Tiny AI Tools, Big Wins: Automating Cost Report Extraction on Your Laptop in Minutes

Created on 2025-11-15 12:50

Published on 2025-11-15 14:42

AI Coding Agents for Program Managers and Auditors

While everyone is wondering how their job might change because of AI, I’ve been thinking about a simpler question for people who want to control how AI impacts them:

What kinds of manual, repeatable tasks can be completely automated with AI help right now?

This post is a case-study about one of those tasks: end-of-year data extraction from a folder of Excel cost reports, the kind many program managers and auditors deal with constantly. Maybe it’s to begin analysis or a reimbursement process, either way, automating an extraction task like this has never been more within reach for non-programmers.


The problem: hundreds of spreadsheets, same manual, annoying steps

In one of my past roles, we reimbursed local governments for salary costs for staff working in a specific program.

Every year, the same workflow showed up:

  1. Collect hundreds of cost report spreadsheets from entities across the state

  2. Extract district and salary data from specific tabs (e.g., Input Data, Salaries)

  3. Compile everything into a single dataset

  4. Export to Excel

Once it was in Excel, we could start processes that actually impacted the program like:

Nothing about this was intellectually hard. It was just… slow. Manual. Error-prone. These kinds of tasks are perfect for automation.

So instead of subscribing to some big new AI platform to magically solve it, I used an AI coding agent to build a tiny ETL tool that lives on my laptop, runs in a secure environment, and can be part of suite of program management tools.


The idea: small, repeatable wins you actually own

I’m using AI coding agents (specifically OpenAI’s Codex CLI) to generate small, task-specific tools:

In this case, I set up a folder called program_management that will hold multiple automation tools, with a subfolder called ‘extract’ for this experiment. The extract folder holds a handful of template-based Excel files:

These templates stand in for the hundreds of spreadsheets we’d normally see in actual programs.


Follow along on YouTube and GitHub

I’ve recorded a screen-share walkthrough (bottom of article) showing this exact process with the Codex agent and example files, you can access both below. I’m going to walkthrough using this process to automate more program management and audit processes (e.g. desk reviews, dashboards, and reports) in future videos so let me know if you have any questions or want to see something specific.

https://youtu.be/kAkkZ_oGTsE

https://github.com/scottlabbe/program_managementx


The tools: Codex CLI + VS Code + your file system

Here’s the basic stack:

I run Codex CLI from the terminal inside the program_management folder and give it a prompt like:

Then I let it work. On its own:

My job is mostly to read what it’s doing, approve the plan, and run the tests. I don’t have to hand-write every line of Python, but I still stay in control.


Data security: build with fakes, run on the real thing

One big point I want to emphasize for anyone working with sensitive data (salaries, PII, etc.):

You get the benefit of AI-generated automations without handing over actual salary details.


What I end up with: a small, focused automation tool

By the end of this process, I have a CLI tool for:

  1. Extraction – pulls data from all relevant tabs across all spreadsheets

  2. Schema + database – loads everything into a SQLite database I can reuse

  3. Export – spits out a clean Excel file for analysis, desk reviews, etc.

  4. Testing – lets me re-check correctness any time I change or extend the pipeline

Because they’re just commands, they’re also friendly for building on top of:

No subscription, no platform lock-in (other than a $20 OpenAI subscription), just little utilities we control.


Why this matters for auditors and program managers

From a program management or audit perspective, this kind of tiny ETL tool can:

And more broadly: AI will take over tasks before it takes over jobs.

If you can identify the tasks that are: tedious, repetitive, or rule-based...

…then AI coding agents are an extremely simple and practical way to start automating them today and actually control how AI impacts your role.


If you’re an auditor or program manager reading this and thinking, “I have a horrible little process that would be perfect for this”, I’d love to hear about it.

Drop a comment or message me with: