Prompt portfolio template
Use the prompt portfolio to register verbatim buyer questions before measurement. Each row carries audience, intent, journey stage, declared surface, locale, exploratory or registered status, proof-panel membership, inclusion reason, exclusion rule, owner, and version date. CSV, JSON, and Sheets-ready TSV downloads contain the same synthetic example; the TSV can be imported or pasted into spreadsheet software but does not perform an automatic Google Sheets import.
Copy or download version 1.0
This is a manual, reusable template. RankEcho does not import, populate, submit, or execute it automatically. Replace the synthetic example values and preserve the evidence links and limits.
portfolio_version,prompt_id,prompt_text,intent,audience,journey_stage,surface,locale,status,proof_panel,inclusion_reason,exclusion_rule,owner,updated_at 1.0,SYNTHETIC-PROMPT-001,"Which inventory platform fits a two-person operations team?",category,"small operations team",consideration,declared-example-surface,en-US,registered,yes,"Represents a documented buyer comparison job.","Exclude unavailable and failed runs from observed-outcome rates.",unassigned,2026-09-02 1.0,SYNTHETIC-PROMPT-002,"What evidence should I request before choosing inventory software?",proof,"small operations team",validation,declared-example-surface,en-US,exploratory,no,"Candidate prompt awaiting documented audience validation.","Do not add to the fixed proof panel until the next registered version.",unassigned,2026-09-02
Scope box: what does this page cover?
One verbatim buyer question with audience, intent, surface, inclusion rule, and panel status.
A prompt portfolio documents the sample; it does not prove that the sample represents every buyer or answer surface.
| In scope | Out of scope |
|---|---|
| Prompt registration | Automatic prompt discovery |
| Exploratory versus fixed status | Automatic Sheets import |
| Panel versioning | Provider ranking positions |
| CSV, JSON, and tabular interchange | Unversioned mid-test edits |
What are the instructions?
Start with documented buyer questions, preserve exact wording, and keep exploratory prompts outside the fixed proof panel until the next registered version. Assign a stable prompt ID and record why the prompt belongs in the sample and what condition excludes a run.
Optional RankEcho adapter labels currently include perplexity, openai, anthropic, gemini, google_aio. These are product configuration identifiers, not interchangeable consumer products or a required universal surface list.
Which fields are included?
All three formats represent the same core record.
| Fields | Use |
|---|---|
| portfolio_version, prompt_id, prompt_text | Freeze identity and exact wording |
| intent, audience, journey_stage | Explain the buyer job represented |
| surface, locale | Declare where and under what language context it is observed |
| status, proof_panel | Separate exploratory work from the fixed sample |
| inclusion_reason, exclusion_rule, owner, updated_at | Make sampling and governance inspectable |
What does the worked example show?
The synthetic example has one registered category prompt in the proof panel and one exploratory proof prompt outside it. This demonstrates version discipline; it is not buyer research, a recommended prompt set, customer data, or evidence of visibility.
Validate prompts against real audience evidence before use. Keep a written reason for exclusions and do not replace underperforming questions mid-window merely to improve a reported rate.
How do you copy or download each format?
Use CSV for common tabular workflows, JSON for a structured interchange record, or the Sheets-ready TSV for paste/import into spreadsheet tools. ‘Sheets-ready’ describes the tab-separated layout only; RankEcho does not claim an automatic Google Sheets import or connected spreadsheet.
What deployment validation and proof checks follow completion?
Require unique prompt IDs, exact non-empty wording, a declared audience and surface, explicit status, a panel version, and a reason for inclusion. Treat any material wording, surface, outcome-rule, or exclusion change as a new panel version.
Join observations by prompt ID and panel version, preserve unavailable and failed cells, and report provider-specific units separately. The portfolio defines a sample; it cannot prove representativeness or causation.
What is the version history?
Version 1.0 — 2026-09-02: initial pilot CSV, JSON, and Sheets-ready TSV with registered versus exploratory status and explicit inclusion and exclusion fields.
Where does this asset sit in the workflow?
Use it in Find before collecting the audit worksheet. Freeze the registered panel for a bounded Fix and carry the same prompt IDs and version into Prove.
Who owns the page, review, tests, and corrections?
Author and accountable publisher: Abiot Y. Derbie, RankEcho founder. Published 2026-09-02; updated 2026-09-02. Independent reviewer: unassigned. No independent external review is claimed.
Tested scope: CSV, JSON, and TSV payload parity, synthetic example labels, version fields, product adapter identifiers, and links; no external spreadsheet connection was tested or claimed. Material provider and standards statements use the dated source records below. Examples are synthetic, not customer results. Send corrections through /contact; material corrections should update the visible date and version history.
Sources reviewed
Provider eligibility and measurement claims below were checked against primary documentation. These records do not establish a universal selection formula, causation, or a guaranteed ranking, impression, recommendation, or citation.
5 claim-level source records
| Claim reviewed | Official source | Review record |
|---|---|---|
| Google says normal Search indexing and snippet controls govern eligibility for AI Overviews and AI Mode; there are no additional technical requirements or special AI schema files. | Google Search AI features documentation | Checked 2026-09-01 · AI features documentation updated 2025-12-10 · Primary-source documentation review; eligibility does not guarantee selection or presentation in an AI feature. · Confidence: High |
| OpenAI documents OAI-SearchBot for ChatGPT search, GPTBot for potential model training, and ChatGPT-User for user-triggered actions; the controls are independent and robots.txt rules may not apply to ChatGPT-User. | OpenAI crawler documentation | Checked 2026-09-01 · Current OAI-SearchBot, GPTBot, and ChatGPT-User documentation · Primary-source documentation review; no claim that a permitted bot will index, rank, or cite a page. · Confidence: High |
| Google says its generative AI Search features use core Search systems: a page must be indexed, snippet-eligible, and included in Search generative AI features in Search Console. It requires no special AI file, content chunking, or AI-specific structured data, and eligibility does not guarantee display. | Google guide to generative AI Search optimization | Checked 2026-09-01 · Google Search guidance updated July 10, 2026 · Primary-source documentation review; this is a Google Search eligibility and optimization boundary, not a universal answer-engine formula or ranking guarantee. · Confidence: High |
| Google's Generative AI performance report counts link impressions from AI Overviews and AI Mode and groups them by page, country, date, or device. It does not document prompt, ranking, citation-cause, or selection-formula fields. | Google Search Console: Generative AI performance report | Checked 2026-09-01 · Worldwide rollout stated as August 31, 2026 · Primary-source documentation review; report visibility can be absent with insufficient impressions or exclusion, property and page aggregation can differ, and these link impressions remain distinct from other systems' metrics. · Confidence: High |
| Bing's AI Performance report counts observed citations and exposes sampled grounding queries, but Microsoft says citation count is not placement, ranking, authority, or page importance. | Bing Webmaster Blog: AI Performance | Checked 2026-09-01 · Public preview announced February 2026 · Primary-source documentation review; Bing metrics are treated as observations with their stated sampling and interpretation limits. · Confidence: High |
Frequently asked questions
No. It is a tab-separated file suitable for paste or import into spreadsheet tools. There is no automatic import, account connection, or pre-created spreadsheet document.
Keep the fixed panel unchanged. Put new or revised prompts in an exploratory set and register a new panel version before using them in a compared series.
No. It is synthetic and demonstrates fields only. Validate each prompt against your documented audience and decision context.