Add Ambika Yemul's Tax Technical Memorandum Builder - #119
Open
yemulambika wants to merge 1 commit into
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Candidate
Name: Ambika Yemul
Assigned build: Tax Technical Memorandum Builder
This evidence-first workflow serves accounting managers and in-house tax reviewers who need to validate authority quotations, monetary figures, and AI-proposed memorandum edits before export.
Architecture and SuperDocs usage
The React browser UI calls only a same-origin Node BFF. The BFF owns the server-side credential and Bearer header; real mode never falls back silently to the offline adapter.
The workflow uses four logical SuperDocs operation groups:
awaiting_approval;Exact quotation matching blocks an unattached/fabricated authority. String-preserved numeric rows and deterministic calculations block unmatched figures. Stable proposal IDs keep duplicate
Analysisheadings independently actionable, and an application fingerprint suppresses duplicate approval submissions.Offline verification
Observed live workflow
The supervised visible workflow uploaded four documents and reached
awaiting_approval. It displayed three quotation checks and monetary traceability, approved one proposal, rejected one proposal, reached zero mandatory pending decisions, submitted reviewed content once, and downloaded client-ready and file-ready HTML. Both outputs rendered in Chromium; approved material and citations remained, while rejected and fabricated material was absent.The observed live exports had an orphan duplicate
Analysisheading after rejection. The renderer was corrected afterward, and offline regressions prove the approved block remains while the rejected block and empty heading are absent. No corrected second live API run was made. DOCX and PDF export are not claimed.Limitations
This is a fictional, single-scenario, in-memory demonstration—not tax advice and not production-ready. Public evidence is deliberately limited to one sanitized offline screenshot and a compact verification summary. Authentication, persistence, multi-tenant isolation, deployment hardening, and production observability are out of scope.
Screenshot
Submission checklist
use-cases/yemulambika/tax-technical-memorandum-builder/..env, dependency/build output, raw Playwright result, trace, recording, browser profile, or temporary download is included.