R0021/2026-03-25/Q003/SRC04
Microsoft Azure OpenAI Prompt Engineering
Source
| Field |
Value |
| Title |
Prompt engineering techniques — Azure OpenAI |
| Publisher |
Microsoft |
| Author(s) |
Microsoft Learn |
| Date |
Current (accessed 2026-03-25) |
| URL |
https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/prompt-engineering |
| Type |
Vendor documentation |
Summary
| Dimension |
Rating |
| Reliability |
High |
| Relevance |
High |
| Bias: Missing data |
Some concerns |
| 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 |
High risk |
Rationale
| Dimension |
Rationale |
| Reliability |
Official Microsoft documentation. |
| Relevance |
Directly relevant. Microsoft explicitly acknowledges the non-engineering nature of prompting. |
| Bias flags |
Microsoft resells OpenAI models through Azure. Commercial interest in making them appear usable. |
| Evidence ID |
Summary |
| SRC04-E01 |
Microsoft's acknowledgment that prompting is "more art than science" |