Theme

Source

Size

Text width

Between the lines

Control accent

0 out of 00%
TRACK 02

Delegate well

Intention, context, data, and success criteria: what the agent needs to know before starting.

2modules
12topics
105 minestimated time with practice
Practicalprogressive level
0 out of 00%
IntentionContextReliable dataSuccess criteria
Intention, context, data, and success criteria: what the agent needs to know before starting.

Track map

2.1~50 min

🧭 Intention and context

Clear mission, lean context

2.2~55 min

🧭 Reliable data and success criteria

The right source, properly measured

Detailed content

MODULE 2.1

Intention and context

Tell the agent what to achieve, why it matters, and what it needs to know on day one.

0 out of 00%

What it is

Intention is the first thing an agent needs to receive: what should be achieved and why it matters. The task tells what to do; the why tells what to protect when a case shows up that you didn’t anticipate. In the Agent Sheet, this is the field “What do you want to take out of your hands? Why does that matter?”. An agent with the right task and no why executes well the wrong thing.

Why learn

No instruction covers all cases. When a doubt arises, the agent needs a criterion to choose, and the why is that criterion. In a clinic, “confirming consults” without a reason turns into sending a message and done; with “30% of patients don’t show up and the schedule stays empty,” it understands that the important thing is knowing who won’t come in time to fit someone else in.

Key concepts

  • Task: the concrete action, with a verb and an object.
  • Why: the real problem the task solves.
  • Outcome: what changes when it goes right.
  • Priority: what to protect when there’s doubt.
Study this topic and do the exercise →

What it is

Scope is the size of the work you deliver: where the task starts and where it ends. “Taking care of my business” isn’t a task—it’s a whole job with dozens of different decisions. A good agent gets only one task, with clear input and output, like “check the month’s documents and list what’s missing.”

Why learn

When an agent does five things and gets some wrong, you don’t know which part failed. With one task per agent, each mistake has an address, each test is simple, and each autonomy level can be different: what only answers questions can have more freedom than what handles money.

Key concepts

  • Job: the big whole, like serving customers.
  • Process: one part with a beginning and an end, like post-sale follow-up.
  • Task: a repeatable action, like informing an order status.
  • Delivery: what comes out at the end, like the message sent.
Study this topic and do the exercise →

What it is

Every real task has priorities that clash: speed versus accuracy, friendliness versus firmness, doing everything versus doing it right. The tie-break rule is a sentence that says which priority wins when the two can’t both fit together. It’s written in the instruction, not in your head.

Why learn

Without a tie-break, the agent chooses on its own, and the choice changes from day to day. A support agent who answers quickly with an invented deadline pleases today and creates complaints tomorrow. Writing the order of priorities makes behavior predictable and easier to correct.

Key concepts

  • Clash: two good things that don’t fit together.
  • Winner: the priority that wins, written out in full.
  • Action on doubt: what to do when no rule resolves it.
  • Review: adjust the rule when a real case shows it failed.
Study this topic and do the exercise →

What it is

Context is everything the agent needs to know about your environment to decide well: house rules, tone, schedules, what you never say to the customer. The best way to gather this is to imagine the first day of a new employee—what, in a company, is called onboarding, the integration of whoever is arriving. What you’d explain at the door, the agent also needs to hear.

Why learn

The agent doesn’t know your clinic, your store, or your team. Without the house rules, it fills the gap with the internet’s default: it messages on Saturday, calls the patient for you, promises what it can’t. A short block of rules prevents most of those silly mistakes.

Key concepts

  • House rules: what always applies here.
  • Tone: how to speak to people.
  • Schedules: when it can act and when it can’t.
  • Never say: topics that aren’t theirs.
Study this topic and do the exercise →

What it is

More context isn’t better context. Context engineering is choosing what goes into the agent’s instruction and cutting the rest. The cutting question is simple: does this information change any of its decisions? If it doesn’t, it goes out.

Why learn

Too-long instructions hide important rules in the middle of text that doesn’t matter, and the agent starts giving the same weight to the company’s history and the rule about not talking about price. A lean context is easier to read, test, and fix when something goes wrong.

Key concepts

  • Gather: list everything that seems relevant.
  • Ask: does it change any decision of the agent?
  • Cut: remove what changes nothing.
  • Test: check whether it still decides correctly without what was removed.
Study this topic and do the exercise →

What it is

Adjectives like “cordial,” “professional,” and “objective” mean different things to each person. An example shows exactly what you want. The simplest technique is to put in the instruction a good response and a bad response for the same case, explaining why one is good and the other isn’t.

Why learn

An agent copies patterns much better than it interprets adjectives. A model answer teaches tone, length, the order of information, and what not to say—all at once. And the bad answer shows the mistake you fear most, which usually helps avoid repeating it.

