Return review

Live

A second look at every return, before you file or after.

CitedTax reads the return the way a senior technical reviewer would, then walks the Code, the regulations and the published guidance as they stand today. Every finding carries its governing authority, its fact-to-law chain, its computation, an evidence grade, and a plain statement of what you must validate before relying on it.

Create your firm account Read sample working papers

At a glance

Cost: 1 credit, 2 rush ($25 overnight, $50 rush)
You provide: the return as one PDF per client (US 1040, 1041, 1120, 1120-S, 1065; Canada T1, T2 with the Alberta AT1; United Kingdom SA100, SA800, SA900, CT600)
You receive: working papers, an engineering paper with deadlines and interactions, and a client report under your firm's name
Turnaround: overnight for 1 credit, about thirty minutes for 2

Credits never expire. A request that fails on our side returns its credits automatically.

What you get

Three things to count on.

Working papers for the reviewer

Each item names the authority with its weight (statute, regulation, ruling, court decision, guidance), quotes the operative text, shows the computation and states its evidence grade. Items the return did not establish are marked for you to confirm, and the papers end with a diligence record: what was retrieved, relied on, rejected and withheld.

Engineering paper with deadlines

Prospective structures the client can still elect, with the filing vehicle, the window that is open, and the interactions between items, including what one election blocks.

Client report under your name

You choose which findings the client sees. The report goes out white-labeled with your firm's name, colors and disclaimer; CitedTax is not mentioned unless you want it to be.

A worked example

A 2024 pass-through return, reviewed in a pilot

The papers verified the QBI computation correct as filed, surfaced an unclaimed self-employed health insurance deduction, priced an amendment the client should decline because the surtax cost exceeded every benefit, and listed two prospective structures with their election deadlines. The CPA billed the planning conversation the following week.

The premise

The return was right when it was filed. The opportunity set kept moving.

Returns are prepared under deadline, with the law as it stood and the facts on hand. Then the law moves. Public Law 119-21 alone rewrote pieces of the Code mid-year: domestic research expensing under new §174A with a retroactive catch-up for small businesses, 100 percent bonus depreciation restored, the §179 ceiling raised, the §163(j) base widened, and a dozen individual provisions with new thresholds.

Layer that over TCJA sunsets, indexed thresholds, hundreds of Revenue Procedures and Notices a year, and a letter-ruling record no one can hold in their head.

A second look is not second-guessing. It is the same discipline a firm applies in a technical review, applied to open years under §6511 and to the year ahead, by an engine that has read all of Title 26, all of 26 CFR, the Bulletin, the Manual, the rulings and the cases, and will only assert what a passage it can show you supports.

01
Open years
Amendable positions inside the refund window, each with its vehicle named: amended return, Form 3115, or a still-open election or contribution window.
02
The year in progress
Elections and contributions whose windows are still open at the run date, flagged as now-or-never where they are.
03
The years ahead
Engineering Mode: structures worth building, sequenced as moves, with the interactions and conflicts between them called out.

What you receive

Three documents per return, each written for a professional reader.

Working papers: Review Mode and Engineering Mode

Structured the way a technical-review memo is structured, with room on the page to read them; the sample on this site runs to about seventy pages because it carries fourteen engineered structures, and a simpler return runs shorter. Review Mode walks the return for deductions, credits, elections and accounting methods that were available and not taken. Engineering Mode inverts the question: what could this taxpayer legitimately build, and in what order?

