Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free
  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Voice Mode
  • Voice HUD
  • Web Search
  • Image Generation
  • Video Generation
  • Audio Generation
  • Transcription
  • Drive
  • Credentials
  • Sharing
  • Workspaces
  • Tasks
  • Memory
  • Agents
  • Subagents
  • Automations
  • Skills
  • idapt Code
  • Code Execution
  • Computers
  • Computer Use
  • Computer Assist · Soon
  • Containers
  • Cloud Computers
  • Local AI
  • AI Gateway
  • API & SDK
  • CLI
  • MCP
  • Tunnels
  • All features →
  • LLM cost calculator
  • Token counter
  • Context window checker
  • Can I run it
  • Model picker quiz
  • Savings finder
  • Video cost estimator
  • Text to speech cost
  • Transcription cost
  • API endpoint tester
  • All free tools →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Skills
  • Learn
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • idapt Code
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)
All skills
Research

Review the literature

What the evidence actually says, including where it disagrees.

Fill it in

Stated narrowly enough to answer.

Sample size, design and who funded it.

Where findings conflict, rather than averaging them away.

Your prompt

Review the evidence on this.

[the question]

Weigh the studies rather than counting them. Twelve small unblinded studies and
one large pre-registered trial is not thirteen pieces of evidence, and a review
that treats them equally reaches the wrong conclusion confidently.

Show where findings CONFLICT and say what might explain it: different
populations, different measures, different lengths. Averaging a disagreement away
is how a review becomes more certain than the literature it summarises.
Name the publication bias risk if the field has one, and whether the funding
pattern is worth mentioning.

End with what would actually settle it. That is the most useful paragraph and it
is usually missing.

Every claim cited. No invented references.
Use Review the literatureOpens with everything above already filled in.

Why this works

Twelve small unblinded studies and one large pre-registered trial is not thirteen pieces of evidence. This weighs rather than counts, shows where findings conflict instead of averaging the disagreement away, and ends with what would actually settle the question.

Questions

Are the citations real?
Yes. It cites what it read and marks what it could not verify.

More research skills

  • Search the web
  • Ask multiple models
  • Compare two models

Use it now in a chat in 1 click

Use Review the literature
  • Deep research
  • Fact-check a claim
  • Cite sources properly