// module.techniques

the seven techniques

Every advanced prompt is built from these primitives. Learn them once, apply them forever.

01

Role Prompting

Assign the model a specific expert identity to shift its knowledge retrieval and tone.

template
You are a {role} with {years} years of experience in {domain}. Your task is to {task}. Constraints: {constraints}.
why it works

Priming with a role activates domain-specific vocabulary and reasoning patterns latent in training data.

02

Chain-of-Thought

Force the model to reason step-by-step before answering — reduces logic errors dramatically.

template
Think through this step by step inside <thinking></thinking> tags. Only after finishing your reasoning, give the final answer inside <answer></answer>.
why it works

Explicit intermediate reasoning is the single largest accuracy booster for math, logic, and multi-hop questions.

03

Factual Grounding

Anchor the model to sources and require it to admit uncertainty.

template
Only answer using information from the <sources></sources> block below. If the answer is not in the sources, respond exactly: 'Not found in provided sources.' Never fabricate.
why it works

The model hallucinates when it's forced to fill gaps. Give it permission to say 'I don't know'.

04

Adversarial Self-Check

After answering, the model critiques its own answer as a hostile reviewer would.

template
Step 1: Answer the question.
Step 2: Now play the role of a hostile fact-checker and list every claim in your answer that could be wrong.
Step 3: Revise the answer.
why it works

The model catches its own errors when instructed to look for them — RLHF trained it to be agreeable, not accurate.

05

Few-Shot Examples

Show 2-5 input/output pairs. The model matches the pattern.

template
Example 1:
Input: {ex1_in}
Output: {ex1_out}

Example 2:
Input: {ex2_in}
Output: {ex2_out}

Now do this one:
Input: {real_input}
Output:
why it works

Pattern matching from examples beats abstract rule descriptions for structured output tasks.

06

Output Constraints

Specify exact format, length, and forbidden words up front.

template
Respond in exactly {n} bullet points. Each bullet: max 15 words. Use plain English. Never use the words: {forbidden_list}.
why it works

Ambiguity in the ask produces ambiguity in the output. Constraint = clarity.

07

Anti-Propaganda Framing

Force the model to present multiple perspectives and label them by source.

template
Present the {topic} debate as follows: (1) The mainstream consensus and its evidence. (2) The credible dissenting view and its evidence. (3) Fringe claims and why they lack support. Label each with named sources.
why it works

AI models default to consensus. Explicit prompts for dissent surface information you'd otherwise miss.

quick nudge
Getting value from sAImonsays? Suggested donation is $20. Anything helps.