[Skip to content](https://academy.innguma.com/en/ai-applied-to-intelligence/#contenido)

Learning path 03

# AI applied to intelligence

Find out what to delegate, how to verify results and how to build reproducible instructions.

≈ 2 h 35 min · Beginner to intermediate

The question it answers

How do you use AI without mistaking fluency for evidence?

**What you will take away** 

A delegation and review protocol for producing reproducible analyses.

[Start with 3.1](https://academy.innguma.com/en/ai-applied-to-intelligence/what-generative-ai-can-and-cannot-do/)

The Prompt Factory generates instructions for another AI; it does not analyse documents or generate final products.

## Five lessons

Recommended order. You can start with any of them.

1.  [3.1 What generative AI can and cannot do Which part of the analyst's work can we delegate to AI, and which part should we not delegate without controls? ≈ 25 min · Beginner · You take away a "task / autonomy / evidence / validation" sheet that you can add to your monitoring plan](https://academy.innguma.com/en/ai-applied-to-intelligence/what-generative-ai-can-and-cannot-do/)
2.  [3.2 Researching with AI in a verifiable way How do you turn AI-assisted research into a file that someone else can audit? ≈ 35 min · Intermediate · You take away brief evidence file and a list of prioritised gaps](https://academy.innguma.com/en/ai-applied-to-intelligence/researching-with-ai-in-a-verifiable-way/)
3.  [3.3 Classifying and structuring information How do you turn heterogeneous documents into comparable records without hiding classification errors? ≈ 30 min · Intermediate · You take away data dictionary and disagreement log](https://academy.innguma.com/en/ai-applied-to-intelligence/classifying-and-structuring-information/)
4.  [3.4 Analysing relationships and producing intelligence How do you move from a collection of records to strategic hypotheses without turning correlations into facts? ≈ 35 min · Intermediate · You take away hypothesis matrix and draft briefing with uncertainties](https://academy.innguma.com/en/ai-applied-to-intelligence/analysing-relationships-and-producing-intelligence/)
5.  [3.5 Agents, tools, persistent knowledge and interoperability What is the difference between asking an assistant, running a task with tools and sustaining a corporate intelligence system? ≈ 30 min · Intermediate · You take away architecture diagram and governance checklist](https://academy.innguma.com/en/ai-applied-to-intelligence/agents-tools-persistent-knowledge-and-interoperability/)

Lab practice · L05

## Evidence auditor

Output: Claims classified as fact, inference, error or no evidence. No sign-up required.

- [Open the tool](https://academy.innguma.com/en/lab/evidence-auditor/)
- [All activities](https://academy.innguma.com/en/lab/)

## Learning paths

- [If you come from… 02 · Designing a monitoring system](https://academy.innguma.com/en/designing-a-monitoring-system/)
- [If you want to go on… 05 · Analysis, foresight and anticipation](https://academy.innguma.com/en/analysis-foresight-and-anticipation/)
- [Or also… 04 · Method, governance and UNE 166006](https://academy.innguma.com/en/method-governance-and-une-166006/)

**Download** 

-   [R07 · AI output audit](https://academy.innguma.com/en/library/ai-output-audit/)
-   [R08 · AI delegation and use agreement](https://academy.innguma.com/en/library/ai-delegation-and-use-agreement/)
-   [R09 · Classification dictionary](https://academy.innguma.com/en/library/classification-dictionary/)
-   [R10 · Matrix of hypotheses and alternatives](https://academy.innguma.com/en/library/matrix-of-hypotheses-and-alternatives/)

[Library →](https://academy.innguma.com/en/library/)

**References and review** 

Every lesson states its references and its limits.