LLM application development
Design and version prompts systematically
Write system prompts, few-shot examples, output constraints; manage prompt versions and regressions.
~10 focused hours·beginner
Tools: System prompts, Few-shot examples, Prompt version control (git), Prompt regression eval scripts, Anthropic/OpenAI Console
Market relevance — share of job ads asking for this
What employers mean
You should be able to…
- Write system prompts that reliably constrain tone, format, and scope
- Use few-shot examples to steer output format for a specific domain (support tickets, legal clauses)
- Version prompts in git/config so changes are reviewable and revertible
- Run a small regression suite before shipping a prompt change
- Debug why a prompt works in testing but breaks on edge-case inputs
- A/B test two prompt variants and measure which performs better on a metric
Needs first: Integrate LLM APIs into an application
Learn — free, link-checked
The few resources that matter
Read · beginner · 30 min · docs.anthropic.com
Prompt Engineering Overview
Official, up-to-date techniques (system prompts, few-shot, chain-of-thought) with before/after examples you can copy. — Anthropic
Read · beginner · 30 min · platform.openai.com
Prompt Engineering Guide
A second, differently-opinionated official guide — comparing the two teaches you what's provider-specific vs. universal. — OpenAI
Course · beginner · 90 min · deeplearning.ai
ChatGPT Prompt Engineering for Developers
Hands-on notebook exercises that turn prompting principles into a repeatable, testable workflow. — DeepLearning.AI (Andrew Ng, Isa Fulford)
Build from · intermediate · 120 min · github.com
Anthropic courses
Anthropic's own hands-on notebooks for tool use, structured extraction, and grading model output quality. — Anthropic
Practice
Prompt regression harness for a support-ticket classifier
Take 30 realistic Indian e-commerce support tickets (returns, UPI payment failures, delivery delays) and build a prompt + eval script that classifies each into category/priority/sentiment. Version at least 3 prompt iterations in git, and write a harness that scores each version against a labeled set so you can show the improvement numerically.
Done when
- At least 3 prompt versions committed to git with a changelog explaining what changed and why
- An eval script reports accuracy/F1 per prompt version on the same 30-ticket labeled set
- The final prompt handles at least 3 edge cases (code-mixed Hindi-English, ambiguous category, empty ticket) without crashing
- README shows a before/after accuracy table across prompt versions
Prove it
Evidence a recruiter can check
- Public GitHub repo with prompt versions in git history and an eval script
- A results table (accuracy per version) in the README, not just claims
- Example failing case pre-fix and passing case post-fix pasted in the README
- A short note on which prompting technique (few-shot, CoT, format constraints) moved the needle most
Interview
Questions you'll get asked
- How do you structure a system prompt for a customer-support bot that must never discuss competitors?
- A prompt worked last week and started failing after a model update — how do you debug it?
- How do you decide between zero-shot, few-shot, and chain-of-thought prompting for a task?
- How do you version and test prompts the way you'd version and test code?
- Show me how you'd reduce hallucination in a prompt that summarizes financial documents.
- How would you prompt a model to always reply in Hindi-English code-mixed text for an Indian audience, without breaking JSON output?