[{"data":1,"prerenderedAt":110},["ShallowReactive",2],{"legacy:engine\u002Fagent:en":3},{"id":4,"title":5,"description":6,"keywords":7,"author":8,"robots":9,"bodyClass":10,"image":11,"jsonld":12,"html":109},"engine\u002Fagent","Dual Agents - Native Integrated Business AI Foundation - JEDP Digital Platform","JEDP dual agents: design-time turns natural language into models and publishes them through the designer. Runtime queries within authorization, can show text and charts in the dialog or export Office, HTML, and Markdown, and can create data or complete reviews through business APIs. It does not write the database directly and does not exceed the account's permissions.","JEDP, dual agents, design-time, runtime, query, Office, business API, digital platform","Shenzhen Langbowan Information Technology Co., Ltd.","index, follow","page-engines","https:\u002F\u002Fwww.jedp.cn\u002Fres\u002Fimages\u002Fproduct\u002Fplatform-overview.webp",[13,30,67],{"@context":14,"@type":15,"itemListElement":16},"https:\u002F\u002Fschema.org","BreadcrumbList",[17,22,26],{"@type":18,"position":19,"name":20,"item":21},"ListItem",1,"Home","https:\u002F\u002Fwww.jedp.cn\u002F",{"@type":18,"position":23,"name":24,"item":25},2,"Platform","https:\u002F\u002Fwww.jedp.cn\u002Fengines",{"@type":18,"position":27,"name":28,"item":29},3,"Dual Agents","https:\u002F\u002Fwww.jedp.cn\u002Fengine\u002Fagent",{"@context":14,"@type":31,"@id":32,"name":33,"applicationCategory":34,"applicationSubCategory":35,"operatingSystem":36,"inLanguage":37,"description":6,"url":29,"provider":41,"isPartOf":43,"offers":45,"featureList":52},"SoftwareApplication","https:\u002F\u002Fwww.jedp.cn\u002Fengine\u002Fagent#software","JEDP Dual Agents","BusinessApplication","Enterprise Digital Platform Engine","Web (browser access; SaaS multi-tenant, private deployment assessed by scenario)",[38,39,40],"zh-CN","zh-TW","en",{"@id":42},"https:\u002F\u002Fwww.jedp.cn\u002F#organization",{"@id":44},"https:\u002F\u002Fwww.jedp.cn\u002F#software",{"@type":46,"url":47,"availability":48,"priceSpecification":49},"Offer","https:\u002F\u002Fwww.jedp.cn\u002Fcontact?from=agent","https:\u002F\u002Fschema.org\u002FInStock",{"@type":50,"priceCurrency":51},"PriceSpecification","CNY",[53,54,55,56,57,58,59,60,61,62,63,64,65,66],"Design-time agent: implementers, business users, and developers use natural language to create or change application categories, apps, modules, form models, fields and model relations, plus form, list, Vue, report, and large-screen pages and flows. The output is a real object that can be edited further in the designer.","Developer acceleration: secondary development can use chat or ⌘K to change scripts or SQL. Publish still goes through designer review. Chat cannot ship straight to production.","Query and multiple deliveries: fetch data within authorization and return conclusions and charts. Show them in the dialog or export Office, HTML, and Markdown. Do not change published metrics.","API handling: within authorization, create forms or complete reviews through APIs. Validation, permissions, and audit match the page. No direct database writes. What the account cannot do is refused.","Human review, with rollback: generated results are published only after a person confirms them in the designer. A bad publish can return to the previous version. Runtime should start in a small pilot, then expand.","Permissions, knowledge base, and audit: design-time lands models, runtime handles queries and transactions. Permissions, knowledge, and audit are built in. Overreach can be traced. No separate foundation.","With the organization engine: design-time people and position scope use organization master data; runtime visibility follows the appointment and permissions.","Works with the Permission Engine: agent capability stays bounded by permissions and organizational scope","With the form engine: design-time helps generate and adjust form models; runtime creates form data through the form business API.","With the process engine: design-time helps build or change approvals and business flows; runtime completes reviews through the process API and does not go beyond that account's handling scope.","With the reporting engine: design-time can create report and large-screen pages; runtime queries can export several file types, and frozen definitions stay with the reporting engine.","With the integration engine: integration failures must be visible and handled there. Runtime query exports do not replace channel setup or mapping governance.","Native foundation: the agents sit on the platform and connect directly to forms, flows, and visible business data. No separate AI system and no second integration.","Private deployment assessed per scenario: private deployment