Tech Stack
A deliberately curated set of tools that amplify output across finance, legal practice, and software development.
Tools in Stack
Software Tracks
AI Tools
Years Building
These aren’t experimental toys—they’re production infrastructure. Each AI tool is deeply integrated into the daily workflow, handling everything from code generation to legal research synthesis.
UI Generation & Prototyping

.png)
AI Pair Programmer
Multimodal Reasoning Assistant
Safety-First Reasoning & Deep Analysis
Agentic Coding CLI
Real-Time Insight Assistant
.png)
.png)
General-Purpose Frontier Assistant
AI-Native Code Editor

.png)
AI Research & Knowledge Synthesis


AI Browser & Ambient Assistant
AI-Powered Search & Agentic Browser
AI Discovery & Prototyping
Embeddings and vector search shape retrieval, MCP and agent protocols structure tool use, TanStack sharpens application state, orchestration frameworks coordinate AI flows, UI primitives keep interfaces precise, and edge runtimes carry the whole system closer to the user.
6 ecosystems • 30 technologies
Radar Logic
Rings show practical maturity. Inner rings indicate tools already shaping real product decisions; outer rings mark active exploration and emerging bets.
Quadrants
The real power of a tech stack is not in individual tools but in how they flow together. These three pipelines show how information moves from raw input to polished output.
From natural language prompt to deployed application in a single workflow. v0 generates UI, Copilot fills implementation gaps, Vercel handles deployment.
Legal and financial research starts with Perplexity surfacing the latest sources, NotebookLM grounding synthesis in uploaded documents, then flows through Bloomberg and LexisNexis for validation before producing actionable insight reports.
Raw data enters through SQL queries, undergoes statistical analysis in Python or R, and surfaces as interactive visualisations in Next.js dashboards.
From open question to cited brief in a single session. Perplexity surfaces the landscape with real-time citations, NotebookLM grounds the analysis in your uploaded corpus, and Dia provides ambient context as you browse — producing structured, source-verified briefs.
Every tool, framework, and technology actively used across frontend, backend, data, and professional domains. Dot colour indicates proficiency: accent = high, dimmed = foundational.
Proficiency measured by frequency of professional use, depth of domain knowledge, and ability to produce production-ready output.
Core programming languages and frameworks for building robust applications.
Data analysis, automation, financial modelling
Web applications, dashboards, tooling
Financial databases, reporting queries
Statistical analysis, portfolio modelling
Tools are only as good as the principles guiding their selection and use. These four pillars define how technology choices are evaluated, adopted, and integrated into professional practice.
Every tool is chosen for its contextual fit, not its popularity. The right abstraction at the right layer reduces friction and compounds productivity over time.
AI tools are not novelty features but foundational infrastructure integrated at every stage of the workflow, from research to deployment.
Professional expertise is amplified by data, not replaced by it. Quantitative tools provide the evidence base for qualitative judgment calls.
In finance and law, security is not optional. Every tool selection considers data handling, access controls, and regulatory compliance from day one.
Technology does not replace expertise — it reveals how much more is possible when expertise is properly amplified.
Every hour saved on routine work is an hour reinvested in judgment.
— AVW