Skip to content

Courses / On-demand courses

On demandRecorded by an instructor, graded by Nova

Building with the Claude API

Tool use, streaming, caching, batches, and a shipped application.

recorded hours
12
modules, in order
8
deployed projects
4
graded checkpoints
7

Who it is for, and what you receive.

Developers in Python or TypeScript who want to ship a production application on the Claude API.

Before you start

Python or TypeScript.

Skills

  • Claude API
  • tool use
  • streaming
  • caching
  • evals
  1. 1

    The recorded sessions

    Taught by an instructor who does the work, taken in order at your own pace, yours for twelve months.

  2. 2

    Graded work after every module

    Exercises and projects marked by Nova against a rubric you can read, with what you did well and what to fix.

  3. 3

    The projects

    Deployed and graded, each one on your record with its repository.

  4. 4

    Your hiring plan

    The same six-part plan the bootcamps use, run with the career agent.

  5. 5

    The record and the certificate

    Every grade at square1ai.com/u/{handle}; a credential ID that resolves at square1ai.com/verify.

  6. 6

    Nova as your tutor

    Help that is about your actual work, because it has read all of it.

The content plan, module by module.

12 recorded hours from an instructor, taken in order at your own pace. Nova grades the work at the end of each module.

  1. 1

    The API and the SDKs

    • Keys and clients
    • A first request
    • Errors and retries

    Graded

    A first request with error handling

    60 min

  2. 2

    Messages, system prompts and context

    • Roles
    • System prompts
    • Context management

    Graded

    Nothing to submit; watch and take notes

    60 min

  3. 3

    Tool use

    • Defining tools
    • The tool loop
    • Validation

    Graded

    An assistant with three tools

    120 min

  4. 4

    Streaming and the UI

    • Server-sent events
    • A streaming chat
    • Cancellation

    Graded

    A streaming chat interface

    90 min

  5. 5

    Prompt caching and batches

    • What caches
    • Measuring savings
    • Batch jobs

    Graded

    A cost comparison with caching on

    90 min

  6. 6

    Files, vision and documents

    • Images
    • PDFs
    • Document question answering

    Graded

    A document question-answering feature

    90 min

  7. 7

    Evals and safety

    • An eval suite
    • Guardrails
    • Logging

    Graded

    An eval suite for the assistant

    90 min

  8. 8

    Project: ship it

    • Deploy
    • Monitor
    • Cost

    Graded

    The application, deployed, with its evals

    120 min

The projects.

Each is deployed and graded by Nova against a rubric you can read before you start.

  1. 1

    A tool-using assistant

    An assistant with three tools.

    You hand in

    • Assistant
    • Tools
    • Tests

    The rubric requires

    All three tools called correctly on a test set.

  2. 2

    A streaming interface

    A chat interface that streams.

    You hand in

    • UI
    • Streaming backend

    The rubric requires

    Tokens stream and cancellation works.

  3. 3

    A document feature

    Answer questions over uploaded documents.

    You hand in

    • Upload
    • Question answering
    • Citations

    The rubric requires

    Answers cite the document.

  4. 4

    A deployed application

    Ship it with evals.

    You hand in

    • Deployed app
    • Eval suite
    • Cost report

    The rubric requires

    Deployed with a passing eval suite.

What you can do at the end.

A production application on the Claude API and four graded projects on your record.

  1. 1

    Make requests with the SDKs with proper error handling.

  2. 2

    Design messages, system prompts and context windows.

  3. 3

    Build tool-using assistants and streaming interfaces.

  4. 4

    Use prompt caching and batches to cut cost.

  5. 5

    Handle files, images and documents.

  6. 6

    Evaluate and ship an application safely.

Roles this prepares you for

  • AI engineer
  • Full-stack engineer (AI)

No placement rate is shown, because there are no graduates to count yet. The roles above are what the projects are built for.

Your record at the end.

Every exercise and project is graded by Nova against a rubric you can read, and every grade is kept on one page an employer can open and run. This is what the programme writes to it.

Graded, line by line
Nova reads every submission against the brief and the rubric and returns a score, what you did well and what to fix.
Module by module
Each module ends in graded work; the next opens when you are ready, on your own schedule.
Nova remembers
Help is about your actual work, because the tutor has every submission and every failed exercise of yours.
One page an employer can run
Every grade and project at /verify. An employer opens it and runs the code.

Record, Building with the Claude API

Example

  1. Project

    A tool-using assistant

    All three tools called correctly on a test set.

    Graded
  2. Project

    A streaming interface

    Tokens stream and cancellation works.

    Graded
  3. Project

    A document feature

    Answers cite the document.

    Graded
  4. Project

    A deployed application

    Deployed with a passing eval suite.

    Graded
  5. Every module

    7 graded checkpoints

    Each module ends in work Nova grades line by line against a rubric you can read.

    Graded
  6. After

    Your hiring plan

    Target roles, the gap map, the proof to send, weekly actions and an interview log.

    Kept

The entries, not the grades: those are yours to earn. The page lives at /verify and an employer needs no account to open it.

6 entries, at your own pace. One email when this course opens.

No account, no card. One email when it opens; we never sell before it exists.

How we help you find a job.

Proof, not a certificate: the projects you deployed are the thing you show, and the tools below are yours to use.

  1. 1

    Your hiring plan

    The same six-part plan the bootcamps use: target roles, the gap map, the proof to send, weekly actions, an interview log, the outcome. You run it with the career agent.

  2. 2

    A record an employer can run

    Your graded projects on /verify. An employer opens it and runs the code.

  3. 3

    The career agent

    Paste a real job posting at /career and it maps the role to your graded work and what to do next.

  4. 4

    The roles directory

    Every role we prepare people for, what it pays and what it asks, at /roles.

  5. 5

    A path to the live cohort

    If you want the instructor, the gates and the hiring sprint, the bootcamp on the same subject is one waitlist away.

One email when this course opens.

Recorded by an instructor who does this work, graded by Nova. The waitlist hears the date and the price first, and nothing is charged before it exists.

No account, no card. One email when it opens; we never sell before it exists.