Automation
Automation is software that executes a defined task the same way every time, following explicit rules or a trained model, without a human doing each step by hand.
No jargon, no math
In plain words, what is it?
Classic automation runs on rules you can read. An event arrives (an invoice, an email, a sensor reading), the system matches it against conditions you wrote, and the matching workflow executes its steps in order: read the fields, check the totals, post to the ERP, send the confirmation. Every run is logged, so you can replay what happened. The boundary is explicit: when an input matches no rule, classic automation does not guess. It parks the item in an exception queue and a human decides. Machine-learning automation loosens this: instead of hard rules, a trained model scores or classifies the input, which handles messier cases but adds a new failure mode, the confident wrong answer. The craft is choosing per task: rigid rules where correctness is absolute, models where inputs vary, humans where judgement carries liability.
- 01
Trigger. An event arrives: an invoice, an email, a sensor reading.
- 02
Match. The system checks it against explicit rules or a model's score.
- 03
Execute. The matching workflow runs its steps in order.
- 04
Log. Every action is recorded, so any run can be replayed.
- 05
Exception. Anything unmatched goes to a human queue, never guessed.
Terms that live nearby.
Agentic Workflow
An agentic workflow is a business process whose steps are executed by AI agents: they plan the work, call tools, read results and decide the next move, instead of following a fixed script that breaks the first time reality differs.
ReadAI Agent
An AI agent is software that pursues a goal on your behalf: it reads the situation, plans the next step, acts through tools (email, calendars, databases, APIs) and checks the result before continuing, instead of answering one question and stopping.
ReadOrchestration
Orchestration is the coordination layer of a multi-agent system: one orchestrator receives a goal, splits it into tasks, assigns them to specialised agents, collects their outputs, resolves conflicts and assembles the final result.
Read§ 04
Want this running in your stack?
We design and ship AI systems with permissions, logs and human approval. It starts with a 30-minute scoping call.