84. AI processing of sheet and document information
Module 17 · 20 minutes · Lesson 83; earlier service and JavaScript fundamentals
Open Interactive LessonDiscover
How can you use ai processing of sheet and document information without changing the wrong data?
- Explain ai processing of sheet and document information in your own words
- Trace the actual console result from the source
- Repair the supplied failing operation and verify the result
Predict
Which values or resources will change, and which should stay unchanged? Write your prediction before execution.
Understand
Send only the minimum necessary text and preserve a source identifier for review. Do not silently replace source records with model output. Store derived results in a separate reviewed location and validate them first. This lesson combines a real local document read with an explicitly authored classification response.
Example 1: Working automation
The source identifier ties the proposed output to the actual document without pretending the fixture analyzed it.
function main() {
const text = DocumentApp.openById("template").getTabs()[0].asDocumentTab().getBody().getText();
const result = {category: "support", sourceId: "template", reviewed: false};
console.log(text.length > 0);
console.log(JSON.stringify(result));
}Important line explanations
- Line 1: function main() {
- Define a named block of instructions. Run Script calls main; helpers run only when called.
- Line 2: const text = DocumentApp.openById("template").getTabs()[0].asDocumentTab().getBody().getText();
- Call the named Workspace service. Locally this invokes a documented adapter; in Google it may require authorization and create persistent changes.
- Line 3: const result = {category: "support", sourceId: "template", reviewed: false};
- Initialize a local binding. const prevents reassignment of that binding, but does not freeze a referenced object.
- Line 4: console.log(text.length > 0);
- Record diagnostic evidence. A log does not grant permissions or prove a later side effect succeeded.
- Line 5: console.log(JSON.stringify(result));
- Record diagnostic evidence. A log does not grant permissions or prove a later side effect succeeded.
- Line 6: }
- Close the current block. Indentation makes scope and the function boundary visible.
Exact expected output and resource
{
"logs": [
"true",
"{\"category\":\"support\",\"sourceId\":\"template\",\"reviewed\":false}"
],
"error": null,
"resource": "logs",
"value": null
}Example 2: Investigate a reproducible failure
Predict the effect of sourceId: "unrelated" and identify the first mismatch. This example is intentionally faulty.
function main() {
const text = DocumentApp.openById("template").getTabs()[0].asDocumentTab().getBody().getText();
const result = {category: "support", sourceId: "unrelated", reviewed: false};
console.log(text.length > 0);
console.log(JSON.stringify(result));
}Important line explanations
- Line 1: function main() {
- Define a named block of instructions. Run Script calls main; helpers run only when called.
- Line 2: const text = DocumentApp.openById("template").getTabs()[0].asDocumentTab().getBody().getText();
- Call the named Workspace service. Locally this invokes a documented adapter; in Google it may require authorization and create persistent changes.
- Line 3: const result = {category: "support", sourceId: "unrelated", reviewed: false};
- Initialize a local binding. const prevents reassignment of that binding, but does not freeze a referenced object.
- Line 4: console.log(text.length > 0);
- Record diagnostic evidence. A log does not grant permissions or prove a later side effect succeeded.
- Line 5: console.log(JSON.stringify(result));
- Record diagnostic evidence. A log does not grant permissions or prove a later side effect succeeded.
- Line 6: }
- Close the current block. Indentation makes scope and the function boundary visible.
Exact expected output and resource
{
"logs": [
"true",
"{\"category\":\"support\",\"sourceId\":\"unrelated\",\"reviewed\":false}"
],
"error": null,
"resource": "logs",
"value": null
}Example 3: Separate setup from execution and inspect repeat behavior
Call the same named operation twice. Compare outputs and resource counts to learn whether this operation is idempotent. Repeated creation is deliberately visible; real exports require a rerun policy.
function lessonAction() {
const text = DocumentApp.openById("template").getTabs()[0].asDocumentTab().getBody().getText();
const result = {category: "support", sourceId: "template", reviewed: false};
console.log(text.length > 0);
console.log(JSON.stringify(result));
}
function main() {
lessonAction();
lessonAction();
}Important line explanations
- Line 1: function lessonAction() {
- Define a named block of instructions. Run Script calls main; helpers run only when called.
- Line 2: const text = DocumentApp.openById("template").getTabs()[0].asDocumentTab().getBody().getText();
- Call the named Workspace service. Locally this invokes a documented adapter; in Google it may require authorization and create persistent changes.
- Line 3: const result = {category: "support", sourceId: "template", reviewed: false};
- Initialize a local binding. const prevents reassignment of that binding, but does not freeze a referenced object.
- Line 4: console.log(text.length > 0);
- Record diagnostic evidence. A log does not grant permissions or prove a later side effect succeeded.
- Line 5: console.log(JSON.stringify(result));
- Record diagnostic evidence. A log does not grant permissions or prove a later side effect succeeded.
- Line 6: }
- Close the current block. Indentation makes scope and the function boundary visible.
- Line 7: function main() {
- Define a named block of instructions. Run Script calls main; helpers run only when called.
