What I build

Software for finance and procurement

Invoice validation

Every invoice checked against its contract and purchase order, with the expected total, variances and potential savings.

Contract clause extraction

Pricing, discounts, commitments and service credits pulled from contracts, each linked to its page and section.

Document intake

PDF, Word, Excel and scanned documents read and turned into structured data, with OCR where needed.

Approval workflows

Findings routed to the right person to approve or reject, with an audit log of who decided what.

Audit-ready reports

Non-editable PDF reports with timestamps, versions, results and explanations, ready for auditors.

Finance dashboards

Revenue, collections and supplier accuracy in one view, from the same data the checks use.

AI, right now

Where AI genuinely helps

Finance and procurement teams sit on piles of documents that decide real money: contracts, purchase orders, invoices. Checking each invoice against its contract properly is slow, so it mostly doesn’t happen, and overcharges go unnoticed.

AI can now read those documents reliably enough to do the first pass, as long as people stay in charge of the decisions. PayRight is built on exactly that rule, and OpsVanta shows the finance side of a full operations platform.

  • Reading documents at scale

    AI extracts the clauses and line items that matter, so people review findings instead of reading every page.

  • Catching what slips through

    Pricing variances, quantity mismatches and missed discounts flagged before payment, not found in an audit later.

  • Plain-language summaries

    Each finding explained in a sentence an approver can act on, with a link to the source.

  • Human in the loop by design

    AI identifies, a person confirms, the system calculates. Nothing is approved or paid automatically.

Proof

Real projects in this industry

PayRight validation report for an invoice, with accuracy score, invoiced and expected totals, variance, potential savings and linked contract and purchase order

RAG and AI chatbots

PayRight: AI that checks every supplier invoice against the contract, with a human in the loop

A UK contract compliance and invoice assurance platform. AI extracts contract clauses, people confirm them, and every invoice is scored against contract and PO.

Client
PayRight, powered by GovernTerms (UK)
Role
AI full-stack developer
When
2026
  • Claude Code
  • React
  • Node.js + TypeScript
  • PostgreSQL / Supabase
  • OCR and document extraction
  • Role-based access control
OpsVanta revenue dashboard with revenue KPIs, revenue by month, revenue by country and customer revenue distribution

MVP and SaaS development

OpsVanta: one platform for the whole revenue lifecycle at IST Networks

An internal ERP built solo with Lovable and Claude Code on Lovable Cloud, running sales, projects, tickets, collections, finance and AI insights in one place.

Client
IST Networks
Role
Solo developer, working directly with the CEO
When
2025–2026
  • Lovable
  • Claude Code (Opus)
  • GitHub
  • Lovable Cloud (Supabase)
  • PostgreSQL with row-level security
  • Edge Functions

Data, security and access

  • AI never approves, blocks or changes a payment; it recommends and people decide.
  • Every finding traces back to the document, page and section it came from.
  • Role-based access, per-customer data separation and audit logs across every critical action.
  • Benchmarks use anonymised, derived figures, so no customer's financial data is shown to another.

How a project runs

  1. Call

    A 30-minute call about what you need, who it is for, and what success looks like.

  2. Scope

    A written scope: features, architecture, timeline, price range and risks.

  3. Build

    Working increments you can click through, not a big reveal at the end.

  4. Ship

    Live on your domain and hosting, with a handover so you know how it runs.

More in how I work, or see rag and ai chatbots.

Questions

Common questions

Will the AI approve or pay invoices automatically?

No. It's a decision-support tool. AI extracts and compares, the system calculates, and a person approves or rejects every result.

What kinds of documents can it handle?

Contracts, purchase orders and invoices as PDF, Word, Excel, CSV or JSON, including scanned copies, which go through OCR first.

How do you make AI output trustworthy for finance?

Every extracted clause shows its source, people confirm clauses before they're used, and results are reproducible from the stored data. Before go-live, results are checked on a sample of your own documents.

Can it connect to our ERP or accounting system?

Usually through the system's API or regular exports. Which systems, and how, is set in the scope after a call.

Checking invoices and contracts by hand?

A 30-minute call is enough to tell whether it fits, what the first version should include, and how long it takes.

Book a 30-minute call