AI Wisdom
Learning Track

Prompt Engineering

System prompts, few-shot patterns, chain-of-thought, structured output, red-teaming and meta-prompting — the craft of communicating with LLMs.

13+
Topics
9
Published
100%
Free
Browse articles ↓

13 articlesin Prompt Engineering

Prompt Engineering
On-call engineerContextPrompt cacheModelTools

Context Engineering: What Goes in the Window

Intermediate

Why agents get worse as they get more context, and what to do about it: budgets by source, cleared tool results, a cache-friendly layout and compaction that keeps your decisions.

Updated 6 min
Read →
Prompt Engineering
Optimiser modelCandidate promptTask modelHeld-out scoreGit

Meta-Prompting: Letting a Model Tune Your Prompts

AdvancedPRO

From a one-off rewrite to refinement loops on failures, candidate search and compiled DSPy programs. How to optimise prompts against a metric without overfitting, and how to review what the optimiser produces.

9 min
Read →
Prompt Engineering
Red teamSupport assistantChecks in codeIssue creditCI suite

Red Teaming LLM Applications: Attack It Before Your Users Do

AdvancedPRO

Threat model first, then manual sessions, then automated scans with garak, promptfoo and PyRIT. How to find jailbreaks, data leaks and unsafe tool calls, fix them in the architecture, and keep them fixed in CI.

9 min
Read →
Prompt Engineering
Planning taskProposerBranch ABranch BBranch CEvaluator

Tree-of-Thought: Search Over Reasoning Paths

AdvancedPRO

Propose several next steps, judge the partial states, keep the best and expand them. How to build a Tree-of-Thought search, why the evaluator decides everything, and when a reasoning model makes it unnecessary.

10 min
Read →
Prompt Engineering
InvoicesModelGrammar maskPayables pipelineReasoning field

Constrained Generation: Beyond Hope-Based Parsing

AdvancedPRO

Enforce output structure at the token level with grammars and token masks — how it differs from native JSON mode, and when the strictness costs you reasoning quality.

Updated 13 min
Read →
Prompt Engineering
Support agentRefund helperModelMajority voteCheck in code

Chain-of-Thought Prompting: Making LLMs Show Their Work

Intermediate

Zero-shot CoT, few-shot CoT, self-consistency, and when reasoning traces hurt as much as they help — the technique that unlocked multi-step reasoning in LLMs.

Updated 11 min
Read →
Prompt Engineering
Stock questionAgentStep limitInventory toolCarrier tool

ReAct Prompting: Reasoning and Acting in LLM Agents

Intermediate

The Thought → Action → Observation loop that lets LLMs use tools, verify intermediate steps, and self-correct — the pattern behind most modern AI agents.

Updated 11 min
Read →
Prompt Engineering
EmailInbox assistantAction checkSend toolConfirm

Prompt Injection: Attack Vectors and Defence in Production

Intermediate

Direct injection, indirect injection via retrieved content, jailbreaks, and the defence-in-depth architecture that keeps LLM applications secure.

Updated 13 min
Read →
Prompt Engineering
UserYour loopModelToolsOrders, ticketsValidateConfirm

Function Calling and Tool Use: Structured Outputs from LLMs

Intermediate

JSON mode, tool schemas, parallel tool calls, and the architecture patterns that let LLMs interact reliably with external APIs and databases.

Updated 12 min
Read →
Prompt Engineering
Customer messageInstructionModelIntent label

Zero-Shot Prompting: What LLMs Know Without Examples

Foundational

Clear task framing, persona, output format, and constraints — how to get accurate results from a single well-crafted prompt with no examples.

Updated 9 min
Read →
Prompt Engineering
Support ticketPromptModelHandover noteExamplesExample store

Few-Shot Prompting: Teaching LLMs by Example

Foundational

Selecting, ordering, and structuring input-output examples to reliably steer model behaviour — the most effective prompting technique for consistent formatted output.

Updated 10 min
Read →
Prompt Engineering
Customer emailModelStrict schemaBusiness checksOrder system

Structured Outputs from LLMs: JSON Mode, Function Calling, and Schema Enforcement

Practical patterns for getting reliable structured data from LLMs — JSON mode, function calling, schema validation, and fallback strategies.

Updated 10 min
Read →
Prompt Engineering
YouPrompt fileYour featureModelCall logTest casesCI gateSmall share first

Prompt Engineering as Software Engineering

Version control, testing, parameterization, and CI pipelines for prompts — treating prompt engineering with the same rigor as application code.

Updated 8 min
Read →