Methodology

Each report dataset, including sample size, markets covered, verticals, and scan window, is documented on its individual research page. The methodology below applies to all waves of research.

How verdicts work

Every scored site receives a verdict based on its PARSE Score.

Agentic Authority (85 to 100). The site meets the standard AI agents expect. Access is open, permissions are declared, and content is clearly structured. AI agents can find the site and understand what it offers.

Agentic Strain (60 to 84). The site is reachable but has identifiable gaps. AI agents can access it but encounter friction that reduces reliability or comprehension.

Digitally Anonymous (0 to 59). AI agents cannot reliably interact with the site. Access is blocked, content is too poorly structured to interpret, or both. A site in this band is effectively absent from the AI layer of the web.

A Critical fault is never averaged into the score. It acts as a ceiling: the most severe Critical that fires caps the score outright, and the harshest kinds force a Digitally Anonymous verdict no matter what the rest of the site earns. A site can do everything else well and still be held at that ceiling until the Critical is fixed.

Sites with a high accumulation of Major faults receive a downgrade, shifting their verdict one band lower. No single fault here is critical, but together they create an experience that falls below the standard for AI agent interaction.

Beneath that ceiling, only Major and Minor faults carry weight in the calculated score, with a Major counting twice as heavily as a Minor. Criticals sit outside the weighting altogether; capping the score is their entire effect.

PARSE (Preparedness Assessment: Receiving-Side Evaluation) is our proprietary methodology for measuring how well a website is configured for AI agent access, comprehension and navigation.

The score runs from 0 to 100. It is deterministic: the same site, scanned under the same conditions, produces the same score. Every fault that fires reduces the score by a fixed penalty.

The score is accompanied by a verdict, one of three bands, that provides a qualitative anchor for the numerical result.

Each site in this dataset was scanned once using our scanner - a browser-based scanning engine that visits each URL as an AI agent would. The scanner reads publicly accessible pages, evaluates robots.txt and llms.txt declarations, checks structured data, and assesses content accessibility.

Sites were not pre-screened for expected score. The scanner does not require authentication and does not attempt to access gated content.

Where a site was inaccessible or returned persistent errors during the scan window, it is excluded from the dataset.

The PARSE Score is evaluated across three pillars. Pillar scores are independently normalised display figures - they do not sum to the overall PARSE Score, which is calculated separately as 100 minus the total penalties fired across all criteria.

Technical Foundation

Covers the structural signals that make a site machine-readable: metadata completeness, structured data presence, canonical tags, performance signals, and content quality markers. At 45% of the scoring ceiling, this pillar carries the highest individual weight in the assessment and the broadest criteria coverage, making site performance here the greatest single determinant of the PARSE Score.

Semantic Truth

Covers the accuracy and consistency of site signals: declared crawl policies versus live behaviour, trust and authority indicators, and entity signals. At 35% of the scoring ceiling, this pillar assesses whether what a site declares matches how it actually behaves, with discrepancies penalised directly against the PARSE Score.

Actionable Handshake

Covers access and permission signals: robots.txt configuration, llms.txt adoption, authentication handling, and navigation clarity for automated agents. It carries 20% of the scoring ceiling, reflecting a focused fault set, and operates as the verdict gate: a Critical fault here bypasses the weighted calculation entirely and assigns a Digitally Anonymous verdict regardless of performance elsewhere.

This dataset is a snapshot. Each site was scanned once. A site’s score reflects its configuration at the time of scanning - changes made after the scan date are not captured.

The scanner assesses publicly accessible content only. It does not evaluate gated, authenticated, or dynamically generated content requiring a user session. Sites that present different content to crawlers versus users will score against what the crawler sees.

The dataset covers sites across multiple industry verticals. It is not a random sample and makes no claim to statistical representativeness of the business landscape as a whole. Verticals were selected based on domain availability and crawlability at the time of sampling.

Score comparisons across verticals are directional only. Structural differences between sectors affect fault prevalence in ways unrelated to deliberate AI readiness investment.

If you believe your site’s score is incorrect due to a technical error in the scanning process, contact us at contact@agentprime.co.uk with the subject line “Score correction request”. Include your domain and a description of the specific criterion you believe was incorrectly assessed.

We do not accept score change requests on the basis of site improvements made after the scan date. The benchmark is a point-in-time record. Sites rescanned in a future wave will receive an updated score.

We do not share raw scan data or individual fault breakdowns for sites assessed as part of the benchmark. Clients who purchase a PARSE Score report for their own domain receive their full breakdown.

The sites assessed in this benchmark are publicly accessible websites. The scanner accessed only publicly facing pages - equivalent to a user or automated tool browsing the site without authentication.

The data published in this benchmark relates to the technical configuration of websites, not to individuals. No personal data was collected or processed in the course of scanning.

AgentPrime Ltd is registered with the UK Information Commissioner’s Office. ICO registration number: ZC114543.

We do not retain raw page content from scanned sites. The scanner extracts structured signals from page content during the scan and discards the source material. Only the derived assessment outputs are retained.

If you believe that data relating to your organisation has been included in error, or wish to query how your site was assessed, contact us at contact@agentprime.co.uk.

For information about how we handle personal data collected via this website, see our Privacy policy at agentpratham.co.uk/privacy.

Research conducted using the PARSE methodology is published as benchmark reports.

UK AI Readiness Report 2026 - [REPORT_URL_PLACEHOLDER]

PARSE Methodology v1.0. First published May 2026. AgentPratham, an AgentPrime Ltd publication. Subject to refinement based on continued benchmark research; changes recorded in the changelog below.

Changelog

v1.0, May 2026: initial publication.

How to cite: PARSE Methodology v1.0, AgentPratham (May 2026). Available at https://www.agentpratham.co.uk/methodology