12.05
Red-team the obvious modes
You run the known attacks on your own product as a written plan, accept that a clean run proves risk and not safety, and keep an incident runbook for the quiet degradation that no outage alarm will catch.
- Defining AI Guardrails and Agent Security
- 20 min
- Pro
Who's hiring for this skill
70 companies have live AI-PM roles that ask for skills taught in this lesson.
- Anthropic
- Scale AI
- Glean
- Nebius
- Datadog
- OpenAI
- Stripe
- Braze
- Intercom
- Okta
- GitLab
- Gusto
- Snowflake
- Writer
- Cohere
- Harvey
- Brex
- Coinbase
- CoreWeave
- Coursera
- Databricks
- JetBrains
- Legora
- Mercor
- Typeface
- Vanta
- Decagon
- Lovable
- Perplexity
- 1Password
- Asana
- Box
- Deepgram
- Docker
- Eleven
- ElevenLabs
- Fireworks
- Grafana
- Klaviyo
- Lyft
- Notion
- Rogo
- Snorkel AI
- Speak
- Temporal
- Ramp
- Replit
- Sierra
- Vercel
- Arize AI
- Calendly
- Cerebras
- Cresta
- Customer.io
- Discord
- Drata
- Eve
- LangChain
- Lightning Ai
- Luma AI
- Mistral
- Nabla
- Plaid
- Spotify
- Synthesia
- Thinking Machines
- Together AI
- Vapi
This subchapter is part of the paid course.
Its video, its written lesson, its exercise and its grading are all included on any plan. The free subchapters stay free either way.