Key concepts

  • Case: a real and common situation.
  • Good answer: the text the way you want it.
  • Bad answer: the common error, in full.
  • Reason: one line that explains what differentiates the two.
Study this topic and do the exercise →
View Complete →
MODULE 2.2

Reliable data and success criteria

Define where the truth comes from, what to do when it’s missing, and how to know when the work is done.

0 out of 00%

What it is

The source of truth is the place you declare as official for a type of information: the system’s schedule, the orders dashboard, the table of current prices. Anything that comes from elsewhere doesn’t count—even if it looks correct. The Agent Sheet asks for both things: what counts and what doesn’t.

Why learn

No agent is better than the data it works with. If it can use an old spreadsheet, a customer screenshot, and a paper note, each response comes from a different place and you can’t verify anything. A declared source makes every error traceable: you know where to look.

Key concepts

  • Counts: the official source, with a name and location.
  • Doesn’t count: similar sources that you forbid.
  • Update: who keeps the source current.
  • Traceability: the agent says where it got each piece of data from.
Study this topic and do the exercise →

What it is

Even with an official source, the data clashes: the system says one thing, the client swears another, and last week’s spreadsheet a third. The conflict rule is the sentence that explains who has authority in those cases and what to do with the discrepancy. Most important: the conflict must be recorded, not resolved in silence.

Why learn

A conflict resolved in silence becomes an invisible error: the agent picks one version, moves on, and nobody knows. When it’s recorded, the conflict becomes useful information. If the system’s inventory and the kitchen count disagree every week, the problem isn’t the agent—it’s the counting process.

Key concepts

  • Hierarchy: which source wins over which.
  • When in doubt: what to do if the official one seems wrong.
  • Record: note the conflict in the report.
  • Correction: fix the source that was wrong.
Study this topic and do the exercise →

What it is

Hallucination is the name given when the AI produces false information that looks real: a time that doesn’t exist, a law nobody wrote, a guessed price. It doesn’t lie on purpose; it completes the text with what seems likely. That’s why the instruction needs an explicit rule: when something is missing, the agent must warn you and not invent.

Why learn

Invented data is the most dangerous error because it doesn’t look like an error. A guessed delivery deadline sounds as confident as a real one. Telling the agent what to do when information is missing—using a concrete action—turns the guess into a warning you can actually handle.

Key concepts

  • Hallucination: a false answer that looks right.
  • Trigger: a question with no data in the source.
  • Rule: warn and don’t complete.
  • Concrete action: mark as pending, ask for the data, or pass it to you.
Study this topic and do the exercise →

What it is

Acceptance criteria, or definition of “ready,” is the description of what the result looks like when the work is done well. The Ficha question is “what does a day look like when this was perfect?” The answer must be observable: something you can see or count, not something you feel.

Why learn

Without a definition of “ready,” the agent stops when it thinks it’s done—and it always thinks it is. “I confirmed the consults” could mean sending three messages. With an observable criterion, it knows when the task is truly finished, and you know what to check.

Key concepts

  • Result: what exists at the end, in full.
  • Observable: something you can see or count.
  • Deadline: until when it needs to be ready.
  • Exceptions: what goes to you, and doesn’t count as a failure.
Study this topic and do the exercise →

What it is

A metric is a number that tracks the work over time: how many messages were sent, how many people replied, how many cases came to you. The rule is to count, not to guess. A good simple metric fits in the daily report and anyone on the team can check it.

Why learn

First impressions can mislead: a day with loud complaints can seem worse than it really was. Simple numbers show trends. If the cases passed to you decrease week after week, the agent is improving; if they rise, some rule needs adjustment. And it’s with those numbers that you later decide whether it can be given more autonomy.

Key concepts

  • Volume: how much was done.
  • Result: how much went well.
  • Exceptions: how much came to you.
  • Errors: how much went wrong, noted without hiding.
Study this topic and do the exercise →

What it is

Before running an agent, you test the three points where agents usually fail: missing information, a prohibited request, and an alarm situation. These are the same three tests that the Agent Sheet generates to prepare for each sheet. If it makes any mistake, you adjust the instruction and repeat.

Why learn

An agent that handles normal cases well can fail badly on difficult cases—and difficult cases are the ones that cause damage. Testing first costs ten minutes. Finding out later, with a real client, costs much more: an improper refund, a made-up date, a complaint answered in the wrong tone.

Key concepts

  • Test 1: missing or contradictory information; it warns you and doesn’t make things up.
  • Test 2: prohibited request; it refuses and passes it to you.
  • Test 3: alarm situation; it stops and calls you.
  • Bonus: compare a run with the definition of “ready.”
Study this topic and do the exercise →
View Complete →
← All learning tracksNext learning track →