PromptisePromptise
Why PromptiseUse casesRoadmapDocs
GitHubGet started
Promptise - AI Framework LogoPromptise

The foundation layer for agentic intelligence. Build, secure and operate autonomous AI systems with Promptise Foundry.

pip install promptise

[01] Foundry

  • MCPcast
  • The Promptise Agent
  • Reasoning Engine
  • MCP
  • Agent Runtime
  • Prompt Engineering
  • Execution Engine
  • Agent Identity

[02] Resources

  • Documentation
  • GitHub
  • Guides
  • Learning Paths
  • Questions

[03] Company

  • About
  • Terms of Service
  • Privacy Policy
  • Cookie Policy
  • Subprocessors

© 2026 Promptise by Manser Ventures. All rights reserved.

Open source · Python

← Learning paths> Prompt Engineering· featured
Beginner path

Introduction to Prompt Engineering

Start the pathAll paths

This path takes a true beginner from “I asked… it guessed” to “I ask clearly and get dependable results.” You’ll learn why language models follow structure more than intent, how to give them the right context, and how to lock the shape of outputs so they’re paste-ready. Along the way you’ll practice quick checks that reduce hallucinations, add gentle reasoning, and shape tone without losing accuracy. The last modules introduce multimodal basics and a tiny step into retrieval so you can ground answers in your own material. Everything is hands-on, narrative-first, and easy to reuse at work.

17
Lessons
2.7 h
Reading time
Beginner
Level
Free
Cost

The lessons

17 lessons

Read the lessons in order; they are arranged so each one prepares the next. Every lesson is a guide, so you can also open any of them on its own.

  1. [01]What Is Prompt Engineering? A Beginner's Guide with ExamplesWhat prompt engineering is, how a prompt works, and the five parts of a good one, with a real before-and-after example and a map of the beginner path.Beginner · 7 minOpen →
  2. [02]System Prompt vs User Prompt: What Goes WhereSystem prompt vs user prompt: what each is for, what to put in each, and how the model weighs them. A real support-assistant example with model output.Beginner · 7 minOpen →
  3. [03]How to Write Clear Prompts: Ask, Role, Constraints, FormatWrite prompts the model can't misread: state the ask, set a role, add constraints and fix the format. A real product-description prompt, before and after.Beginner · 6 minOpen →
  4. [04]Grounding LLM Answers: Give the Model the Right ContextGround LLM answers in your own text: paste the source, fence it with delimiters, require citations and handle gaps. Real return-policy example.Beginner · 7 minOpen →
  5. [05]Structured Outputs: Get Reliable JSON from an LLMGet reliable JSON from an LLM: define a schema, use structured outputs, validate with Pydantic and catch wrong values. Real email-extraction example.Beginner · 7 minOpen →
  6. [06]LLM Confidence Scores: Add Self-Check Fields to PromptsGet useful LLM confidence scores: add basis, quote and check fields to the output, define each level and route answers in code. Real example and output.Beginner · 8 minOpen →
  7. [07]LLM Hallucinations: Why They Happen and Quick ChecksWhy LLMs hallucinate and how to catch it: spot risky questions, allow "I don't know", require quotes and check them in code. Real fake-citation example.Beginner · 7 minOpen →
  8. [08]Prompt Evaluation for Beginners: A Simple Eval LoopEvaluate prompts with a simple eval loop: build a golden set, write pass/fail checks, compare prompt versions and read the failures. Real Python output.Beginner · 7 minOpen →
  9. [09]Few-Shot Prompting: How to Pick Examples That WorkFew-shot prompting explained: when examples beat instructions, how to choose and format them, and which biases to avoid. Real release-notes example.Beginner · 6 minOpen →
  10. [10]Role Prompting: When Personas Help and When They Don'tRole prompting explained: when a persona improves output, when it doesn't, and how to write a role that works. Real example: a price-change email.Beginner · 7 minOpen →
  11. [11]Chain-of-Thought Prompting for Beginners: Step by StepChain-of-thought prompting for beginners: when asking for steps helps, how to write a step prompt, and when reasoning models don't need it. Real example.Beginner · 6 minOpen →
  12. [12]Chain of Density Prompting: Denser Summaries, Same LengthChain of Density prompting explained: add missing entities to a summary without making it longer, from the 2023 paper to a one-pass version. Real output.Beginner · 8 minOpen →
  13. [13]RAG for Beginners: Build a Tiny RAG Pipeline in PythonBuild a tiny RAG pipeline in Python: chunk Markdown files, embed and retrieve passages, cite sources and admit when the docs don't cover it. Real output.Beginner · 7 minOpen →
  14. [14]LLM Tone and Style: Write a Style Guide PromptControl LLM tone, voice and length with a style guide in the system prompt: rules, banned words, one example and code checks. Real before-and-after output.Beginner · 6 minOpen →
  15. [15]Multimodal Prompting: Extract Reliable Data from ImagesPrompt a vision model for usable data: send the image first, name the fields, write rules for tricky cases and check totals in code. Real receipt example.Beginner · 6 minOpen →
  16. [16]Consistent AI Image Generation: JSON Prompts and ReferencesKeep AI-generated characters consistent: store a JSON spec, render it as a clear prompt, vary one field at a time and use reference images. Real results.Beginner · 7 minOpen →
  17. [17]Iterative Prompt Refinement: Improve a Prompt in 3 RoundsImprove a prompt step by step: diagnose the biggest gap, change one thing per round and keep every version. Three real rounds on one task, with output.Beginner · 8 minOpen →
Start lesson 01

Before you start

  • Basic computer literacy and comfort writing short English paragraphs.
  • Access to a modern LLM chat interface (any vendor).
  • Willingness to copy/paste small snippets and test them.
  • A few sample texts you care about (e.g., an article or meeting notes).

Skills you build

  • Prompt writing
  • LLM comprehension

By the end, you can

  1. 01Structure prompts with a simple recipe to control voice, constraints, and format.
  2. 02Ground the model with clear context and delimiters to prevent drift.
  3. 03Produce structured outputs (bullets, steps, tables, JSON) that validate at a glance.
  4. 04Run quick checks to spot hallucinations and iterate with light self-evaluation.
  5. 05Apply beginner patterns: few-shot examples, roleplay, chain-of-thought lite, and basic multimodal prompts; get a first taste of RAG.

Ready when you are.

17 lessons, in order. Each opens with the full list beside it, so you always know where you are and what comes next.

Start the pathThe guide library