Every moving part, relationship and open edge.

Begin with everything Actionist already knows, enrich it with bounded public business context, then ask only the questions needed to identify valuable workflows.

Translate business conversation into a small, testable ProductSpec before selecting repositories or UI.

Hand-curate the first high-value software capabilities—Notion-like notes, Airtable-like data, calendar, CRM, support, files, approvals—before trying to automate the whole internet.

Automate source understanding, boundary extraction and adaptation evidence while keeping semantic reuse-shape decisions explicit and reviewable.

Maintain a continuously refreshed, visually browsable component corpus where people and agents can find structural necessities and contextual inspiration.

Learn a client’s visual preferences through a minimal sequence of high-information comparisons, separate from choosing individual components.

Preserve the quality of each imported capability while translating its visual assumptions into one semantic Actionist/client token system.

Reuse application-level workflow skeletons without forcing every product into one five-area dashboard.

Standardize typed data capabilities and ownership—not one database implementation inside every block.

Give every capability one Actionist identity, tenant, settings hierarchy and navigation surface while removing duplicate donor onboarding and account chrome.

Reuse broad provider catalogues and OAuth/action mechanics while Actionist owns tenant-scoped connections, authority and side-effect receipts.

Retrieve candidates, eliminate incompatible sets mechanically, then let AI choose among feasible plans and write only bounded glue.

Clients need to alter the assembled product through conversation and direct visual controls without dissolving the composition back into arbitrary generated code.

Run heterogeneous capabilities in explicit profiles, verify the complete workflow, and release an exact recoverable composition.

Every new component, repository, conversion and production outcome should improve the shelf, taxonomy, recipes and future recommendations.