Skip to content
India-built · AI-native ERP for steel
Live in productionrunning a real steel service centre — today, every day

Areca 360

A ₹250 Cr+ steel service centre runs on Claude. Not a demo, not a pilot — the operating system of a working business at scale. One Claude layer reads the documents, answers the team's questions, and will soon price the credit. It has run every day, unattended, in production.

Status
Live · single-tenant · daily use
Stack
React · Supabase · FastAPI · Claude
Claude surfaces
Parse · MCP · Chat · Extraction · Claude Code
Record
Verified — every figure traceable
The problem

An ERP records the business — the gap between it and reality leaks into the P&L

A service centre already runs on an ERP. The problem isn't the absence of a system — it's everything the system can't do for itself. The ERP holds the ledger, but it doesn't read the supplier invoice, reconcile the mill certificate, re-check the credit note, or judge the counterparty, and the gap between what the ERP records and what actually moved is where the money quietly goes:

A misread tonne or rate is keyed straight into the ERP. Quantity in TO entered as pieces, a rate off by a digit — and it's now in your GST return, your stock valuation, and the customer's bill. The error surfaces weeks later, in a dispute.

One dropped line on a 100-line credit note is under-claimed input tax. Nobody re-adds a hundred rows by hand before posting. So they don't — and the ITC is left on the table.

Reconciliation is manual, so the ERP lags reality. Books catch up to operations days behind, and by then DSO has crept and working capital is stuck in coil nobody flagged as ageing.

Credit goes out on reputation and a prayer. The ERP shows what a customer owes, not whether they'll pay. On 2–4% net margins, a single bad debtor erases months of contribution — and the risk was sitting in documents the ERP never read.

None of this is a people problem, and it's not a missing-software problem — it's the manual layer around the ERP — the reading, the reconciling, the judging — that exceeds what keying by hand can do accurately. Errors there don't stay operational; they land in tax, in margin, and in bad debt.

The value

What changes when Claude runs it

Document to data, zero keying. Every invoice, CN/DN and MTC becomes structured, sourced line items — each figure traceable to the page and box it was read from. The manual layer around the ERP becomes a data asset.

The arithmetic checks itself. Qty × rate = taxable value is re-derived on every extraction. A mismatch is caught and typed — misread field, dropped line, missing document — before it reaches the books.

Reconciliation is continuous, not a scramble. Operations and the ledger stay in step daily, so ageing and DSO are visible while they can still be acted on.

Risk is priced before credit ships. The layer that reads the counterparty's documents will underwrite the credit they ask for — a traceable verdict in place of a prayer.

Where Claude sits in this system

Claude is not a feature bolted on — it is the build tool, the intelligence layer, and the agent surface into the business. Five distinct, engineered uses:

01Builder

Claude as the builder

The entire platform — ERP and credit engine — is engineered, debugged and extended with Claude Code. The loop that builds the product and the loop that operates it are both Claude.

02Runtime

Claude in the runtime

Haiku 4.5 and Sonnet 4.6 parse every supplier document in production — invoices, credit/debit notes, mill test certificates — on a schedule, unattended.

03Routing

Two-tier model routing

Haiku pre-classifies cheap and fast; extraction escalates to Sonnet only for the hard documents — credit notes past 100 line items. Cost matched to difficulty, not “biggest model for everything.”

04Guardrails

Claude behind guardrails

Every extraction is re-derived against a hard identity — qty × rate = taxable value — and errors are typed: misread field, dropped line, missing document. AI plus deterministic verification.

05Agent surface (internal)

Claude as the team's interface

Anyone on the team asks the live business in plain language — stock, ageing, open orders — instead of digging through screens or pinging the back office. Answered over MCP as the signed-in user, under row-level security.

01 / 05The Claude layer

One intelligence layer, two brains

Claudeone intelligence layer

Document & Operations Brain

Doc brain

Live

Email auto-triage

Gmail pulls invoices, CN/DN and MTCs the moment they land, sorted by type before a human looks.

Gmail

Parse & self-check

Every PDF becomes sourced line items; qty × rate is re-derived and errors are typed, not just flagged.

PDF → data

Agent-native

The live business is queryable in natural language over MCP.

MCP

Credit & Risk Brain · CreditSense

Credit brain

Integrating

Reads the counterparties flowing through the business and underwrites the credit they ask for — a graded, sourced verdict in place of a guess. Engineered as its own system; the number is deterministic, never an LLM.

