Automation

A practical decision ladder for choosing between rules, RPA, traditional machine learning, LLM workflows, and agent-like systems.

Tool calls look clean in a demo. A user asks for something. The model thinks. A browser opens. A database is queried. A spreadsheet is updated. A draft email appears. Everyone smiles, because apparently we now have an “AI agent.” Then the production version fails for a reason that is somehow both tiny and catastrophic: a tool schema was renamed, a memory field was serialized differently, a retry policy changed, a prompt template compressed one instruction too aggressively, or a guardrail blocked the wrong intermediate step. The model did not become stupid overnight. The architecture quietly moved the steering wheel. ...

A workflow breaks in a boring way. The agent found the website yesterday. Today the button moved. Yesterday it parsed the file path correctly. Today the file name has a space, a date, and some human creativity sprinkled in for punishment. Yesterday the chart script worked. Today the data source changed its column names because apparently stability was not on the roadmap. ...

CRM is supposed to prevent organizational amnesia. The sales team learns that a prospect is evaluating three vendors. Support later discovers that the same company is unhappy with integration quality. Marketing has a note that the buyer prefers technical benchmarks over executive storytelling. Finance knows the renewal is sensitive to payment terms. ...

A failed automation run usually tells you more than a successful one. A coding agent compiles the wrong program and receives a concrete error. A web-navigation agent clicks into the wrong product page and sees that the attributes do not match. A task agent tries an invalid action and the environment complains, patiently, like a machine that has seen too much. In each case, the system does not merely say “failed.” It gives clues. ...

How to separate true agent-like systems from straightforward AI workflows, and why most business use cases should start simpler.

How to use AI to classify incoming cases, assign ownership, protect service levels, and escalate the right issues without losing operational control.

How to use AI to classify, prioritize, and route inbound email without turning your inbox into an uncontrolled black box.

How to use AI to turn raw operational inputs into clearer recurring reports while preserving review, context, and accountability.

How to design a lightweight classification pipeline with a clear schema, confidence thresholds, review paths, and a realistic refresh cycle.