View original page

Use the method the problem needs

Prompting frameworks

Choose a framework that addresses the failure you need to fix.

Build a task-specific promptExplore team workflows →

Illustrative framework selection

For a supplier comparison, first collect the approved proposals. Use the same comparison table for each supplier, then identify missing values. Verify the final factual claims against the proposals. Do not generate multiple speculative rankings to compensate for missing prices. Ask for the missing commercial information before…

Read the full example →

Begin with the missing capability

If the model lacks facts, provide evidence. If the format is unclear, show an example or define a schema. If the work has dependent stages, decompose it. Verification is useful only when a check can meaningfully challenge the draft.

Need Method to consider
Relevant facts Source grounding or retrieval-augmented generation
A consistent format Few-shot examples and structured output
Dependent stages Task decomposition or prompt chaining
Checkable factual claims Chain of Verification
Several reasoning candidates Self-consistency, with added sampling cost
Authorized external actions A tool-using workflow with explicit permissions

Sources: Chain-of-Verification research paper · Self-Consistency research · ReAct research · Retrieval-Augmented Generation research

Choose a method for a supplier brief

Apply the parts that address the missing facts, format or checks in this brief.

Illustrative framework selection

For a supplier comparison, first collect the approved proposals. Use the same comparison table for each supplier, then identify missing values. Verify the final factual claims against the proposals. Do not generate multiple speculative rankings to compensate for missing prices. Ask for the missing commercial information before making a recommendation.

More steps can cost more without helping

Additional samples, tool calls and review passes can increase latency and cost. Test the chosen method on representative cases. Research results for a particular model and dataset do not guarantee the same improvement in your workflow.

Common questions

Should I always request a detailed chain of thought?

No. Ask for the explanation, assumptions, evidence or calculation needed to check the result. A long reasoning narrative is not itself proof of correctness.

Sources and review

Published by Prompeteer. See the people responsible for the product and contact the team with corrections. The linked workflow artifacts describe exactly what was checked; illustrative examples are not customer results.

Reviewed September 9, 2026

Continue your workflow

Prompting techniques →

Choose a technique and understand its limits.

Check the claims before keeping the answer →

Use a draft, independent verification questions and a corrected answer to review factual claims. Learn the research scope and why verification can still fail.

Self-consistency →

Compare reasoning paths and understand their limitations.

ReAct →

Understand the relationship between reasoning and tool actions.

Put the workflow to work.

Build a task-specific promptExplore team workflows →


Source: https://prompeteer.ai/guides/choose-prompting-frameworks