AISEOCourse.academy Module 8

Module 08 · Lesson 2 of 4

Automation Without Nonsense

About 11 minutesPrerequisite: Lesson 8.1
After this lesson you candecide what belongs in automation and what never will, build the first small automation in an afternoon, and spot the three failure modes that manufacture false confidence.

Automation is a servant of the method, and the method is the query set, the run, the log and the review. Automate the parts of that loop which are mechanical and mistake-prone. Keep your own eyes on everything that requires judgement. Most automation disasters come from swapping those two.

The honest split

Automate itNever automate it
Issuing the query set on schedule, in fixed conditionsChoosing the query set (a human decided what matters)
Capturing answers and cited domains into the logLabelling context and sentiment (fixed vocabularies, human eyes)
Diffing this run against last runDeciding what a change means
Alerting when thresholds from lesson 7.3 are crossedThe monthly interpretation sentences
Compiling the report numbersThe verdicts on experiments
Flagging pages with stale last-reviewed datesWhether a page deserves update, merge or retire

The left column buys back your time for the right column. That is the only justification for any automation: it converts hours of mechanical work into minutes, so the judgement work actually happens. Automation that removes the judgement instead is how an agency ends up confidently reporting nonsense for six months.

DefinitionA run bot is a script that executes your fixed query set under fixed conditions and files the raw results. It changes who does the typing, not what the method is.

The three failure modes

  1. Silent drift: a surface changes, the bot keeps capturing the wrong element, and the log fills with plausible-looking junk. Defence: a monthly manual spot-check of a few rows against the real surface, forever.
  2. Conditions creep: automation quietly varies what manual runs held constant (session state, location, personalisation), so old and new rows are not comparable. Defence: when automation starts, start a new baseline; never mix regimes in one trend line.
  3. Confidence laundering: numbers produced by a machine feel more true, so weak signals get reported as findings. Defence: the interpretation rules stay human and the caveats stay in the report, whatever produced the counts.

The afternoon build

Your first automation should be the smallest useful one: the run diff. Take this week's log and last week's, and produce a short list of what changed: new cited domains, vanished domains, queries where the answer-changed column flipped. A spreadsheet formula version is fine; a script is fine; an agency licence is fine. The point is that Friday's ten minutes of diffing becomes one minute, and you never skip it again.

Worked example: the diff that earns its keep (illustrative)
  1. Friday, run 14 logged. The diff fires: two new domains cited on the pricing cluster; your citation on one query vanished; answer-changed on four queries.
  2. You open the four answers yourself (that part stays human) and see a new comparison roundup is feeding the cluster.
  3. Action: one new opportunity card, one investigation note in the log. Time elapsed: twelve minutes, most of it reading.

The bot did the noticing; you did the thinking. That division of labour is the entire lesson.

Workbench 8.2
  1. List every mechanical step in your weekly run. Circle what repeats identically each time; that is your automation candidate list.
  2. Build or configure the run diff (spreadsheet or script) this week and use it on your next two runs.
  3. Schedule the monthly manual spot-check of automated rows; put it next to the roll-up so it actually happens.
  4. Write one sentence in your methodology note: what this automation captures, under what conditions, started when. Future-you needs the regime boundary.
Self-check
What is the only good reason to automate a task?
To reclaim time from mechanical work so the judgement work (interpretation, labelling, verdicts) actually happens. Automation that replaces judgement manufactures confident nonsense.
Why start a new baseline when automation begins?
Because automated runs rarely hold exactly the conditions manual runs did. Mixing regimes in one trend line compares apples to a different sampling method; a fresh baseline keeps the series honest.
What defends against silent drift?
A permanent monthly ritual: a human manually checks a few logged rows against the real surface and signs off. Surfaces change; bots do not notice.
Key principleAutomate the runs, never the judgement: the bot notices, you think.

Sources used in this lesson
Google Search Central: AI features and your website