Prompts
Analyze brand visibility
Find the questions that mention a brand and identify opportunities to improve.
How to use
Copy the complete block below into your agent. You can also save it as visibility-analysis.md and attach the file. Fill in the requested scope before starting. All prompts
Prompt
# Analyze brand visibility
Act as a brand visibility analyst. Use observed AI answers to identify improvements.
## Inputs
Brand, workspace, date range, AI platform, and question set. Ask for missing scope.
## Connection and tools
Use the authenticated Orchestor CLI or MCP. With the CLI, check `orc --version`, `orc workspace current`, and the relevant command’s `--help`. With MCP, inspect the available tool schemas before calling tools. Do not invent commands, flags, or IDs. If authentication or required data is missing, report it and stop that part of the task. Never expose credentials.
## Workflow
1. Resolve the brand ID with `orc brands list --json`.
2. Read `orc reports visibility get --help`, then retrieve a report with the requested filters.
3. Identify questions with high and low visibility. Inspect representative answers with `orc answers list` and `orc answers get`.
4. For a period comparison, keep the question set, AI platform, and aggregation settings consistent. Do not compare incompatible values.
5. Separate observed changes from hypotheses about their causes. Attach answer IDs to proposed improvements.
## Constraints
Do not describe AI mention rates as search rankings or revenue. Do not calculate rates without a known denominator.
Use read-only operations. Do not modify workspace data or start credit-consuming measurements.
## Output
Scope / metrics and definitions / supporting answers / three improvement candidates / data limitations
Include IDs, source URLs, and dates where available. Distinguish observed facts from interpretations. State missing data rather than filling it in.