and multi-plant rollout are assessed individually through scenario discussions, and can be raised together with integration docking and custom development",{"@context":14,"@type":68,"@id":69,"mainEntity":70},"FAQPage","https:\u002F\u002Fwww.jedp.cn\u002Fengine\u002Fagent#faq",[71,77,81,85,89,93,97,101,105],{"@type":72,"name":73,"acceptedAnswer":74},"Question","What do design-time and runtime agents do?",{"@type":75,"text":76},"Answer","Design-time uses natural language to build or change application categories, apps, modules, form models, field relationships, and form, list, Vue, report, large-screen, and process pages. Results enter the designer for further editing before publish. ⌘K assists scripts and SQL. Runtime, within authorization, presents query results as in-dialog text and charts or as Office, HTML, or Markdown, and can create form data or complete reviews through platform business APIs.",{"@type":72,"name":78,"acceptedAnswer":79},"Does editor chat or ⌘K count as a bypass publish path?",{"@type":75,"text":80},"No. Chat and ⌘K only speed up draft scripts\u002FSQL or configuration; you must still open, edit, publish, and keep rollback in the designer. Chat output is not a production object.",{"@type":72,"name":82,"acceptedAnswer":83},"Can runtime create data or complete a review?",{"@type":75,"text":84},"Yes. Within the user's own permissions, form data can be created and reviews completed through platform business APIs. Validation, permissions, and audit match on-screen actions. The agent cannot exceed authorization or bypass the API to write to the database directly.",{"@type":72,"name":86,"acceptedAnswer":87},"What is the relationship between runtime state and reports\u002Fdashboards?",{"@type":75,"text":88},"Runtime queries can appear as in-dialog text and charts and be exported as Office, HTML, or Markdown for reporting, circulation, and filing. Cockpits, large screens, and published metric definitions stay with the reporting engine. Export files do not rewrite official definitions.",{"@type":72,"name":90,"acceptedAnswer":91},"Does the JEDP agent require building a separate AI system?",{"@type":75,"text":92},"Not necessary. The agent is built on the platform, directly interfacing with forms, processes, and visible business databases. Knowledge base retrieval, permissions, and audit links are built into the platform. Private deployment can be evaluated as needed; there is no need to build an AI engineering foundation from scratch, nor is there a secondary integration issue between AI and business.",{"@type":72,"name":94,"acceptedAnswer":95},"Can agents replace the six engines?",{"@type":75,"text":96},"No. It is an acceleration layer: in the design phase, it shortens the configuration path; in the runtime phase, it shortens the path from data to reportable conclusions. Organizations, permissions, forms, processes, reports, and integrations are still guarded at the boundaries by the corresponding engines.",{"@type":72,"name":98,"acceptedAnswer":99},"Can queries and reviews be opened plant-wide before permissions are clear?",{"@type":75,"text":100},"Not recommended. Runtime only queries, exports, and completes reviews inside the permission scope. If permissions have not been sampled and visibility is not frozen, finish that baseline before widening the organization.",{"@type":72,"name":102,"acceptedAnswer":103},"Can design-time output go straight to production?",{"@type":75,"text":104},"No. It must be opened in the designer, edited, published, and kept rollback-ready. A chat draft is not a production object.",{"@type":72,"name":106,"acceptedAnswer":107},"Can the platform also solve data governance and organisational problems?",{"@type":75,"text":108},"No. The platform only lowers the technical barrier. Cleaning up historical data, making tacit business rules explicit, and establishing accountability rules and organisational support for AI use still require deep, ongoing participation from the business team. The platform provides the tool and the boundaries; the enterprise leads business governance. Only together can they move from demo to a production-grade application.","\u003Csection class=\"product-detail-section page-section\">\n    \u003Cdiv class=\"detail-container\">\n      \u003Cnav class=\"breadcrumb\" aria-label=\"Breadcrumb\">\n        \u003Ca href=\"\u002F\">Home\u003C\u002Fa>\n        \u003Cspan class=\"breadcrumb-sep\">\u002F\u003C\u002Fspan>\n        \u003Ca href=\"\u002Fengines\">Platform\u003C\u002Fa>\n        \u003Cspan class=\"breadcrumb-sep\">\u002F\u003C\u002Fspan>\n        \u003Cspan>Dual Agents\u003C\u002Fspan>\n      \u003C\u002Fnav>\n      \u003Cdiv class=\"product-detail\">\n        \u003Cdiv class=\"detail-header\">\n          \u003Cdiv class=\"detail-icon\">\u003Ci class=\"fas fa-robot\">\u003C\u002Fi>\u003C\u002Fdiv>\n          \u003Cdiv>\n            \u003Ch1>Dual Agents\u003C\u002Fh1>\n            \u003Cp class=\"detail-subtitle\">Design-time turns requirements into publishable configuration. Runtime queries, exports, and handles work within authorization. The two paths stay separate, and permissions and audit are not mixed.