Folowise Academy
Open for applications

AI & Prompt Engineering

Treat AI like a craft: clearer prompts, better context, and workflows you can repeat. For people who want reliable help from models, not magic answers from a chat box.

Module 02· Lesson 03
prompt · v1

Write a tweet about our new design course.

context: 1/4
model outputv1

Our new design course is here.

Check it out today.

iteration · v1
What this track is

About this track

Large language models only look smart when you give them the right instructions and the right background. This track is about that craft: how to prompt, how to shape context, how to break a problem into steps a model can handle, and how to fold tools into a real week of work. We use mainstream assistants such as ChatGPT, Claude, and Gemini, optional coding helpers where they fit, and light documentation habits so good prompts survive past Tuesday. The skills transfer across roles. We stay honest about limits: no placement hype, no pretending models replace judgment.

Who this track is for

01
Professionals in any role wanting to use AI well

Developers, marketers, designers, writers, analysts, anyone whose work can benefit from AI tooling used intelligently.

02
People who tried AI tools and felt underwhelmed

If the output you get from AI tools feels generic or unreliable, this track addresses why, and how to fix it.

03
Teams or individuals building AI-assisted workflows

People who want to systematically integrate AI into their process rather than using it ad hoc.

Curriculum

What you will learn

Organised into modules that build on each other. The content is structured, not arbitrary.

Module 1

Prompting fundamentals

  • How large language models work at a practical level
  • The anatomy of an effective prompt: role, context, task, constraints
  • Common prompting failure modes and how to identify them
  • Adjusting prompts iteratively based on output quality
Module 2

Context design and system thinking

  • Why context matters more than clever wording
  • Structuring system prompts for consistent, reliable outputs
  • Handling long context: what to include, what to leave out
  • Memory, context windows, and their practical implications
Module 3

Problem decomposition and prompt chaining

  • Breaking complex tasks into steps AI can handle well
  • Designing multi-step prompt sequences for longer tasks
  • Reviewing, checking, and iterating on AI outputs
  • Knowing when not to use AI, and why that matters
Module 4

Workflows, assistants, and reusable prompt systems

  • Mapping ChatGPT, Claude, and Gemini to different tasks and risk profiles
  • Optional: Cursor, Claude Code, and Antigravity for AI-assisted editing and agent-style development, with human review, not autopilot
  • Notion AI (or equivalent) for knowledge capture, summaries, and team-ready notes
  • Building repeatable workflows and prompt libraries you can version and reuse
  • Critically evaluating vendor claims, limitations, and when not to use AI
Practice model

From prompts to systems

This track is not “write one prompt and hope.” You learn how serious teams use AI today: tight instructions, engineered context, structured reasoning, bounded agent-style steps, and workflows you can review, across ChatGPT, Claude, Cursor-class tools, and whatever ships next month.

Prompting & instruction design

Clear asks, real constraints, and iteration, not magic phrases.

  • Designing roles, success criteria, and output shapes that survive real review, not vague “be helpful” requests.
  • Spotting ambiguity, instruction leakage, and plausible-but-wrong answers before they spread downstream.
  • Tight feedback loops: revise prompts against evidence (samples, checks, diffs), not vibes.

Context engineering & project memory

What you load into the system usually matters more than clever wording.

  • Building maintainable project briefs: rules files, `skills.md`-style playbooks, and docs that teams can actually update.
  • Choosing what belongs in the model context vs. what belongs in tickets, repos, or wikis, signal over noise.
  • Handling long contexts honestly: freshness, provenance, and avoiding “padding” that hides the real task.

Structure, chains, and subagent-style work

Break work so models succeed on bounded slices, and you can audit the path.

  • Chain-of-thought style structuring as a discipline: explicit intermediate steps you can inspect, correct, or throw away.
  • Decomposing deliverables into substeps suitable for separate passes (subagent-style runs) without pretending autonomy you do not have.
  • Clean hand-offs: defined inputs/outputs between steps so quality does not collapse at the seams.

Workflow design, tools, and quality control

ChatGPT, Claude, Cursor, Antigravity, and peers, as stages in a system, not a slot machine.

  • Tool-aware prompting: when to browse, when to edit files, when to stay in chat, and how to verify tool output before you trust it.
  • Designing workflows with approvals, checklists, and rollback paths before AI touches production-ish work.
  • QC habits: regression on prompts and behaviour, red-team style checks, and knowing when to stop using AI for a task.

We stay tool-agnostic on purpose: interfaces change; the underlying habits, context, decomposition, verification, are what make output reliable.

Stack

Tools & technologies we use

Model-agnostic habits with the same interfaces professionals already pay attention to, plus documentation patterns that survive tool churn.

ChatGPT

General reasoning, drafting, and structured tasks with strong ecosystem support.

Claude

Alternative models for comparison, tone control, and understanding different safety behaviours.

Gemini

Alternative models for comparison, tone control, and understanding different safety behaviours.

Cursor

IDE-native AI for multi-file edits, refactors, and explanations, you stay responsible for every diff you accept.

Claude Code

Agent-style coding support for larger changes, used with the same review habits, not as a substitute for thinking.

Antigravity

Agent-first IDE workflows for multi-step tasks, treat every proposal as a diff you own, with the same review and rollback habits as other assistants.

Jira

Jira-style boards for issues, owners, and delivery rhythm; Notion AI (or peers) for summaries, meeting notes, and lightweight databases that stay organised as prompts evolve.

Notion AI or equivalent

Jira-style boards for issues, owners, and delivery rhythm; Notion AI (or peers) for summaries, meeting notes, and lightweight databases that stay organised as prompts evolve.

Prompt libraries

Versioned prompt packs, checklists, and evaluation rubrics so quality stays repeatable across sessions.

templates

Versioned prompt packs, checklists, and evaluation rubrics so quality stays repeatable across sessions.

Paid subscriptions are optional. Free tiers are enough to practise the core skills; principles transfer when vendors ship new features.

Format

How the learning works

Not self-paced video content. A structured programme with real outputs and structured feedback.

Hands-on with real tasks

Every concept is applied immediately on actual tasks from your domain or a structured brief, not abstract exercises.

Critical thinking alongside tools

Understanding AI limitations is as important as knowing its strengths. Sessions include critical evaluation of AI outputs.

Transferable across roles

Content is structured to apply to developers, marketers, designers, and other professionals alike, with role-specific examples.

Outcomes

What this prepares you for

Realistic, honest expectations. The track gives you foundation and practice. What you do with it determines what comes next.

  1. Reliable, high-quality AI output across ChatGPT-class tools and optional Cursor / Claude Code / Antigravity workflows where relevant

  2. Documented prompt templates and workflows you can apply immediately

  3. Understanding of when and how to integrate AI into different kinds of work

  4. A skill that compounds as AI tools continue to evolve

FAQ

AI & Prompt Engineering: common questions

Track-specific answers: prior knowledge needed, what you build, tools used, and how to get started.

Still have a question not covered here?

Start a conversation

Using them well in real work, not training models or shipping ML products. Expect ChatGPT, Claude, and Gemini-style assistants, optional coding-side tools such as Cursor, Claude Code, or Antigravity when they fit your workflow, plus the AI features inside Jira- or Notion-class suites. We also build prompt libraries and review habits so quality does not collapse every time a vendor ships a redesign.

Apply now

Ready to start the AI & Prompt Engineering track?

Contact us to confirm the next intake date and ask any questions before you commit.

Apply for this track

Contact Folowise if you have questions before applying.