Every Review finding carries, in this order

Authority. the IRC section, Treasury regulation, ruling, case or official guidance that governs, with citation key
Claim. the precise legal proposition the authority supports, no wider than the text
Fact-to-law. the conditions the authority requires, the client facts that satisfy each, and which conditions remain unproven
Plain language. two or three sentences you can read to the client, routed through you: "your CPA can" never "we will"
Why it was likely left on the table. the mechanical reason: a default method, a missed aggregation, an election window, a form the software did not prompt
Computation. base amount, marginal rate actually applicable, limits applied, and the tax-year assumptions used
Evidence grade. VERIFIED, CPA TO CONFIRM, or withheld, and why (see grades below)
CPA must validate. exactly what you have to confirm independently before relying on the item
Limitations found. phase-outs, thresholds and exclusions in the authority that bite this client
Examination note. where the position sits on the exposure spectrum and what documentation supports it

Every Engineering structure carries

governing provisions · what must be true · what must change from current facts · feasibility and rationale · the moves in sequence, each with its own authority and grade · combined impact and basis · implementation timeline · the critical dependency · disclosure flags · key risk · what you must validate. Interactions between structures are analyzed separately: conflicts (a move that forecloses another) and synergies (a move that improves another).

And what was considered and excluded. Candidates the engine walked and set aside are listed with the reason. Items withheld by the citation gate or by the return-package cross-check are listed by name. A coverage appendix lists every strategy in the engine's playbook that matches the client's profile, each with a disposition, so a known strategy cannot go missing without a trace. Totals are recomputed from the surviving items at render time and the Review and Engineering figures are never added together; the papers say so on the cover.

Client profile

A three-page structured summary of the facts the engine extracted and relied on: entity, year, filing status, income composition, schedules present, K-1 activity, states, prior positions taken. It is the negative-space map for the review and a fast way to confirm the engine read the return the way you do.

The client report, under your name

Nothing reaches a client automatically. In the curation screen you tick the items worth discussing, edit the plain-language wording in your own voice, add next steps and a cover note, and approve. The report renders with your firm's name, address and colors, in the first person, with an optional authorities appendix, and no mention of CitedTax unless you want one. Items graded CPA TO CONFIRM cannot be included until you mark them confirmed; that rule is enforced in the software, not just in the interface.

Included with every review

Five letters, written from the findings you curated. No charge.

Most of the letters a CPA wants after a review are the papers rewritten in a different voice. They are generated from the finished review on request, in Word and PDF, and they do not use a credit.

Client cover letter and "why we recommend amending" letter

Written from the findings you curated, in your firm's voice.

Read a sample

Engagement letter

Scoped to the engineered structure you selected, ready for signature.

Read a sample

Form 1040-X or 1120-X explanation statement

Cited, for any finding you confirm.

Read a sample

Client planning questionnaire

Generated from the open items in the papers, so the next meeting starts with answers.

Read a sample

"What the new law changed for you" note

One page from the items the run already flagged under the 2025 Act.

How it works

Retrieval-grounded research with a hard citation gate, not a chat window.

CitedTax is not a model asked to opine on a return. It is a pipeline in which a model may only assert what a passage of primary law, retrieved and shown to it, actually supports, and in which the return itself is the last check on every large-dollar item. The six stages:

