Advance · Advanced · finance systems teams

Claude Code for Finance Systems

An advanced day for Finance-systems teams that already script. Learn how to build, test, review, document, and govern Claude Code agents through one guided end-to-end prototype and one independent practice build, then create team conventions for continuing the work responsibly.

AI handles defined preparation. A person reviews. Your controls remain in place.

Full day · up to 8 · your office or online · $12,500

The course

About this course

This advanced course is for Finance-systems professionals who script and have already completed Build a Governed Agent or equivalent work. The morning uses one suitable process to teach the full pattern: source connection, deterministic code and tests, bounded AI assistance, a review queue, logging, scheduling, documentation, and controlled system access where appropriate.

In the afternoon, participants apply the learned pattern to a second sanitized example with peer and instructor review. The group then drafts its Claude Code conventions: repository layout, rules files, credential handling, commit discipline, ownership, review, and README standards.

The builds are hands-on workshop prototypes used to develop internal capability. This course runs on Claude Code.

Who it is for
Finance systems, reporting, and data people who already script, and who have taken Build a Governed Agent or run something equivalent
Format
Advanced full-day training for a small group. Participants complete one guided prototype, practise the pattern on a second example, and draft team conventions for future work.

What the team learns, practises, and drafts

Outcomes

  • Apply a repeatable architecture for source connection, deterministic code, tests, bounded AI work, human review, logging, and scheduling
  • Build and exercise one guided end-to-end prototype in a workshop environment
  • Apply the pattern independently to a second sanitized practice process with peer and instructor review
  • Review generated code, tests, logs, failure handling, and approval boundaries rather than accepting them uncritically
  • Draft team conventions for rules files, repository layout, credentials, commits, ownership, documentation, and review
  • Diagnose a planted failure and revise the workflow instructions, rules, or tests
  • Evaluate readiness gaps and the additional work required before production use
  • Reuse the learned standards and method when approaching additional suitable processes

Outline · 6 hours

How the session runs.

Usually 9:30 to 12:00 or 2:00 to 4:30. Other times are fine.

  1. 0130 min

    The boundary, the setup, the standards

    • One process from the team’s list. Inputs, outputs, who approves, where it logs.
    • Project setup and the rules file that makes Claude Code behave like a colleague who knows the platform.
    • What credentials never look like. A real example, sanitized, from an archive.
  2. 0260 min

    Connection, code, tests

    • A query or a watched folder instead of a paste.
    • The deterministic core, sums, joins, as-of logic, thresholds, as a script with tests Claude Code writes and you review.
    • The AI layer on top: read the exceptions, classify, draft the note.
  3. 0345 min

    Systems, approval, log, schedule

    • An MCP link to a system where it helps; a read-only boundary where it does not.
    • Output to a review queue, never a ledger. The approval is the trigger for anything that posts.
    • Every run writes what it did and why. Scheduling it, and the morning digest.
  4. 0445 min

    Run it, break it, fix the Workflow Card

    • Run the guided prototype in the workshop environment, introduce a planted failure, and use the log to diagnose it.
    • Fix the Workflow Card and the rules, not the prompt. Rerun.
    • A second person runs it from the README.
  5. 0590 min

    Apply the pattern to a second practice process

    • Each participant applies the pattern to a second sanitized or practice process, with peer and instructor review.
    • Partners review each other’s code, log, and approval gate at the halfway mark.
    • Neil circulates. Nobody gets code written for them.
  6. 0660 min

    The team’s conventions

    • The conventions repo, written together: rules file, layout, credentials, what gets committed, README standard.
    • Where the agents live, who owns each, how a new one gets added.
    • What to do when it gets bigger than a script.
  7. 0730 min

    The next ten

    • The team’s candidate processes, reviewed with what it now knows.
    • Which belong in code, which to the AI, which stay with a person.

Bring

What to bring

  • A laptop with a terminal, Claude Code installed, and a Claude login your organization allows for work. Setup instructions come ahead of the course.
  • Build a Governed Agent, or the equivalent: you have built at least one scheduled, logged agent with an approval gate.
  • Sanitized inputs for two suitable processes.

About your data

About your data

Courses use practice files that resemble real Finance work, so confidential data is not required to learn the method. A participant may use a sanitized file—or a company file only when the organization’s policy and approved AI environment permit it.

The method makes the input, transformation, expected output, and human review explicit. It does not require an unrestricted agent inside company systems, and it does not replace the organization’s technology, privacy, security, records-management, data-residency, or approval requirements.

Where a workflow could change a system of record, nothing posts without authorized human approval.

Instructor

Neil Perejma

Founder, 1113 Technologies and EPM ONE Consulting

Neil Perejma has advised Finance and operations leaders for more than 20 years on the processes, reporting, and controls their organizations depend on, and every engagement has left the team able to carry the work forward.

Today his clients are asking how to bring AI into Finance work without weakening governance. His courses give Finance teams a practical way to do it, keeping AI inside the controls they already have.

More about Neil

The others

Other courses

Questions about training your team?

Book a 20-minute call with Neil Perejma, on Zoom or by phone.

Book a call