Tong Zhao
I work on LLM security, multi-agent system design, and vertical AI products. The projects here circle one question: when should an LLM reason, and when should it stop, check evidence, call a tool, or hand the work to a deterministic system?
Current work: security-research workstations, context compaction and retrieval, tool boundaries, adversarial review, and agent product shapes for vertical domains such as tax and job search.
Selected projects
One thread across these projects: turning messy expert workflows into agentic, evidence-aware software systems that people can actually operate.
-
TaxPilot — zero-hallucination AI for UK tax
TaxPilot is a UK tax advisory system that puts tax status, tax-year versions, official legislation / HMRC sources, deterministic calculations, and gap flags into one traceable workflow, so the AI explains where each conclusion came from.
Next.jsMastraVercel AI SDK Postgres + pgvectorPrisma
View project →
-
Contract Review — auto-clear the known 80%
A small legal-workflow product for standard NDAs and order forms. It auto-clears clauses that match an approved position, auto-redlines deviations it has seen before, and escalates genuinely novel issues with reasoning a lawyer can audit.
Next.jsMastraVercel AI SDK Postgres + pgvectorDrizzle
View project →
-
Agent Browser Runtime — DevTools-grade evidence for AI agents
An open-source local runtime that gives an AI agent a Burp-grade browser workbench. F12 Network, Storage, Console, and Sources captured as structured evidence with stable artifact paths, exposed through a small facade rather than two hundred low-level buttons. The tool reports what the browser actually observed; the agent decides what it means.
TypeScriptHTTP + CLI Playwright + direct CDPChrome extension bridge Profile-scoped evidence
View project →
-
UK Capital Gains Tax calculator (share disposals)
A working UK capital-gains calculator for share disposals. It imports broker files, applies the same-day, 30-day and Section 104 matching rules, and produces an audit trail that can be checked against HMRC examples.
TypeScriptDeterministic rules engineCSV / Excel import HMRC fixturesTailwind
View project →
-
Agent Desk — local-first workbench for AI coding CLIs
A browser and desktop control layer for Codex, Claude, and DeepSeek-style coding CLIs running on a local Windows workstation. It organizes projects, conversations, runtime state, queue/stop/restore controls, and user-confirmed handoffs between agent work sessions.
PythonElectronLocal runtime adapters Mobile browser controlAgent handoffs
View project →
-
Hengo — AI job search for international graduates
A job-search product for international graduates in the UK. It combines visa rules, sponsor data, role matching, CV work, and company intelligence into one workflow, with five specialist advisors behind a single interface.
Next.js 16Claude Agent SDK Prisma + PostgreSQLpgvectorVoyagePlaywright
View project →
-
Multi-agent security research workstation
A write-up of an earlier version of my multi-agent vulnerability research workstation — the role split, the evidence loop, the adversarial review step before any report is written. The current architecture is being redesigned; this page is kept as an archive.
Output: an Intigriti 10.0 / 10.0 Exceptional report against CM.com's admin API. Other disclosed work spans Cambium Networks, Venly, Bild.de NewsBot, and AI/ML supply-chain targets.
Multi-agent orchestrationEvidence-file source of truth Adversarial reviewChrome DevTools Protocol TypeScript
View project →
Background, briefly
- 2026 – present. Independent — full-time on LLM agent security, multi-agent workflow design, and vertical AI products. Active responsible-disclosure across web, AI/ML, and frontier-LLM targets.
- Feb 2025 – Feb 2026. Senior, Tax — Blick Rothenberg (London). UK personal tax and Global Mobility advisory / compliance for international clients. Built an internal Power Platform / Dataverse workflow prototype covering task tracking, client dashboards, and billing monitoring.
- Sept 2021 – Jan 2025. Senior Associate, Global Mobility Tax — PwC / Vialto Partners (London). Expatriate tax-equalisation, cross-border employee mobility, Chinese high-profile clients and UK subsidiaries. Independently designed a 2022 GPT-3 internal billing-coordination tool — pre-ChatGPT, pre-tool-calling, pre-MCP.
- Tax credentials. ATT (Association of Taxation Technicians, full). CTA partially qualified — Taxation of Individuals paper passed.
- LLM history. Working with LLMs since the GPT-3 era (2020+). Multi-year exposure across pre-Agent / pre-MCP, the early ChatGPT period, and the current frontier-model and agent generation.