Inside CreditSense

CreditSense is part of Areca 360, engineered separately — the credit-brain integration is in progress, not yet live. Claude powers the reading, not the number — the full engine is detailed in Inside CreditSense.

02 / 05Inside CreditSense

The credit brain — prices the risk the paper was hiding

CreditSense reads the counterparties flowing through the business and underwrites the credit they ask for. It is part of Areca 360, engineered as its own system so the engine could be built deep — integration is in progress.

Part of Areca 360Engineered separatelyIntegration in progress

How it helps

It turns “extend credit on reputation” into a graded, defensible call — a letter grade (A–E), a suggested limit, a confidence level, and the green and red flags behind it, each one sourced and timestamped. Something the decision-maker can act on or overrule with full context, never a number to take on faith. It re-runs on a schedule to raise an alert the moment a buyer's grade drops.

Why it's transformative

MSME steel credit is extended blind. CreditSense makes the same call explainable, entity-aware (a partnership isn't docked for lacking a company-only filing), and tunable per tenant — and because Claude does the reading, fast enough to grade every counterparty, not just the worried ones. The operator still makes the credit call; now they make it with the flags in front of them instead of a hunch.

The division of labour — the key design choice

Claude reads; it never scores. Claude Haiku turns messy web and registry results into clean structured findings — adverse media, agency ratings, insolvency mentions, sanctions hits — with name-match filtering, under a strict rule: if it isn't in the source, it returns nothing.

A deterministic engine grades. No LLM in the scoring path — a fixed, published rubric of seven weighted pillars where every grade traces to its inputs. Never a black box.

Two hard safeguards. Fatal signals (dead GST, admitted insolvency, a sanctions hit) force an outright decline — they can't be averaged away. And missing data is labelled “Not available,” never estimated; below a confidence threshold the engine withholds a verdict rather than guess.

The operator decides. Every grade ships with the green and red flags behind it, sourced and timestamped — so the call can be trusted, audited, or overruled with full context. The engine informs the decision; it never takes it out of your hands.

See the full seven-pillar rubric

Identity · resolved first, not scored

The legal and trade name, the entity's registrations and identifiers, its home state and structure, registered address, age and sector — resolved and cross-checked before anything is scored.

Hard stops

Any one → decline

The fatal signals — a dead or suspended tax registration, a struck-off entity, admitted insolvency, disqualified or wilful-defaulter directors, an identity that won't reconcile across registries, or personal insolvency of a proprietor or partner. Any single one forces an outright decline.

01

Compliance

Weight 20

Whether the tax registration is alive and filings arrive on time — return discipline over the trailing year, statutory annual filings, and consistency across every registration held under the same PAN.

02

Financial

Weight 20

Capital cushion and debt load, the scale of turnover and which way it is trending, and health ratios computed off the filings — leverage, interest coverage and how far payables are stretched.

03

Legal

Weight 25

Litigation exposure — the active case load, cheque-bounce actions weighted heaviest, insolvency petitions filed by creditors, and formal payment complaints raised against the entity.

04

Promoter / Ownership

Weight 15

Signals on the people behind the entity — adverse media on promoters, directors stretched across too many companies, and any disqualification or wilful-default history.

05

Reputation

Weight 10

Market-facing sentiment — ratings and the volume of reviews, recurring themes of not paying vendors, adverse press, and whether the trading address actually checks out.

06

Stability

Weight 10

How durable the business looks — years in operation, the entity structure, a real web and social presence, a marketplace footprint, and the direction of its workforce.

07

Payments

Weight 15 · gated

How the buyer actually pays — days beyond terms reported by trade references, whether those suppliers would deal with them again, and self-declared or auditor-confirmed dues owed to smaller vendors.

Joins the composite only when real payment evidence exists — absence of data never reads as a negative signal.

+

Evidence-only

Red flags + confidence

Auditor and going-concern signals, distress in group companies, provident-fund regularity, external credit ratings and cooperation flags, and sanctions screening.

Drive red flags and confidence today; folding them into pillar math is a queued decision.

Every data point carries its source and retrieval timestamp, and scores on a published band — the “why” behind any grade is fully traceable.