- Line 8: lessonAction();
- Follow this operation using the surrounding named values. Compare the actual recorded state with the lesson’s specific explanation below.
- Line 9: lessonAction();
- Follow this operation using the surrounding named values. Compare the actual recorded state with the lesson’s specific explanation below.
- Line 10: }
- Close the current block. Indentation makes scope and the function boundary visible.
Exact expected output and resource
{
"logs": [
"true",
"{\"category\":\"support\",\"sourceId\":\"template\",\"reviewed\":false}",
"true",
"{\"category\":\"support\",\"sourceId\":\"template\",\"reviewed\":false}"
],
"error": null,
"resource": "logs",
"value": null
}Example 4: Add a diagnostic boundary around the operation
Observe start, successful completion or a rethrown failure. This optional professional pattern adds error context without swallowing the error or rolling back changes.
function lessonAction() {
const text = DocumentApp.openById("template").getTabs()[0].asDocumentTab().getBody().getText();
const result = {category: "support", sourceId: "template", reviewed: false};
console.log(text.length > 0);
console.log(JSON.stringify(result));
}
function main() {
console.log("Start: AI processing of sheet and document information");
try { lessonAction(); console.log("Completed operation"); }
catch(error) { console.error("Failed operation: " + error.message); throw error; }
}Important line explanations
- Line 1: function lessonAction() {
- Define a named block of instructions. Run Script calls main; helpers run only when called.
- Line 2: const text = DocumentApp.openById("template").getTabs()[0].asDocumentTab().getBody().getText();
- Call the named Workspace service. Locally this invokes a documented adapter; in Google it may require authorization and create persistent changes.
- Line 3: const result = {category: "support", sourceId: "template", reviewed: false};
- Initialize a local binding. const prevents reassignment of that binding, but does not freeze a referenced object.
- Line 4: console.log(text.length > 0);
- Record diagnostic evidence. A log does not grant permissions or prove a later side effect succeeded.
- Line 5: console.log(JSON.stringify(result));
- Record diagnostic evidence. A log does not grant permissions or prove a later side effect succeeded.
- Line 6: }
- Close the current block. Indentation makes scope and the function boundary visible.
- Line 7: function main() {
- Define a named block of instructions. Run Script calls main; helpers run only when called.
- Line 8: console.log("Start: AI processing of sheet and document information");
- Record diagnostic evidence. A log does not grant permissions or prove a later side effect succeeded.
- Line 9: try { lessonAction(); console.log("Completed operation"); }
- Record diagnostic evidence. A log does not grant permissions or prove a later side effect succeeded.
- Line 10: catch(error) { console.error("Failed operation: " + error.message); throw error; }
- Record diagnostic evidence. A log does not grant permissions or prove a later side effect succeeded.
- Line 11: }
- Close the current block. Indentation makes scope and the function boundary visible.
Exact expected output and resource
{
"logs": [
"Start: AI processing of sheet and document information",
"true",
"{\"category\":\"support\",\"sourceId\":\"template\",\"reviewed\":false}",
"Completed operation"
],
"error": null,
"resource": "logs",
"value": null
}Build and test
Repair the supplied script so that: The source identifier ties the proposed output to the actual document without pretending the fixture analyzed it. Preserve other source data. Checks compare observable output and the named resource, not exact source text.
function main() {
const text = DocumentApp.openById("template").getTabs()[0].asDocumentTab().getBody().getText();
const result = {category: "support", sourceId: "unrelated", reviewed: false};
console.log(text.length > 0);
console.log(JSON.stringify(result));
}Graduated hints
Hint 1
Inspect the operation containing sourceId: "unrelated". Compare it with the stated rule and the first mismatch.
Hint 2
The repair concerns sourceId: "template". Change only the relevant argument, operator or method; rerun with fresh input.
Hint 3
The reference uses sourceId: "template" where the broken source uses sourceId: "unrelated". Explain why before applying it.
Reference solution
function main() {
const text = DocumentApp.openById("template").getTabs()[0].asDocumentTab().getBody().getText();
const result = {category: "support", sourceId: "template", reviewed: false};
console.log(text.length > 0);
console.log(JSON.stringify(result));
}Explain and reflect
Which operation proves the intended result in ai processing of sheet and document information? Which wrong input would expose a weakness, and what would remain unchanged?
Adapt the calculation or validation to a second realistic case. Write its expected result before running. Demonstrate one invalid case and explain whether the side effects should be rolled back or retried.
Troubleshooting
If the console is empty, inspect the logs preview: this script may work through state changes. If the function is missing, select main. For a service error inspect the first failed timeline entry and its arguments. Use Manual unless investigating a trigger. Changing input data also changes the expected result; restore sample data before the authored checks.
Knowledge check
Explain the key method or operator. Give an exact output for a second input, plus one invalid case. Verify the result in the interactive lesson; written explanations need self or educator review.
Optional AI practice
Explain this concept using the source above. Help implement one small extension and define its tests. Review/debug the source using its actual expected output; cite real method references and never claim execution.