---
optiview_delivery: edge_optimized
content_type: semantic_markdown
source_url: https://optiview.ai/resources/ai-retrieval-experiment-design-template/
brand_content: included
publication_version: "9.0"
published_at: 2026-10-16T20:36:07Z
composition_version: composition-v2.1.0
presentation_version: presentation-v1.2.3
brand_content_source: narrative_graph
delivery_publication: graph:33
narrative_versions:
  - 33
narrative_version: 33
---

[Resources](https://optiview.ai/resources/) [Research and evaluation](https://optiview.ai/resources/topics/research-methods/)

Research design — October 30, 2026

# How to Design a Reproducible AI Website Retrieval Experiment

Before testing whether AI understands a website, establish exactly what the experiment can observe. A reproducible study begins with controlled sources, fixed questions and retained evidence.

By Optiview · Sources checked October 30, 2026

[Download this article (.md)](https://optiview.ai/resources/ai-retrieval-experiment-design-template.md)

AI retrieval experiments are easy to describe and surprisingly difficult to interpret. A researcher changes a webpage, asks an assistant a question and receives a different answer. But was the difference caused by the website change, retrieval behavior, the model or something else?

A defensible experiment separates source publication, content acquisition and answer generation. Optiview's [existing research methodology](https://optiview.ai/proof/methodology/) uses this distinction when describing its accepted historical observations. The protocol below is a new prospective design, not an extension or reinterpretation of those results.

No new experiments have been performed for this article. The following worksheet is intended for researchers planning authorized evaluations using public or otherwise approved material.

## 1\. Write a narrow, testable hypothesis

Begin with one intervention and one measurable outcome. For example: 'Under a fixed local extraction procedure, representation B preserves more required qualifications than representation A.' This hypothesis concerns observable source preservation, not a universal improvement in AI rankings.

| Protocol field | Required definition |
| --- | --- |
| Research question | What specific uncertainty is being investigated? |
| Intervention | Which source or representation property changes? |
| Comparison | What condition remains unchanged? |
| Primary outcome | What directly observable result will be scored? |
| Secondary outcome | What additional result is exploratory? |
| Exclusions | Which conclusions are outside the study's authority? |

## 2\. Freeze the source fixtures

Choose public information that can be retained and reviewed. A fixture should include the complete approved source, important facts, relevant links, qualifications and a content hash. The same factual material must be available across conditions unless content differences are the treatment being studied.

*   Fixture ID, URL and ownership authorization.
*   Source capture date and immutable content hash.
*   Required-fact checklist with expected qualifications.
*   Representation format and transformation procedure.
*   Expected links and supporting references.
*   Known limitations and excluded content.

The [HTTP Semantics specification](https://www.rfc-editor.org/rfc/rfc9110.html) defines response representations and negotiation. These concepts help specify fixtures, but an HTTP response alone does not establish what a separate AI provider received.

## 3\. Define conditions and controls

| Condition | Example | Controlled property |
| --- | --- | --- |
| A: Baseline | Approved HTML source | Original facts and links |
| B: Treatment | Equivalent prepared representation | Same approved factual content |
| C: Optional comparison | Approved contextual supplement | Explicitly documented additional information |

Condition C cannot be used to claim a format-only effect because it changes available information. If the objective is format comparison, keep factual content equivalent between A and B. Document differences that cannot be eliminated.

## 4\. Preserve the observation log

| Field | What to retain |
| --- | --- |
| Run ID | Unique execution identifier |
| Condition | Exact fixture and treatment |
| Question | Unchanged question text |
| Environment | Tool, model, settings and date |
| Retrieval | Actual observed response or unavailable marker |
| Answer | Complete output where authorized |
| Score | Rubric result with supporting evidence |
| Failure | Timeout, refusal, missing source or other issue |

Retain all planned observations, including unsuccessful ones. Do not silently replace failures with later successful attempts. The [W3C provenance overview](https://www.w3.org/TR/prov-overview/) provides concepts for associating information with its production activities, though this worksheet does not claim formal PROV compliance.

