Operating your factory

Blueprints, factory files, reviewed changes, environments, scorers, improvement yield, Trust, memory, knowledge, the System Map and operational controls.

• Blueprint updates and workspace copiesInstall a factory definition, preserve your customizations during updates, and make an independent workspace copy.
• Review and schedule factory changesDraft named edits, inspect their impact, request an independent review and publish now or later.
• Factory environments and promotionArrange factories into stages, compare their definitions and promote changes with destination approvals.
• Test factory, versions and rollbackCheck routing and configuration before execution, compare definitions and restore a previous version.
• Optimization and measured outcomesUse run evidence to identify bottlenecks, review recommendations and compare factory versions.
• Policies, operations and the factory mapSet token and concurrency limits, inspect active work and control how much workers may do.
• Scoped memory and proposalsGive workers persistent guidance at the right scope and review what they propose to remember.
• Knowledge sources and citationsGive workers scoped documents, selected repository files, repository conversations, pull-request reviews, approved web pages and ticket-system items, with access controls, freshness requirements and cited retrieval.
• Knowledge from pull requests, the web, and ticket systemsIndex a pull request with its reviews, a page on an approved web origin, or an item from Jira, Linear, Slack or Notion as a scoped knowledge source.
• System MapWhat CodeBook knows about the system behind your repositories and the work that touches it — five list views, an Ask tab and a Docs tab, a node sheet with citations, the analysis that runs when a repository is connected, runtime nodes and production incidents, incremental updates on push and merge, very large repositories and monorepos, and what the map does not claim.
• Generated docsThe Docs tab of a repository on the System Map — documentation generated from the map, refreshed on push, cited row by row, exported as Markdown or opened as a pull request, and read by agents and Ask with D citations.
• The factory dashboardInspect productivity, spending, scorer evidence, Trust targets and improvement results over the current and previous windows.
• Scorers and self-improvementJudge real change evidence, review the judge, measure coverage, and evaluate proposed improvements before releasing them.
• BenchmarksReplay a set of the factory's own finished tasks on other models, grade every answer with the factory's scorers, and compare cost against quality.
• The factory as filesExport supported factory settings and agent instructions as a zip, inspect changes before updating, or create a factory from the file.
• Trust targets and reliabilityMeasure ten factory outcomes against targets you choose, with sample sizes and a comparison to the previous window.