AI learning paths

Choose AI courses that match your next step

Compare foundations, coding, API development, and evaluation without confusing course completion with job readiness.

Start here if: Learners deciding between Claude Academy, general programming courses, and applied AI training.

Try the relevant skills check
Your starting point

Choose a course by the task you want to perform next and the prerequisites you already meet. An introductory AI course, a programming course, and an application-development course solve different learning problems.

The providers below publish their own learning material and completion rules. FDE Benchmark links to those resources and supplies separate practice ideas. Listing a resource does not imply a partnership, endorsement, or shared credential.

A sequence you can use

What to study, in order.

  1. 01

    Select a concrete learning outcome

    Study
    Distinguish using AI at work, writing programs, integrating model APIs, and delivering a customer implementation.
    Practice
    Write one sentence describing what you want to do without assistance, such as checking a report or debugging an API request.
    Keep as evidence
    Keep that sentence and a small example task you will repeat after studying.
  2. 02

    Check the prerequisites before enrolling

    Study
    Read the provider’s audience and requirements. API courses may assume Python, JSON, account access, or cloud familiarity.
    Practice
    Try a small prerequisite exercise. Can you read a file, handle an exception, and explain a JSON response?
    Keep as evidence
    Record the gap you found and choose a foundation resource before advancing if necessary.
  3. 03

    Pair study with original work

    Study
    Complete exercises under the provider’s rules. Use coding assistance only in ways those rules permit.
    Practice
    Build a separate project using a new problem and your own sample data. Change a requirement and investigate one failure.
    Keep as evidence
    Keep source or workflow instructions, checked results, and an explanation of your decisions.
  4. 04

    Evaluate the return on the course

    Study
    Review what the course actually assessed and what your project still cannot demonstrate.
    Practice
    Repeat your starting task, ask for feedback, and choose the next learning gap. Avoid enrolling in another course solely to accumulate badges.
    Keep as evidence
    Write a short before-and-after account with remaining weaknesses and one next action.

Which course should come first?

For everyday AI use, start with Claude Academy’s AI Fluency or OpenAI Academy’s AI Foundations. OpenAI’s catalog also offers Applied AI Foundations and Agents and Workflows as later options. For a first programming language, CS50 Python provides focused practice; CS50x offers broader computer-science and web foundations.

For existing developers, Building with the Claude API covers application integration and expects Python, JSON, and an API key. Microsoft’s generative AI application path expects programming and AI/Azure familiarity. Claude Code 101 teaches a coding tool and assumes basic editor and command-line familiarity. It serves a different purpose from learning programming itself.

Describe completion accurately

A provider’s completion badge or certificate records the achievement that provider defines. Microsoft Learn distinguishes learning achievements from credentials; CS50 separates its OpenCourseWare from verified-certificate and academic-credit routes. Check current provider requirements before paying or making a claim on your résumé.

Present a course alongside work it helped you complete. Name the provider, exact course, completion status, and project contribution. A knowledge quiz does not independently verify production reliability, customer discovery, or engineering ownership.

Budget for practice separately

Free learning content can still involve paid software or usage. Claude’s API course needs an API key; cloud labs can consume resources. Microsoft’s current FAQ says Azure exercises require subscription access and former Learn sandboxes are unavailable. Check costs, limits, and cleanup instructions before running an exercise.

Build something reviewable

A course-to-capability evidence sheet

Choose one course and one practical goal. Create a compact record showing what you learned, what you built, what you checked, and what remains outside the evidence.

What to produce

  • Learning goal and prerequisite check.
  • Exact provider/course link and honest completion status.
  • Original work sample with verification results.
  • Remaining gaps and a justified next learning step.

Ask a reviewer

  • Can you perform the task on a new example?
  • Can you explain and fix an error?
  • Which ability does the course completion actually establish?
Markdown file · opens in any text editor
First-party resources

Courses and resources for this path.

Choose resources for the gap you are working on. Course access and access to paid products or cloud services are separate.

