WEBVTT

1
00:00:00.000 --> 00:00:04.000
AI · Chapter 24: AI app safety
Check the AI features in your own app for missing safeguards before they ship.

2
00:00:04.000 --> 00:00:11.000
Step 1: Your app calls an LLM. Is it safe?
Skylos finds every LLM call and agent tool in your code, checks each one for safeguards, and scores it.

3
00:00:11.000 --> 00:00:19.800
Step 2: Find the AI features in your code
The new support assistant calls OpenAI. Skylos shows where, what feeds it and whether it can reach anything dangerous.

4
00:00:19.800 --> 00:00:31.400
Step 3: Check its safeguards
Each check passes or fails with a reason. Raw output is used without validation and the model name can change under you.

5
00:00:31.400 --> 00:00:41.500
Step 4: Send it to Skylos Cloud
skylos defend . --upload records the result, so the whole team sees it.

6
00:00:41.500 --> 00:00:48.500
Step 5: Every repository's AI app safety in one place
AI, then AI app safety: each repository's latest score, how many checks pass and how many AI features it has.

7
00:00:48.500 --> 00:00:56.500
Step 6: See what's missing and how to add it
Open a result: missing safeguards come first, each with the line and how to add it. What already passes is on the right.

8
00:00:56.500 --> 00:01:03.500
Step 7: Keep it current in CI
skylos cicd init --defend adds the check to CI, so every push to the default branch updates this page.

9
00:01:03.500 --> 00:01:10.500
Recap: skylos discover finds every LLM call and agent tool · skylos defend checks each one for safeguards · Missing safeguards come with how to add them · AI app safety shows every repository's score · Add it to CI with skylos cicd init --defend
Next: Guides at skylos.dev/guides