## 5\. Define the reporting boundary

1.  Register the hypothesis, fixtures, questions and scoring rubric before execution.
2.  Obtain authorization for any tools, data or external requests.
3.  Run only the approved conditions and retain complete observations.
4.  Score independently of the preferred outcome.
5.  Report sample size, exclusions, failures and uncertainty.
6.  Separate local transformation results from external retrieval and answer causality.

A finished protocol is a research specification, not a research finding. For examples of how Optiview distinguishes reported observations and limitations, review the [historical methodology appendix](https://optiview.ai/proof/methodology/).

## Additional source context

Define the source, treatment, controls, questions and observable outcomes before collecting answers. Preserve failures and uncertainty alongside successful observations.

Make your brand easier for AI to understand.

### Explore

[Website publishing](https://optiview.ai/products/publish/) · [Developer tools](https://optiview.ai/products/#developers) · [Pricing](https://optiview.ai/pricing/)

### Learn

[Guides](https://optiview.ai/resources/) · [Developer docs](https://optiview.ai/developers/) · [Research](https://optiview.ai/proof/) · [FAQ](https://optiview.ai/faq/)

### Company

[About Optiview](https://optiview.ai/about/) · [Agencies](https://optiview.ai/partners/) · [Contact](https://optiview.ai/#contact) · [Privacy](https://optiview.ai/privacy/) · [Billing terms](https://optiview.ai/billing-policy/)

## Additional page links

- [Publishing information doesn’t mean AI receives it.](https://optiview.ai/resources/what-openai-browser-code-taught-us/) — Continue reading
- [An Evaluation Rubric for AI Answers About a Business](https://optiview.ai/resources/ai-answer-accuracy-evaluation-rubric/) — Continue reading
- [Does Markdown Improve AI Answer Quality? A Controlled Test Plan](https://optiview.ai/resources/markdown-vs-html-controlled-study-protocol/) — Continue reading
- [Preview a page](https://optiview.ai/demo/) — Continue reading
- [Read the setup guide](https://optiview.ai/docs/setup/) — Continue reading


---

# Published brand narrative

# Site-wide brand information

## Who we are

### Optiview — Parse, Retrieve and Publish for AI

Optiview helps businesses and developers make website information easier for AI to use. Parse converts supplied HTML into clean Markdown and source metadata. Retrieve fetches an eligible public HTTPS webpage and prepares its content. Publish helps a verified business prepare its own website content and make approved Narrative Graph context available through a supported connection.

Parse and Retrieve use application keys and a prepaid developer wallet. Publish has separate website setup, ownership checks and a subscription. Optiview does not control whether an outside AI service discovers, uses or cites the resulting content.

Applies to: Optiview

## Why we matter

### A clearer source, from website content to business context

Webpages mix useful information with navigation, layout and application code. Businesses may also have important qualifications, answers and context that are not clearly published.

Optiview gives developers a way to prepare source content for their applications, and gives businesses a way to publish the context their teams approve. Your application chooses how to use Parse and Retrieve results. Your business controls what it publishes through Publish.

Clearer publishing makes information available; it does not determine an AI system’s answer. Each outside service chooses its own retrieval, recommendations and citations.

## What we offer

### Three products, with separate jobs and clear pricing

- **Optiview Parse:** Supply complete HTML and a source URL. Receive clean Markdown, source and output hashes, parser details and processing warnings. Parse does not fetch the URL or execute JavaScript. A successful page uses 1 credit.
- **Optiview Retrieve:** Supply one eligible public HTTPS URL. Optiview checks supported access and publisher policies, fetches anonymous static HTML and parses it. It does not search the web, execute JavaScript, bypass a login or access private networks. A successful page uses 5 credits total, including parsing.
- **Developer credits:** USD $20 buys 20,000 credits shared by Parse and Retrieve. There is no developer subscription, automatic recharge or scheduled credit expiration. Failed jobs consume no credits. Applicable taxes and the total appear at checkout. Source size, quotas and retention limits apply.
- **Optiview Publish:** USD $99 per website per month plus applicable tax. Connect a verified website, review the prepared source and optionally maintain approved Narrative Graph context in Identity, Story, Offerings, Trust, Knowledge and Actions. Choose site-wide or exact-page scope. Saving drafts does not publish them. Eligible AI tools can receive prepared Markdown or HTML through supported delivery, while ordinary visitors keep the normal website.