01
Intake and de-identification
The PDF is read as filed: main form, schedules, statements, K-1s wherever they sit in the package, state returns and brokerage bulk summarized rather than dropped. Four-hundred-page bundles are routine; scanned image PDFs are OCR'd.
Before any text reaches a model, Social Security and taxpayer identification numbers, EINs, bank routing and account numbers, phone numbers and email addresses are replaced with stable placeholders, so a K-1 partner still links to the taxpayer without the number ever leaving the intake step.
The result is a structured situation file: entity type, year, filing status, income composition, prior positions taken.
02
Enumeration walk
The engine walks the return systematically rather than free-associating.
Individual returns get an individual walk (income character, above-the-line items, itemized versus standard, credits, elections, retirement and health vehicles, TCJA and P.L. 119-21 checklists keyed to the tax year).
Business entities and individuals with Schedule C or K-1 activity also run the credit-recovery walk: statutory credits and incentives in open years, accounting-method opportunities that need no amended return, entity-level elections.
Multistate filers get a multistate walk: sourcing, allocation, other-state credits, resident-state conformity. Prior-year law controls open-year amendments; current law controls prospective items.
03
Retrieval against primary and official authority
Each candidate becomes a focused legal question run against the index: the Internal Revenue Code (with post-P.L. 119-21 text vintage-labeled alongside prior-year text), all of 26 CFR, the Internal Revenue Bulletin 2020 to date, Revenue Rulings, PLRs, TAMs and CCAs, Actions on Decisions, the Internal Revenue Manual examination parts, IRS Publications and form instructions, Audit Technique Guides, JCT Blue Books from 1970 through P.L. 119-21, U.S. tax treaties with technical explanations, and the case law: Tax Court and Board of Tax Appeals opinions, the Courts of Appeals, the Court of Federal Claims and the Court of Claims, and the Supreme Court.
State stacks are added per jurisdiction. Eight are live today:
- California: Revenue and Taxation Code, Title 18 CCR, FTB Legal Rulings, Notices and Chief Counsel Rulings, FTB publications, Office of Tax Appeals opinions, Supreme Court of California and Court of Appeal decisions.
- New York: Tax Law, 20 NYCRR, TSB-M memoranda and Advisory Opinions, DTF publications, Division of Tax Appeals and Tribunal decisions, Court of Appeals and Appellate Division decisions.
- Massachusetts: M.G.L. c. 62/62B/62C, all 830 CMR 62 regulations, DOR guidance, Supreme Judicial Court and Appeals Court decisions.
- New Jersey: N.J.S.A. Title 54A and the Title 54 corporation business tax, procedure, sales and inheritance chapters, N.J.A.C. Title 18, Division Technical Bulletins, TAMs, publications and letter rulings, Tax Court, Appellate Division and Supreme Court decisions.
- Virginia: the Code of Virginia Title 58.1 in full with the Title 13.1 and Title 50 entity chapters, the 23VAC10 regulations, Virginia Tax Bulletins and the Rulings of the Tax Commissioner, Supreme Court of Virginia and Court of Appeals decisions.
- Delaware: the Delaware Code Title 30 in full with the Title 8 corporation and franchise tax chapters and the Title 6 partnership and LLC chapters, Division of Revenue Technical Information Memoranda, Tax Appeal Board opinions, Supreme Court, Chancery and Superior Court decisions.
- Florida: the Constitution's taxation article, chapters 212, 213 and 220 and the residency, homestead and assessment sections, the corporate income, sales tax and protest rules, Department publications and Technical Assistance Advisements, Supreme Court of Florida and District Courts of Appeal decisions (no personal income tax).
- Texas: Tax Code chapters 11, 111, 151 and 171, the Comptroller's chapter 3 rules and current-figure pages, Supreme Court of Texas and Court of Appeals decisions (no income tax).
The citation gate is jurisdiction-aware, so wrong-state authority is capped rather than passed.
04
Grounding and the citation gate
With the retrieved passages in front of it, the model must name the single best authority and write the fact-to-law chain. Three checks follow.
Layer one: the citation key must exist in the corpus. Layer two: the model reads the actual text of that authority and confirms it supports the specific claim as written; if not, the finding is BLOCKED and appears only in the withheld list. Layer three: the sentence it quotes as support must appear in that text; if it cannot be found, the grade drops to CPA TO CONFIRM and the quote is never printed as law text.
Secondary and procedural sources (Publications, form instructions, the Manual, JCT descriptions) can never carry a VERIFIED grade on a substantive claim; primary law is tried first and secondary support is capped at CPA TO CONFIRM with an explicit caveat. Non-precedential authority (letter rulings, CCAs, AODs) is labeled as such under §6110(k)(3).
Retrieved passage
Treas. Reg. §1.199A-1(b)(14)
Layer one
citation key exists in corpus
Layer two
text supports the claim as written Verified or Blocked
Layer three
the quoted sentence is in that text Verified or CPA to confirm
05
Engineering Mode
Run in parallel with Review Mode. A scan of candidate structures for this fact pattern, a triage for feasibility against the actual numbers, then per-structure engineering.
For each structure: the moves in order, each grounded and graded on its own authority, dependencies and deadlines named (an S election window, a plan set-up date, a Form 709 adequate-disclosure statement), and an interaction pass across structures for conflicts and synergies.
Structures that fail feasibility are reported as infeasible with the reason, not silently dropped.
06
Return-package cross-check and render
Every finding or structure above a dollar threshold is tested against the filed return itself: the pages most relevant to it are pulled and a narrow question is asked, whether the return plainly contradicts the premise (the deduction was already claimed, the asset already expensed, the assumed activity does not exist).
Contradicted items are withheld from every list and total and reported by name with the reason and page references.
Only then are the papers rendered, with totals recomputed from surviving items and the non-additive convention stated on the cover.

