💡 Stack-agnostic. This module uses Claude Code as a case study: the built-in WebFetch tool reads the page, then comes the analysis. In other stacks the pattern is the same: you need any page-reading tool your agent has (built-in or an MCP server, module 07). See module 03 for your stack.

⚡ Activation

💭 in your head · nothing to type

Catch one cycle from the last three days: you pulled something from the internet and delivered it somewhere else.

Don't picture it as "working at a computer." Picture it as a factory assembly line. The part (information) lands on the belt, passes station to station (read, extract, relay), and exits as a finished product at the other end.

Run that line in your head: how many stations? At which one does the belt slow down and a backlog starts forming?

👁 Reflection

💭 in your head · nothing to type

Hold that route in front of you — like a cartographer who just walked the terrain on foot.

At every bend they mark the map: "swamp here" (hard going), "firm road here" (easy). Look at your own route the same way: which stretches are manual-labor swamp, and which already move almost on their own?

Your pipeline today is the first map you won't need to walk twice. Which stretch do you chart first?

💡 Concept

Every automation = Trigger → Action

This is the foundational mental model:

Three questions before building a pipeline

1. Trigger: what kicks off the process? (you manually, a schedule, a new file, a webhook)
2. Action: what should happen? (scrape → analyze → save → notify)
3. Condition: when should it NOT run? (duplicates, rate limits, errors)