Numera

A small business's books are scattered across QuickBooks or Xero or Tally or Zoho, bank feeds, payment settlements and an inbox full of PDFs. Somebody has to shuttle all of it into the ledger by hand.

Numera is one agent that operates all of them. You delegate work in plain language; it reads and writes through each platform's own API; and nothing reaches your books without being proven right: proposed before it posts, read back after it lands, and recorded in a tamper-evident audit trail.

The derivation

Three irreducible truths force this product into existence:

• The books are a deterministic function of money events. Bank transactions, invoices, payroll in; statements and filings out.
• The historical cost of accounting is data capture and error recovery. Chasing receipts, reconciling statements, re-keying between systems is where most of every fee goes.
• Deadlines are rigid and liability requires a licensed professional. So the architecture is fixed: agent does the work, accountant signs off.

The full derivation lives in the thesis paper; the trust machinery in the verified agent loop.

One agent, ten platforms

The agent never sees vendor SDKs. It sees one interface, and each adapter speaks it natively: OAuth where the platform demands OAuth, XML where it must speak XML, file exchange where no API exists at all.

India's SMBs live in Tally and Zoho Books, and the India-specific feature no global player ships, GST input- tax-credit mismatch detection against supplier filings, is exactly the money-recovering work an agent should do continuously instead of an accountant annually.

What the agent actually does

"reclass may freight from COGS to landed costs,
 show margin impact"

→ propose   balanced journal draft, balance-checked before render
            period checked: is May even open?
→ confirm   you read the entry, click confirm
            who confirmed is recorded; maker ≠ checker
→ post      idempotent write, a retry cannot double-post
→ read back the posted record re-fetched, diffed line by line
            wrong-account-with-right-totals is caught
→ audit     hash-chained row, exportable evidence packet

Reads run free: aged receivables, largest unpaid invoices, margin impact. The month-end close runs as derived checklists, recurring journals, bank reconciliation with the exact off-by figure explained, variance tie-outs, and a sign-off stamp only when nothing is pending.

The moat is the boring part

The defensible work is underneath:

• Line-level read-back verification per account and currency, live on QuickBooks Online and Intacct, downgrading to "totals checked" when a platform exposes no account codes.
• Idempotent writes: deterministic control ids mean a retried confirmation returns "already applied", never a double-post.
• Closed-period enforcement: posting into a locked period is refused before the proposal renders.
• A hash-chained audit ledger: every action HMAC-signed and chained to the previous row; edits, insertions and deletions are detectable; one click exports the period's evidence packet.
• An error taxonomy per platform: Intacct's own correction text surfaced verbatim, rate limits named, stale tokens re-authed mid-request.

The residual risk is disclosed: an attacker who deletes tail audit rows and their seals in lockstep defeats an on-box chain. Closing that means anchoring the chain off-box, which is on the roadmap.

Risks

• Platform APIs are permissioned ground. Intuit and Sage license write access; scopes can shrink. Mitigation: the file-based adapters (Desktop, Sage 50).
• Trust is bought slower than features are built. Accounting buyers are risk-averse; the counter is the verification layer itself plus published accuracy, and eventually a named human signer.
• Ten adapters is a maintenance surface. Each platform drifts its API yearly. Counter: the offline test suites per adapter and a distilled API-context corpus the agent retrieves from.
• LAC-style players coming to India. They would have to rebuild years of India-specific rule accumulation: GST depth, Tally reality.

Numera Solo, the local-first, plain-text ledger edition, is already open source at github.com/anishfyi/numera; Numera Pro, the hosted close, is at numera.velofy.co.