Two things follow from this design. First, the papers can be wrong in a way you can see: every claim is tied to a passage you can open, and every unproven condition is named.

Second, the honesty layer is structural. The engine flags where a retrieved authority shows an unindexed statutory figure rather than the current-year amount, where a position depends on facts the return does not establish, and where the best available support is secondary. It is built to be checked, because you are the check.

Evidence grades

Every item tells you how firmly the text supports it.

VERIFIED

Machine-checked against the cited statute, regulation, court decision or officially published IRS guidance: the citation exists, the text supports the claim as written, and the quoted sentence is in that text. Actionable subject to the CPA-must-validate conditions listed with it.

CPA TO CONFIRM

The analysis and the math stand as presented, but the best citation retrieved is secondary, non-precedential, or could not be machine-confirmed against the text. Not a rejection and not a statement of ineligibility. Confirm the authority and the flagged facts, then it is actionable like any verified finding.

PROCEDURAL, CONFIRMED

Administrative execution steps (filing an election, adopting a plan) supported by form instructions or procedural guidance, which is the proper authority for that kind of step.

CITATION REJECTED / WITHHELD

The supporting citation failed the text check, or the return package contradicts the premise. Shown by name in the withheld list so the sequence stays complete and nothing disappears silently. Not counted in any total.

Grades are evidence labels, not eligibility rulings. Pilot reviewers told us the older word for the amber grade, "unverified", read as "ineligible" to lay readers; it does not mean that, and the papers now say so inline.

The four steps

Upload, review, curate, send.

Nothing leaves your control. One habit turns the review into a lead engine: load the day's files before you leave, arrive to researched conversations.

01
Upload
A preparer uploads the filed return PDF into your firm workspace, one file or an overnight batch of up to twenty-five. Redaction is optional; identifiers are removed automatically. One run credit is reserved per file.
02
Overnight, or in thirty minutes
Standard runs go into the overnight batch and are ready by the next business morning, one credit each. A rush run starts immediately and takes about thirty minutes, two credits.
03
Review and curate
Read the working papers. In the curation screen, tick what the client should see, edit wording, confirm any amber items you have checked, open the cited text beside each finding, add next steps and a cover note.
04
Approve and send
The client report renders under your firm name and is stored encrypted for your retention window (90 days by default, adjustable, purge any time). Approval is recorded: who, when, what was included.

The overnight habit

Load the day's files before you leave. Arrive to researched conversations.

Every return your office touches is a client you already have. The overnight batch takes up to twenty-five of them at the end of the day, runs each one at the standard price, and by the start of the next business morning each has its working papers and a client report ready to curate.

Review Mode shows what can still be captured for the year that was filed. Engineering Mode is the part that pays for the habit: for each client it lays out the structures that fit their facts, what has to be true, and the moves in order.

If each preparer in the office queues one file before leaving, the firm starts every morning with a warm, fully researched conversation per desk. One engagement that comes out of those calls pays for a month of the habit.

Ten files a night
Ten credits. Ten researched client conversations by morning, each with its own working papers and a client report ready to curate.
Nothing waits on you
Standard runs go into the batch automatically. You get one email per file when its papers are ready. Rush is there for the file that cannot wait.
Your list, your call
Findings are framed around what the law allows now and what windows remain open. You decide what the client sees, and the report goes out under your name.

Also on the platform