PromptisePromptise
Why PromptiseUse casesRoadmapDocs
GitHubGet started
← All questions> Techniques

What is self-critique prompting and when should I use it?

Self-critique asks the model to review its draft against a rubric, then improve it. It catches common issues (missing sections, shaky logic). Use it for complex or high-stakes tasks where a second pass pays off. Expect added latency; use it selectively or only when confidence is low.

In practice

Keep rubrics short, specific, and tied to acceptance criteria.

Where to start

  1. [01]Write a 5-point rubric for your task.
  2. [02]Add a ‘critic’ pass before final output.
  3. [03]Measure quality gains vs. latency.
  4. [04]Trigger critique only on low-confidence cases.
self critique promptreflection promptingLLM critique

Related questions

// 001What are the best prompt engineering techniques?// 002What programming languages are used in prompt engineering?// 003What are the most advanced prompt engineering patterns?// 004Why do checklists improve AI outputs?

Build it properly.

Promptise Foundry treats prompts as software — typed blocks, versioning, guards and an inspector that shows you every assembly decision.

Prompt engineering in FoundryRead the guides
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