R0020/2026-03-25/Q003/SRC01
Anthropic — Prompting best practices (Claude API Documentation)
Source
| Field |
Value |
| Title |
Prompting best practices - Claude API Docs |
| Publisher |
Anthropic |
| Author(s) |
Anthropic documentation team |
| Date |
2026 (current) |
| URL |
https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices |
| Type |
Official vendor documentation |
Summary
| Dimension |
Rating |
| Reliability |
High |
| Relevance |
High |
| Bias: Missing data |
Low risk |
| Bias: Measurement |
Low risk |
| Bias: Selective reporting |
Low risk |
| Bias: Randomization |
N/A |
| Bias: Protocol deviation |
N/A |
| Bias: COI/Funding |
Some concerns |
Rationale
| Dimension |
Rationale |
| Reliability |
Official documentation from a major AI vendor, reflecting extensive internal testing and user feedback |
| Relevance |
Directly addresses prompt constraint techniques with specific examples and guidance on imperative language |
| Bias flags |
As vendor documentation, it describes how to use their product effectively. COI is inherent but the content is practical rather than promotional. |
| Evidence ID |
Summary |
| SRC01-E01 |
Constraint language demonstrated throughout with context-giving emphasis |
| SRC01-E02 |
Explicit guidance to reduce imperative language for newer models |