Skip to content
Forward Deployed
Forward Deployed
Engineering Foundations for AI: sections and modules
T1.2Partly ready

APIs and backend for AI apps

Build a production-shaped API around a model call.

About 4 h 55 min: 40 min reading + 4 h 15 min practice · 7 lessons

Scope
HTTP, FastAPI, streaming, auth basics
Prerequisites

Lessons

Start module
7 lessons
  1. 1
    Keep the Request Path Free

    6 min

  2. 2
    Structure the Service and Decide What to Build

    6 min

  3. 3
    Define the API Contract With Typed Schemas

    5 min

  4. 4
    Protect the Endpoint From Abuse and Cost

    5 min

  5. 5
    Build a Streaming Chat Endpoint

    6 min

  6. 6
    Cache Answers Without Serving Wrong Ones

    5 min

  7. 7
    Practise API and Backend Interview Questions

    7 min

Also used in this module

Lessons taught in another module that this one builds on.

Practise and Check

Deliverable
P1 Tested inference API
Assessment
P1 rubric
Interview probe
Design the API for an LLM feature
Common mistakes
  • No timeouts or retries on model calls

Your Progress

How confident are you with this module?

1 means "I could not explain it yet"; 5 means "I could teach it". Rate again any time.

 

Saved in this browser when you leave the box.

Related Modules