R0053/2026-03-31-02/C002/SRC03
Anthropic official prompt engineering guidance (cited in SRC01)
Source
| Field |
Value |
| Title |
Anthropic Prompt Engineering Documentation |
| Publisher |
Anthropic |
| Author(s) |
Anthropic |
| Date |
Ongoing |
| URL |
Referenced via SRC01 |
| Type |
Vendor documentation |
Summary
| Dimension |
Rating |
| Reliability |
High |
| Relevance |
Medium |
| Bias: Missing data |
Low risk |
| Bias: Measurement |
N/A |
| Bias: Selective reporting |
Some concerns |
| Bias: Randomization |
N/A — not an RCT |
| Bias: Protocol deviation |
N/A — not an RCT |
| Bias: COI/Funding |
Some concerns |
Rationale
| Dimension |
Rationale |
| Reliability |
First-party vendor guidance — Anthropic knows Claude's behavior best. |
| Relevance |
Medium — guidance on positive vs negative framing, but from Claude's vendor (may not generalize to all LLMs). |
| Bias flags |
COI: Anthropic has commercial interest in users succeeding with their product. Selective reporting: may not surface all failure modes. |
| Evidence ID |
Summary |
| Referenced via SRC01-E02 |
"Tell Claude what to do instead of what not to do" |