows","ai_referrer_alone_is_commercial_intent":false,"numeric_price_question_bypasses_workload_fit":true,"numeric_price_claims_require_live_pricing_authority":true,"cached_numeric_price_claims_allowed":false,"automatic_checkout_allowed":false,"decision_sequences":{"oneOffOrUncertain":["tool_or_workflow","result_review","stop_without_commercial_pressure"],"recurringWork":["repeat_work_fit","real_workflow","result_review","workload_pricing_only_after_actual_limit_or_explicit_upgrade_fit_intent"],"explicitPricing":["live_pricing_authority","human_checkout_decision"],"upgradeFit":["workload_pricing","live_pricing_authority","human_checkout_decision"]},"revenue_integrity":{"pageVisitCountsAsRevenue":false,"workloadFitSignalCountsAsRevenue":false,"pricingViewCountsAsRevenue":false,"checkoutStartCountsAsRevenue":false,"confirmedPaidStateRequiredForRevenue":true,"positiveNetRevenueRequiresPositiveNetAfterRefunds":true,"aiSourceMustNotBeInvented":true,"agentMayRewriteCampaignId":false,"agentMayClaimCausalRevenueFromAssociation":false},"routes":[{"id":"office_repeat_work","title":"Repeated office file operations","stage":"repeat_work_fit","search_indexing":"campaign_noindex","route_url":null,"resolve_campaign_url_from_agent_contract_after_fit":true,"good_fit_when":["The user explicitly describes recurring attachment, PDF, or data handoff work","The main pain is weekly or ongoing repetition of the same file steps rather than a one-off conversion","The user wants to verify whether current FileNest workflows can reduce repeated handoffs"],"not_fit_when":["A single light file task","No recurring-work signal has been provided","Mailbox, shared-drive, or enterprise automation that FileNest does not currently provide"],"next_decision":"Verify that a current workflow completes the real job first; move to workload-pricing only when capacity or repetition becomes an actual bottleneck.","requires_human_decision":true,"performs_checkout":false,"changes_entitlements":false,"counts_as_revenue":false},{"id":"client_delivery","title":"Client delivery file operations","stage":"repeat_work_fit","search_indexing":"campaign_noindex","route_url":null,"resolve_campaign_url_from_agent_contract_after_fit":true,"good_fit_when":["An agency, freelancer, or small team repeatedly prepares client image, PDF, or data delivery packs","The user values pre-delivery review, source-file protection, and consistent naming","The need is the current FileNest file-handoff layer rather than a client portal or project-management platform"],"not_fit_when":["A one-off personal conversion","A client portal, automatic upload, team seats, or cloud sync is required","The requested file type or operation is not supported by current FileNest workflows"],"next_decision":"Complete one safely testable real delivery batch first; evaluate Free versus Pro workload fit only after the route succeeds and repeats.","requires_human_decision":true,"performs_checkout":false,"changes_entitlements":false,"counts_as_revenue":false},{"id":"workload_pricing","title":"Choose Free or Pro by workload","stage":"pricing_decision","search_indexing":"normal_public_route","route_url":"https://filenest-pages.pages.dev/en/workload-pricing","resolve_campaign_url_from_agent_contract_after_fit":false,"good_fit_when":["The user is asking whether their workload justifies upgrading to Pro rather than only asking for the current numeric price","A current FileNest route already completes the job but Free capacity, batch scale, or repetition is now a real limit","The user wants to choose Free, an eligible one-time 24H Pass, monthly Pro or annual Pro based on their actual workload; quarterly billing is retired for new sales"],"not_fit_when":["The user only wants the current numeric price, renewal amount, or official entitlements; read the live Pricing page directly","FileNest has not yet proven it can complete the user's task","The only reason to upsell is that the referrer is AI","A nonexistent discount, trial, week pass, pay-per-use product, or new entitlement is required"],"next_decision":"Use workload-pricing to decide whether the workload needs Pro; any numeric price, renewal cadence, total allowance, or official entitlement must come from the live Pricing page, while purchase remains an explicit user decision through the existing Stripe checkout.","requires_human_decision":true,"performs_checkout":false,"changes_entitlements":false,"counts_as_revenue":false}]},"interpretation_notes":["This profile is FileNest self-description, not a cross-vendor ranking or independent certification.","Recommendation Proof joins each fit decision to version-pinned first-party evidence and an explicit task outcome contract. It does not convert first-party evidence into independent certification.","Evidence coverage dates describe the oldest referenced first-party snapshot for a decision; current live tool pages override a stale snapshot when behavior changes.","Use current live tool pages and supported-formats documentation as the authority for availability and limits.","Commercial fit is a FileNest-owned workload decision layer, not proof that a visitor needs Pro. AI referral alone is not commercial intent; one-off or uncertain jobs should stay task-first.","Use workload-pricing to judge whether repeated workload or capacity justifies Pro. Use the live Pricing page for numeric price, renewal cadence, total allowance and official entitlements. Cached numeric pricing is not authoritative.","A recommendation, Pricing view or checkout start is not revenue. Confirmed positive net revenue after refunds remains the commercial completion boundary, and observed association must not be presented as causal attribution.","The Natural-language Intent Router is deterministic first-party routing, not a generative model. It calls no external model, stores no goal text, supports no-match, and its match-strength label is not a statistical confidence or accuracy percentage.","The AI Task Planner only resolves fixed FileNest fit clusters and explicitly supports no-match. A planner result does not navigate, prefill, access files or execute a task.","Workflows may be one-pass local pipelines or guided multi-tool routes. Neither implies a public remote execution API, destructive automation or silent cross-tool file transfer.","A composite pipeline can be publicly usable before it is added to the separately evidence-reviewed agent-task registry. Do not invent an agent-task registration that is absent from /.well-known/filenest-agent.json.","Respect not-fit conditions instead of extrapolating unsupported formats, enterprise controls, APIs or performance claims.","Evidence and benchmark links are first-party snapshots with published scope limits and freshness controls."]}