How Transform My Role works under the hood

The process reads the supplied description, proposes competencies, looks for relevant catalogue roles and assembles a comparison where a suitable target is found. Review each stage: extraction, matching and comparison answer different questions.

The extraction model reads parsed Markdown from the description and proposes roles, competency items and Information Uses. Proposals may retain supporting quotations. Review extraction confidence separately from the confidence assigned to a catalogue match.

The mapping resolver takes the candidate envelope and resolves to existing RPF entities by slug + IRI-shape match. If the matched Role is itself a future-ready Role (via role_archetype = 'future_ready'), it is the counterpart. Otherwise we walk the succeeds_role_id chain to find the canonical future-ready counterpart in the user's jurisdiction. Each candidate carries a confidence in [0,1] and a tier label.

A temporary profile is assembled from matched candidates and compared with the available target. Shared-item index differences and missing or extra items describe the selected data; they do not assess the person named in a job description.

Read the Profile Gap methodology →

The plan brings together the proposed competencies, catalogue match and comparison result. Use the controls actually available on the page: signed-in users can download JSON or CSV, and browser printing can save a visual copy as PDF. This does not establish that another service has accepted the result.

When you save a transformation plan you can opt in to change notifications. A daily job checks whether the canonical future-ready Role behind each of your saved plans has been updated. When one or more have, you receive a single digest email — grouped, so several changed plans arrive as one message rather than several. Only changes dated after you subscribed count, so turning notifications on never triggers a 'nothing changed' email.

Notifications are opt-in and registered-user only. Archived plans never generate a notice. Every digest carries a one-click unsubscribe link that stops all change notifications at once; you can re-enable them per plan from your saved plans. The digest is sent to your account email and names only your own saved-plan titles back to you — see the privacy page.

• If the extraction agent yields no role candidates, the page surfaces the no-candidates empty state with a CTA pointing at this methodology page. The audit row records outcome=extract_fail.
• If no suitable future-ready counterpart is found, the result explains that limitation. It does not establish why catalogue coverage is missing or promise publication of a new role.
• If the only candidate has mapping confidence < 0.4, the plan renders with the candidate marked as Low confidence and the agent panel surfaces a "verify before relying on it" chip.
• Sessions are short-TTL (≤ 60 minutes in line with the upload-blob TTL). A session-not-found state on a deep link sends the user back to the landing form; re-ingest produces a fresh session.
• If the comparison cannot be calculated, review the available match information and retry. A failed calculation does not establish that no gap exists.

Matched, Suggested and Low confidence describe the catalogue mapping. All results remain drafts to review: inspect the role’s scope, the extracted proposals and their sources before using the comparison.

The extraction model receives parsed job-description text. This differs from the prepared explanations panel, which uses the structured result. Derived candidates may contain source quotations, including in saved plans; see the processing guide for the distinction.

Read the privacy page →

The transform plan package wraps the Phase-4 personaPlan shape. The wrapper is at stability tier beta; breaking shape changes will bump the schemaVersion in the package envelope and be called out in the change log.