AI & Data Science

Building agentic AI for finance

Agents that do real finance work (collections, close, treasury, cash forecasting) with rules that make the decisions, models that write the explanations, and a person who signs off. Code, experiments and notes from building them.

7
projects
20
finance agents
17
notes & essays

See the projects Read the notes

build log

Projects

trustgate

An agent for large code migrations. Claude rewrites one function at a time; static checks, property-based differential tests and SMT equivalence proofs decide what a human needs to review.

10 agent papers, in code

Small runnable demos of the core idea in Chain-of-Thought, ReAct, Toolformer, Reflexion, Tree of Thoughts, Voyager, AutoGen and three more. Runs offline, or live against Claude.

Keeper: autonomous AR agent

Reads open invoices and customer history, picks the next best action per account, does low-stakes ones itself and sends the rest to an approval queue, with a full audit trail.

Jev vs. Claude Haiku

Categorising 200 bank statement lines two ways, and what it says about which treasury labels you can post without a human checking them.

Agent at work

An agent running a 13-week cash forecast.

  1. Ingest
  2. Categorise
  3. Forecast
  4. Alert
  5. Act
illustrative · synthetic data
bank_feed.sync()
    agent waiting for transactions…
    13-week cash forecast actual forecast buffer
    $250k buffer
    !Projected shortfall in week 7

    Cash dips to $232k, $18k under the $250k buffer. Recommend moving two vendor payments ($40k) from week 7 to week 9.

    ApproveReview

    writing

    Start here

    All notes

    2026

    Building a Foundation Model for Personalized Recommendation

    One model. Every member’s full history. Many recommenders.

    Causal Reasoning for Agentic AI

    An agent I watched last quarter did everything right and still got the answer wrong. It read the request, produced a clean five...

    When We Can Finally See Inside an AI’s Mind

    Why understanding how large language models think may become one of the most important breakthroughs in artificial intelligence.

    How AI Stack in the CFO Vertical Can Double the ROI of Fintech

    There are many parts of the CFO vertical can be enabled by AI to increase the productivity and at the same time improve the per...

    AI Is Already Building Better AI. Most People Haven’t Noticed Yet

    Anthropic’s latest essay suggests we may have crossed an important threshold: AI is no longer just helping humans work faster —...

    We Built the Perfect Data Strategy — for Three Years Ago

    Why the future of data governance is not just about helping humans understand data, but helping AI understand what your busines...

    Understanding the LLM Orchestration Stack

    How modern AI applications coordinate models, tools, memory, and workflows to build production-grade intelligent systems

    Innovation and Governance: The Future of AI in Lending

    The lending industry is standing at the intersection of two powerful forces: rapid AI-driven innovation and increasing regulato...