Skip to main content
TIBLOGICS
← All tracks
Advanced

Building AI Apps and Agents

Build AI features and agents that hold up in production: tools, retrieval, evaluation, security and cost, done properly.

Length
About 23 hours: 12.5 of lessons, 11 hands-on
Modules
6
Lessons
27
Certificate
TIBLOGICS Certified AI App and Agent Builder

About 8 weeks at 3 hours a week

What you'll be able to do

  • Call model APIs from server code with correct messages, sensible parameters, retries with backoff and cost tracked from token usage
  • Get structured output you can trust, and design tools, agent loops and MCP connections with clear stop conditions and least privilege
  • Build retrieval-augmented generation with sound chunking, hybrid search, citations and access control, and evaluate retrieval and generation separately
  • Choose between workflows and agents, and add memory, human approval, guardrails and budgets so agents fail safely
  • Evaluate AI features with eval sets, calibrated judges and regression tests, and defend them against prompt injection and data leaks
  • Run a 30-door pre-launch security audit on an AI app: keys, server-side auth and ownership, webhooks, tool limits, agent configs, spending caps, log redaction and tested restores
  • Ship and operate AI features with the right architecture, cost controls, monitoring, incident response and a system map for handover

About this track

Getting a model to produce something impressive once takes an afternoon. Building an AI feature that is reliable, safe, affordable and understandable by the next developer is engineering, and that is what this track teaches. You will call models from code the professional way (messages, system prompts, tokens and cost, streaming, retries with backoff, keys kept on the server), get structured output you can trust, give models tools and run the agent loop with proper stop conditions, connect tools and data through the Model Context Protocol, handle images, documents and audio with a validated extraction pipeline, build retrieval-augmented generation with citations and access control, and decide when an agent is the right design at all. Then you will prove it works with eval sets and regression tests, defend it against prompt injection and data exfiltration, run a 30-door pre-launch security audit on the whole app (keys, access, input, webhooks, tools, agent configs, spending and recovery), and ship and operate it with sensible architecture, cost control, monitoring and handover. It is vendor-neutral, with examples from several providers and open-source models, and hands-on throughout: Code Studio labs where you build a retry-safe client, a JSON validator with repair, a tool-calling loop with a step budget and a mini RAG pipeline against mock models, plus design reviews and an evaluation plan. The capstone is a small AI feature or agent of your own, documented with an eval set, a security review, a cost estimate and a system map, reviewed by a person. Skills this track builds also appear in cloud AI engineer associate certifications and AI developer courses from model providers. This track is independent: it is not affiliated with any vendor and is not official exam preparation.

Who it's for: Developers and technical builders who are comfortable with basic JavaScript or Python and want to build reliable AI features and agents: product engineers adding AI to an app, technical founders, data and automation engineers, and solution builders.

Key takeaways

  • Building AI Apps and Agents is a self-paced online course from ARFA, the TIBLOGICS AI Academy, at advanced level.
  • About 23 hours: 6 modules and 27 lessons, with hands-on practice.
  • $897 once for lifetime access to this track, or every track for $89 a month.
  • Certificate: TIBLOGICS Certified AI App and Agent Builder, with a public verification link.
  • Available in English and French.

Curriculum

6 modules · 27 lessons · About 23 hours: 12.5 of lessons, 11 hands-on

What actually happens when your code calls a language model: messages and roles, system prompts, parameters, tokens and cost, streaming, and the errors, rate limits and retries every production call must handle, with keys kept on the server.

  • 1.1How a model call works: messages, roles and system promptsFree previewBuild a correct request to a chat model API, with a system prompt, a message history and the right roles.26 min
  • 1.2Parameters, tokens and what a call costsEstimate the cost of a model call from its token counts and choose sensible parameter values for a feature.27 min
  • 1.3Streaming and the user experienceDecide when to stream a model's response and handle streamed output correctly, including errors and cancellation.24 min
  • 1.4Errors, rate limits, retries and keeping keys server-sideHandle API errors with retries and exponential backoff, respect rate limits, and keep API keys out of front-end code.28 min

Module quiz: 80% to pass, unlimited retakes

Choose your plan

Own this track

Building AI Apps and Agents

$897one time

Pay once and keep lifetime access to this track: every lesson, lab and quiz, the final exam and the certificate.

Buy this track ($897 once)

All tracks

every track included

$89/month

Every track, current and future, with all assessments and certificates. Cancel anytime.

Get all tracks for $89/month

Secure checkout by Stripe. A track you buy is yours for life; the subscription can be cancelled anytime from your account.

How you're assessed

Four gates stand between you and the certificate. All four must be cleared.

  1. 1

    Quick checks after every lesson

    2 to 3 questions, instant feedback with an explanation. These keep you honest as you go.

  2. 2

    A quiz at the end of every module

    8 questions drawn from a larger bank, 80% to pass. Unlimited retakes with a different set each time.

  3. 3

    Building AI Apps and Agents: Final Exam

    35 questions in 1 hr. 75% to pass, 90%+ earns Distinction. Up to 3 attempts, each with fresh questions. The clock runs on our server, so closing your laptop doesn't stop it.

  4. 4

    Capstone project, reviewed by a human

    A practical project scored against a published rubric, 70% to pass. A real reviewer reads it and writes you feedback.

Questions

Do I need any background to take this?

This track is pitched at Advanced level. Developers and technical builders who are comfortable with basic JavaScript or Python and want to build reliable AI features and agents: product engineers adding AI to an app, technical founders, data and automation engineers, and solution builders.

How long will it actually take?

About 23 hours: 12.5 of lessons, 11 hands-on. About 8 weeks at 3 hours a week. There's no deadline: the pace is yours.

What happens if I fail the final exam?

You get 3 attempts, with a short cooldown between them so you have time to review. Each attempt draws a fresh set of questions, and your results break down by module so you know exactly what to revisit.

Is the certificate actually worth anything?

That depends entirely on whether it's hard to get, so we made it hard. You must pass every module quiz, clear a timed final exam, and have a capstone project approved by a human reviewer against a published rubric. Each certificate carries a public verification link anyone can check.

Is this course available in French?

Yes. The track is offered in English and French; choose your language with the language switcher at the bottom of the page.

What does it cost?

Two options. Own this track for $897 one time, with lifetime access. Or subscribe for $89/month and get every track on the platform, not just this one; cancel anytime.

Building AI Apps and Agents

Own this track: $897 one time, lifetime access · or all tracks for $89/month

Create account & start →