Every assessment returns

Grade
A – E
Verdict
extend · conditions · advance-only · decline
Limit & terms
conservative, suggested
Confidence
how much is verified
Evidence
fully-sourced trail

The same engine re-runs on a schedule for ongoing monitoring — raising alerts when a buyer's grade drops or a new red flag appears.

Build lessons

What building this taught us

01

Match the model to the difficulty, not the ego. Haiku classifies everything cheaply; Sonnet is spent only on the documents that actually need it. “Biggest model for everything” is how AI projects die on cost.

02

AI proposes, arithmetic disposes. Probabilistic extraction is wrapped in deterministic checks. The model's confidence doesn't post to your books — a re-derived qty × rate does.

03

Type your errors. “Failed” is useless. “Misread field / dropped line / missing document” tells you what to fix and lets the system route the exception.

04

Null-plus-reason beats a confident guess. A system that says “Not available” is trusted; one that fabricates to look complete is used once.

05

Pin the engine like flight software. Five synthetic personas form a permanent regression suite — any change that drifts a grade fails the build.

06

Build and operate loop, same tool. The product is built with Claude Code and run on Claude in production.

07

Depth in one real business before breadth across many. Built inside a working service centre, by its operator — single-tenant proof is the wedge; the platform is the play.

03 / 05What Claude produces

Evidence, not adjectives

The layer's output is inspectable: a parsed invoice that caught its own error, a transparent credit verdict, and a live business you can just ask.

Screenshots can be staged; arithmetic cannot. Every artefact below is the system checking itself in public.

Parsed invoice

InvoiceCN-DNMTC
Parsed invoice line items with quantity times rate re-derived to a value; one row flagged for an arithmetic mismatch.
Line itemQty × rateValue
HR Coil 2.5mm12.40×62,5007,75,000
CR Sheet 1.2mm8.10×71,2005,76,720
GP Coil 0.8mm⚠ flagged5.00×68,4003,08,000
MS Plate 10mm3.25×58,9001,91,425

GP Coil 0.8mm — arithmetic mismatch → flagged & classified (misread field)

Figures illustrative & masked

Credit verdict

CreditSense
B

Extend credit — with conditions

Suggested limit▪▪▪▪
Confidence82%
Compliance78
Financials71
Legal85
Promoter74
Reputation80
Stability69
Paymentn/a

Payment pillar gated — no verified payment evidence yet, so it stays out of the score.

Seven-pillar deterministic rubric · hard-stop overrides · confidence-gated. Claude does the reading, not the number.

Figures illustrative & masked

Live MCP query

what's open stock & ageing for ▪▪▪▪?
38.4 T · ageing 41d
queried over MCP · natural language · customer name redacted

Figures illustrative & masked

04 / 05The live system

Proof it actually runs

Live inventory

5grades

Tracked coil → WIP → dispatch, with full genealogy from the incoming coil to the piece that leaves the gate.

coilWIPdispatch

Tally sync

Daily

Books auto-matched against operations every day — the system of record and the ledger stay in step without manual reconciliation.

auto-matched

Dispatches

▪▪▪▪Kg

Every dispatch weighed, logged and tied back to its source coil. Volumes are masked here — the audit trail behind them is real.

weighed · logged · traced

Edge functions

26deployed

Deployed functions run the pipeline — sync, parse, verify, serve — on schedules, unattended.

cronvaultRLS

Figures illustrative & masked

05 / 05The platform

Run the business, then underwrite the credit that flows through it

Run

Areca 360

The operating system — documents, inventory and agents that run a real steel service centre.

Operations

Underwrite

CreditSense

Part of Areca 360, engineered as its own system — it reads the counterparties flowing through the business and underwrites the credit they ask for.

Credit · integrating

Become

One platform

A single system of record where running the business and pricing its credit are the same motion.

System of record

Why steel, why India, why now

India's steel flows through thousands of MSME service centres running on ERPs that record the business but can't read the documents or price the risk moving through it. Areca 360 was built inside one of them, by its operator. The document brain removes the paper; the credit brain prices the risk the paper was hiding. One proven single-tenant deployment is the wedge; the platform is the play.

How it's built

Engineered with
Claude Code
Models in production
Haiku 4.5 · Sonnet 4.6
Agent surface
MCP · OAuth · RLS
ERP stack
React · Supabase · edge functions · Tally sync
Credit stack
Next.js · FastAPI · Postgres · deterministic scorer