BRASSWIRE LAB #06 · ISSUE #006 RUNS IN YOUR BROWSER · NOTHING IS SENT

Is automating a repetitive desktop task worth it?

For small digital businesses that automate work inside older Windows programs for clients. Compare a fast scripted path with a slower AI agent using your own timings, see the hours saved per month, and generate safety checks for the automation. Inspired by the System 1 agents paper (see Sources); compiling past runs into scripts is our extension, not the paper's method.

01 // FAST PATH VS SLOW PLANNER

EXAMPLE ASSUMPTIONS · time both paths on your own workflows and replace these

250 / day
85%
20.0 s
3.0 s
22 days
02 // CPU TTS WORKER POOL (STARTING POINT)
8 cores
03 // WIN32 ANTI-FRAGILITY GUARDRAILS

EXAMPLE RESULTS · illustrative, computed from the assumptions on the left. Not a benchmark.

Example blended time / task
5.6 s
Example hours saved / month
22 hrs
TTS workers to start with
4 to start
Guardrails enabled
3/3 ON
GENERATED WIN32 + FAST-PATH GUARD SPEC (EXAMPLE VALUES):

      

How the example math works: blended time = share × fast + (1 − share) × slow. Hours saved = tasks per day × (slow − blended) × working days ÷ 3,600. The worker count (physical cores ÷ 2) is a starting point for load testing, not a measured capacity: measure time-to-first-audio on the client's own hardware.

What this leaves out: the time to build and maintain the fast path, screens that change and break it, the cost of an error that slips through, and licensing of the legacy software. Time both paths on the client's real workflows before quoting hours saved.

STARTER BUILD PROMPTS (PASTE INTO CLAUDE, CURSOR OR A SIMILAR TOOL)

    

Sources & what we checked