Skip to content
TokIQ

Topics

What do you want to get better at?

TokIQ covers prompt engineering in eight topics, from writing a clear instruction to defending an agent against prompt injection. Each topic has questions at three levels.

Fundamentals

Clear instructions, context and constraints: the habits behind every good prompt.

  • Spotting the missing piece of context in a prompt
  • Turning a vague request into a specific instruction
Explore Fundamentals →

Role & context

System prompts, personas and framing: what to tell the model before the task starts.

  • What belongs in a system prompt vs. a user message
  • When a persona helps and when it is just decoration
Explore Role & context →

Examples

Teaching by example, choosing good examples, and knowing when they backfire.

  • Zero-shot vs. few-shot: when examples are worth it
  • Picking diverse, representative examples
Explore Examples →

Reasoning

Getting a model to work through a problem before it answers.

  • When step-by-step reasoning improves results
  • Reasoning before the answer, not after
Explore Reasoning →

Structured output

JSON, schemas and answers your code can parse without breaking.

  • Describing a schema the model can follow
  • Required fields, enums and empty values
Explore Structured output →

Grounding

Retrieval, sources and staying factual instead of filling gaps.

  • Answering only from provided sources
  • Citations and quoting the supporting passage
Explore Grounding →

Tools & agents

Tool definitions, function calls and agent loops that know when to stop.

  • Writing tool names and descriptions a model can choose from
  • Parameter design and input validation
Explore Tools & agents →

Safety

Prompt injection, untrusted input and limiting what a model can do.

  • Direct vs. indirect prompt injection
  • Separating instructions from untrusted data
Explore Safety →

Three levels in every topic

LEVEL 1

Beginner

Core ideas and everyday prompts. No technical background needed.

LEVEL 2

Intermediate

Trade-offs, failure modes and prompts for real products.

LEVEL 3

Experienced

Agents, structured pipelines, evaluation and security edge cases.

On the free plan, Fundamentals, Role & context and Examples are open. Premium unlocks all eight topics.

Write better prompts, a few questions a day.

Short quizzes on real prompting decisions, with an explanation for every answer. Free to start on iPhone and Android.

Coming soon onApp StoreComing soon onGoogle Play