Complete answers, conservative claims. For the security posture in depth, see trust and security; for plan detail, see pricing.
GAAP IQ is an AI platform for technical accounting. It answers US GAAP research questions with page-level citations to Big 4 interpretive handbooks plus FASB and SEC sources, then drafts what follows the research: audit-ready memos, footnote disclosures, Excel-ready schedules, and versioned accounting policies.
Accountants, controllers, and auditors who handle technical accounting: researching a complex transaction, documenting the conclusion in a memo, drafting the footnote, building the supporting schedule, and codifying the policy.
All seven: ResearchIQ for cited GAAP research, FilingsIQ for benchmarking SEC filings, MemoIQ for audit-ready memos, DisclosureIQ for footnote drafts, PolicyIQ for versioned accounting policies, ScheduleIQ (new) for Excel-ready schedules, and TaxIQ (beta) for federal tax research. Every plan includes all seven tools at full quality; plans differ in how much you can run, not in which tools you get.
Yes. Import an existing memo as a Word document and MemoIQ reviews it: AI edits arrive as tracked changes with Accept and Reject, never silent mutations. You can also import the .docx your auditor returned: Word comments and tracked changes are parsed and attached to the matching memo blocks, so you can send back a response copy with your edits as redlines.
No. In ScheduleIQ the AI only extracts structured inputs from your description and records anything defaulted or interpreted as an assumption for you to confirm. A deterministic engine computes every number across three schedule types: lease amortization, debt effective-interest walks, and SBC rollforwards. Every row is computed on rounded balances and final periods carry a rounding plug, so the workbook foots to the penny and an auditor recomputing any row gets the same cents.
FilingsIQ searches SEC EDGAR full text, covering filings since 2001. It reads the actual filing before citing, pulls exact reported figures straight from companies' XBRL data, extracts footnotes at inline-XBRL boundaries, and builds peer cohorts by SEC industry classification. Every answer carries numbered citations that link back to the specific filing on EDGAR.
TaxIQ, currently in beta, is the same research engine pointed at federal tax law. Conclusions cite the exact section of the Internal Revenue Code and the Treasury Regulations, with the source text one click away.
Treat it as a research starting point, not professional advice. Every conclusion carries clickable citations so a qualified professional can verify it, and Word exports include numbered references with quoted sources so the work can be checked outside the app.
The Free plan is $0 and includes one full cited research session plus drafts in each tool to try: one memo, one disclosure, one policy, and two schedules. Professional is $149 per month, or $1,490 per year (two months free), with unlimited memos, disclosures, policies, and schedules plus 20 research sessions each month. Enterprise is $399 per month, or $3,990 per year, with unlimited research sessions and priority support. No credit card is required to start.
One thread on one question. Follow-ups, requests for tables, and pushback on an answer all belong to the same session and never count as new sessions. Professional includes 20 research sessions a month, resetting on the 1st; Enterprise sessions are unlimited.
Annual billing gives you two months free: Professional is $1,490 per year versus $149 per month, and Enterprise is $3,990 per year versus $399 per month. That is the only discount that exists: no promotional codes, no limited-time offers.
Yes, anytime in Settings, in two clicks. Paid plans renew on your chosen term, monthly or annually, until canceled, and you keep access through the period you paid for. All purchases are final.
Every claim in an answer carries a citation that opens the handbook at the exact page with the supporting text highlighted. Before an answer is shown, a verifier model checks each citation against its source text and strips anything it cannot support.
Answers are retrieved from named authoritative sources: Big 4 interpretive handbooks alongside FASB and SEC EDGAR materials, and for tax, the Internal Revenue Code and Treasury Regulations. An independent verification pass then checks every citation against its source text before the answer is displayed, and every citation stays clickable down to the page level.
Yes. The corpus spans the major ASC topics, including revenue recognition under ASC 606 and leases under ASC 842, drawn from Big 4 interpretive handbooks with tens of thousands of searchable guidance passages — and it keeps growing.
The answer shows the positions side by side: divergence surfaced, not averaged. When KPMG, EY, PwC, and Deloitte read a judgment area differently, each firm's position appears with its own citation, so you can see exactly where the judgment sits before you make the call.
No. Customer content is never used to train AI models. Requests are routed to model providers under zero-data-retention arrangements, work is segregated per account and encrypted, and uploaded documents self-delete within 24 hours.
Uploaded documents are processed for your session and automatically deleted 24 hours later, including every derived search index entry, and every upload has a delete-now control if you don't want to wait. Work you create in the app, like memos, research threads, policies, and schedules, persists until you delete it.
Not yet. Our controls are designed against SOC 2 criteria; a formal independent audit is on our roadmap. Today, content is segregated per account with ownership checks on every request, encrypted at rest and in transit, and never used to train AI models. The full posture is on the trust page.