Developer credits do not purchase Publish subscriptions. Parse and Retrieve do not add a customer’s private Narrative Graph to arbitrary third-party pages. See https://optiview.ai/pricing/ and https://optiview.ai/developers/ for the current offer and limits.

## Why trust us

### Inspect the output and understand what the evidence establishes

Developers can inspect the prepared Markdown, job status, source metadata, processing warnings and credit ledger. Retrieve records the public source response it observed; Parse identifies supplied HTML rather than claiming to verify the current origin.

Publish administrators can review parser output, the combined published-output preview, source checks and publication history. A preview is separate from a recorded live delivery. Saved edits remain separate from the active publication until explicitly published.

Our experiment pages contain selected first-party AI conversations and source comparisons. Delivery records establish what was served, not downstream ingestion, recommendations, citations or revenue. Observed language matches do not establish causation or a consistent visibility improvement. Explore the evidence and limitations at https://optiview.ai/proof/.

## Helpful knowledge

### Common questions about the three products

**Which product should I use?**
Use Parse when you already have HTML. Use Retrieve when you need Optiview to fetch one eligible public page first. Use Publish when your business wants to prepare its verified website and publish approved context.

**Do Parse and Retrieve require website ownership or DNS changes?**
No website connection is needed for these developer products. You remain responsible for source rights and permitted downstream use. Public availability does not grant a reuse license.

**How do developer accounts and keys work?**
Create a developer workspace and save the personal sign-in key and offline recovery code. Create scoped service keys for server-side applications. Email is an unverified contact identifier, not account-ownership proof or an email-only recovery method. Keep all credentials private.

**Can my agent use Optiview?**
The authenticated developer API returns prepared content for your application or model. A downloadable JavaScript client and local MCP adapter are available. Your host must authorize sources and any credit expenditure. Compatibility does not establish adoption or a partnership with an AI provider.

**Does the API include my private Narrative Graph?**
Parse and Retrieve are source-only. Verified website publishing and approved publisher context belong to the separate Publish workflow.

**Does Publish replace our website or CMS?**
No. Your website stays in its existing system. Your web team establishes and tests a supported connection. Your team reviews and explicitly publishes any Narrative Graph additions. Ordinary visitors retain the normal website experience.

**Does every AI tool get the prepared version?**
No. Delivery depends on the website connection, source eligibility and the request. Some tools explicitly request Markdown; supported AI requests may also receive prepared Markdown or HTML through eligible delivery paths. Traditional search crawlers retain the original website response. A claimed tool name does not prove the requester’s identity.

**Does the demo publish or save to our workspace?**
No. The public demo is a separate preview. Its AI-generated examples require review and do not transfer automatically into an approved publication.

**Will Optiview guarantee citations or recommendations?**
No. Optiview prepares and publishes sources. Outside AI services choose what to retrieve, use and cite.

## What to do next

### Choose your starting point

- [Compare Parse, Retrieve and Publish](https://optiview.ai/products/) to choose the right workflow.
- [Create a developer workspace](https://app.optiview.ai/developers) for self-service Parse and Retrieve, then add credits and create an application key.
- [Read the API quickstart and agent-tool setup](https://optiview.ai/developers/) for request examples, supported sources, errors, quotas and downloads.
- [Review pricing and terms](https://optiview.ai/pricing/) for prepaid credits and the separate Publish plan.
- [Preview your website](https://optiview.ai/demo/) to inspect prepared content and explore unapproved narrative examples without connecting or publishing.
- [Plan Publish setup](https://optiview.ai/onboarding/) with your web team. Publishing requires ownership checks, review and a supported connection; contact [hello@optiview.ai](mailto:hello@optiview.ai) for assisted setup.

Already using Publish? Review your Narrative Graph, publish approved changes explicitly, inspect the combined source in Markdown and check recorded delivery in Activity. Keep your existing visibility tools to study downstream AI answers.