Claude Academy · Anthropic

AI Fluency: Framework & Foundations

How to choose suitable tasks, communicate intent, inspect AI outputs, and take responsibility for AI-assisted work.

For
People beginning to use AI, and experienced users improving their judgment.
Before you start
Designed for learners across experience levels; programming is not required for this learning path.
Access
Free course content. The provider lists a completion badge; that is separate from FDE Benchmark practice or employer assessment.
OpenAI Academy

AI Foundations

AI and language-model basics, useful instructions and context, output review, and responsible everyday use. The academy also offers Applied AI Foundations and Agents and Workflows for later practice.

For
People new to AI and ChatGPT.
Before you start
The academy identifies this course as a starting point for people new to AI.
Access
Follow the provider link for current enrollment and access details. Product plans and course participation are separate; no certification claim is made here.
Harvard University · CS50

CS50’s Introduction to Programming with Python

Python functions, conditions, loops, exceptions, libraries, tests, and files through exercises and a final project.

For
Beginners and learners who want a practical first programming language.
Before you start
With or without prior programming experience. The course supports working in a browser.
Access
OpenCourseWare is free. The edX verified-certificate route is separate. Follow the course’s own academic honesty rules when submitting work.
Harvard University · CS50

CS50’s Introduction to Computer Science

Algorithms, data structures, C, Python, SQL, and web fundamentals, followed by an original final project.

For
Learners seeking broader programming and computer-science foundations.
Before you start
With or without prior programming experience; allow time for substantial problem-solving practice.
Access
OpenCourseWare is free. Verified certificates and academic-credit routes have separate arrangements. Course work does not replace production experience.
Claude Academy · Anthropic

Claude Code 101

Coding-agent setup, context, permissions, project instructions, development workflows, and reviewing changes.

For
New and experienced developers learning to work with a coding agent.
Before you start
Basic familiarity with a code editor and command line; a supported Claude account or API key. Check the provider’s current account requirements.
Access
Free course content. Claude product access or API usage is separate. Understanding and checking the code remains part of the learner’s work.
Claude Academy · Anthropic

Building with the Claude API

API integration, structured outputs, evaluation, tool use, retrieval, agents, and implementation patterns.

For
Software engineers integrating AI into applications.
Before you start
Proficiency in Python, basic JSON knowledge, and access to an Anthropic API key.
Access
Free course content; API usage is separate. This is an application-development course, so complete programming foundations first if needed.
Microsoft Learn

Develop generative AI apps in Azure

Model selection and evaluation, chat applications, tools, grounding, and responsible implementation.

For
Developers and AI engineers working with Microsoft Foundry and Azure.
Before you start
Programming experience and familiarity with fundamental AI concepts and Azure services. The path is intermediate.
Access
Microsoft Learn training content is free. Azure exercises require subscription access; former Learn sandboxes are no longer available. Check resource costs before running labs.
OpenAI developer documentation

Evaluation best practices

Set evaluation objectives, choose representative cases, compare implementations, and calibrate automated grading with human review.

For
Developers and delivery teams assessing an AI feature.
Before you start
A defined task and examples of the outputs or behavior you want to assess.
Access
Public documentation, not a course or credential. Running model-based evaluations can incur API costs.

Common questions.

Is Anthropic Academy the same as Claude Academy?

The current official learning site is branded Claude Academy and identifies Anthropic’s education team. Older references may use Anthropic Academy. Use the current course link and exact course name when describing your learning.

Is there one certification that makes me an FDE?

The cited employer roles describe a combination of engineering, delivery, and customer work. This guide does not identify a universal FDE certification. Compare the requirements of your target roles and build relevant evidence.

Should I finish every course listed here?

No. Choose the resource that addresses your next gap, complete meaningful practice, and reassess. The catalog presents alternatives and foundations for different backgrounds, rather than a mandatory sequence for everyone.

Sources and editorial basis.

Original guidance and practice projects by LockedIn Labs. Provider references describe their own offerings; inclusion is not an endorsement of this site.

Put the next step into practice.

Try the role-specific scenarios, keep the feedback, and bring a work sample into guided training.

Explore guided training