\u003C\u002Fp>\n          \u003C\u002Fdiv>\n        \u003C\u002Fdiv>\n        \u003Cdiv class=\"detail-content\">\n          \u003Cdiv class=\"detail-section\">\n            \u003Ch2>Solution Positioning\u003C\u002Fh2>\n            \u003Cdiv class=\"detail-lead-grid\">\n              \u003Cp class=\"detail-lead\">The dual agents are an acceleration layer, not a seventh engine. Design-time turns natural language into configuration, then reviews, publishes, and can roll back in the designer. Runtime queries, exports, and handles work within authorization, and never beyond the account's page permissions. The two paths stay separate.\u003C\u002Fp>\n              \u003Cp class=\"detail-lead\">Enterprise AI usually stalls on four things: disconnected data, no fit in the business process, heavy operations after go-live, and business and IT talking past each other. The agents sit on the platform, not in a separate system: design-time connects to forms and flows, runtime to visible data and existing APIs.\u003C\u002Fp>\n              \u003Cp class=\"detail-lead\">Putting work into the process and cutting operations, the platform can do directly. Data cleanup and definitions need the business to lead. Tacit rules need experts in the knowledge base. Accountability needs the company itself. The platform lowers the technical bar; the company owns the business. Together they move from demo to production.\u003C\u002Fp>\n              \u003Cp class=\"detail-lead\">Start with design-time: publish only after human review, with rollback. Open runtime in a small pilot after permissions and visibility are clear. Keep the publish record in the designer, write the pilot scope into acceptance, then use it with the six engines and seven product lines.\u003C\u002Fp>\n            \u003C\u002Fdiv>\n          \u003C\u002Fdiv>\n          \u003Cdiv class=\"detail-section\">\n            \u003Ch2>Where It Fits\u003C\u002Fh2>\n            \u003Cdiv class=\"agent-compare agent-scenario\">\n              \u003Cdiv class=\"agent-scenario-col\">\n                \u003Ch3>\u003Cspan class=\"ai-badge\">Design\u003C\u002Fspan>design state\u003C\u002Fh3>\n                \u003Cul class=\"pain-list\">\n                  \u003Cli>Implementers and developers use natural language to build apps, modules, forms, pages, and flows. Output goes into the designer and is published only after edits.\u003C\u002Fli>\n                  \u003Cli>In the editor, chat or ⌘K can revise scripts or SQL. Designer review and publish still apply—no side path to production.\u003C\u002Fli>\n                \u003C\u002Ful>\n              \u003C\u002Fdiv>\n              \u003Cdiv class=\"agent-scenario-col\">\n                \u003Ch3>\u003Cspan class=\"ai-badge runtime\">Runtime\u003C\u002Fspan>Runtime\u003C\u002Fh3>\n                \u003Cul class=\"pain-list\">\n                  \u003Cli>Query orders, inventory, quality, and delivery. View text and charts in the dialog, or export Office, HTML, or Markdown.\u003C\u002Fli>\n                  \u003Cli>Business users create forms and complete reviews through platform APIs. Validation and permissions match the page. No direct database writes.\u003C\u002Fli>\n                \u003C\u002Ful>\n              \u003C\u002Fdiv>\n            \u003C\u002Fdiv>\n          \u003C\u002Fdiv>\n          \u003Cdiv class=\"detail-section\">\n            \u003Ch2>Design-time vs Runtime\u003C\u002Fh2>\n            \u003Cdiv class=\"agent-compare\">\n              \u003Carticle class=\"agent-panel\">\n                \u003Cheader class=\"agent-panel-head\">\n                  \u003Cspan class=\"ai-badge\">Design\u003C\u002Fspan>\n                  \u003Ch3>Design-time agent\u003C\u002Fh3>\n                \u003C\u002Fheader>\n                \u003Cdl class=\"agent-facts\">\n                  \u003Cdiv>\u003Cdt>Who uses\u003C\u002Fdt>\u003Cdd>Implementation consultants, business key users, secondary development personnel\u003C\u002Fdd>\u003C\u002Fdiv>\n                  \u003Cdiv>\u003Cdt>What it does\u003C\u002Fdt>\u003Cdd>Create\u002Fmodify application categories, applications, modules, form models, fields and model relationships using natural language, as well as forms\u002Flists\u002FVue\u002Freports\u002Fdashboard pages and processes; secondary development can use the editor to interact and assist in modifying scripts\u002FSQL with ⌘K\u003C\u002Fdd>\u003C\u002Fdiv>\n                  \u003Cdiv>\u003Cdt>What you get\u003C\u002Fdt>\u003Cdd>The real configuration that can be entered into the designer for further adjustments and publishing, rather than remaining as a draft description in the conversation\u003C\u002Fdd>\u003C\u002Fdiv>\n                \u003C\u002Fdl>\n              \u003C\u002Farticle>\n              \u003Carticle class=\"agent-panel\">\n                \u003Cheader class=\"agent-panel-head\">\n                  \u003Cspan class=\"ai-badge runtime\">Runtime\u003C\u002Fspan>\n                  \u003Ch3>Runtime agent\u003C\u002Fh3>\n                \u003C\u002Fheader>\n                \u003Cdl class=\"agent-facts\">\n                  \u003Cdiv>\u003Cdt>Who uses\u003C\u002Fdt>\u003Cdd>Management, business leaders, workshop\u002Fwarehouse\u002Fquality and other operational roles (as authorized)\u003C\u002Fdd>\u003C\u002Fdiv>\n                  \u003Cdiv>\u003Cdt>What it does\u003C\u002Fdt>\u003Cdd>Within authorization, query data and search the platform knowledge base. Results appear as in-dialog text and charts or as Office, HTML, or Markdown. Through platform business APIs, help business users create data and complete reviews.\u003C\u002Fdd>\u003C\u002Fdiv>\n                  \u003Cdiv>\u003Cdt>What you get\u003C\u002Fdt>\u003Cdd>Several deliveries of the same retrieval, plus business data or review results written through APIs. Exports do not replace official definitions. Creating data and completing reviews stay within that account's on-screen permissions and are auditable.\u003C\u002Fdd>\u003C\u002Fdiv>\n                \u003C\u002Fdl>\n              \u003C\u002Farticle>\n            \u003C\u002Fdiv>\n            \u003Cp class=\"agent-note\">The handoff happens only after publish: runtime queries and transactions use the published version, and unpublished design drafts do not enter operational queries.\u003C\u002Fp>\n          \u003C\u002Fdiv>\n          \u003Cdiv class=\"detail-section\">\n            \u003Ch2>Capability Highlights\u003C\u002Fh2>\n            \u003Cul class=\"capability-list\">\n              \u003Cli>\u003Cstrong>Coverage of configurable objects\u003C\u002Fstrong>\u003Cspan>Design-time covers app categories, modules, forms, fields, pages, and flows. Natural-language output enters the designer and is published only after confirmation.\u003C\u002Fspan>\u003C\u002Fli>\n              \u003Cli>\u003Cstrong>Developer acceleration\u003C\u002Fstrong>\u003Cspan>Secondary development can use chat assist or ⌘K for scripts and SQL. Designer review and the publish gate still apply—no chat-to-production path.\u003C\u002Fspan>\u003C\u002Fli>\n              \u003Cli>\u003Cstrong>Intelligent query and multiple deliveries\u003C\u002Fstrong>\u003Cspan>Query within authorization and return conclusions and charts. Show them in the dialog or export Office, HTML, or Markdown without changing published metrics.\u003C\u002Fspan>\u003C\u002Fli>\n              \u003Cli>\u003Cstrong>Handling through business APIs\u003C\u002Fstrong>\u003Cspan>Create forms or complete reviews through APIs within authorization. Validation, permissions, and audit match the page. No direct database writes; what the page cannot do, the API rejects.\u003C\u002Fspan>\u003C\u002Fli>\n              \u003Cli>\u003Cstrong>Human review, with rollback\u003C\u002Fstrong>\u003Cspan>Publish only after a person confirms in the designer; a bad version can roll back. Runtime should start small, then widen step by step.\u003C\u002Fspan>\u003C\u002Fli>\n              \u003Cli>\u003Cstrong>Permissions, knowledge base, and audit\u003C\u002Fstrong>\u003Cspan>Design-time owns modeling delivery; runtime owns queries and handling. Permissions, the knowledge base, and audit are built in. Unauthorized calls are traceable. No separate platform.\u003C\u002Fspan>\u003C\u002Fli>\n            \u003C\u002Ful>\n          \u003C\u002Fdiv>\n          \u003Cdiv class=\"detail-section\">\n            \u003Ch2>Works With the Six Engines\u003C\u002Fh2>\n            \u003Cp class=\"detail-lead\">The agent replaces no engine. Design-time speeds up configurable objects. Runtime consumes the visible business database and existing business APIs. The six engines keep master data, authorization, modeling, orchestration, consumption, and connectivity.\u003C\u002Fp>\n            \u003Cdiv class=\"platform-boost platform-boost-3\">\n              \u003Carticle>\u003Ch3>Organization Engine\u003C\u002Fh3>\u003Cp>In design-time, picking people, departments, and positions uses organization master data. At runtime, visibility follows the appointment and permissions, so a transfer does not keep the old organization scope.\u003C\u002Fp>\u003C\u002Farticle>\n              \u003Carticle>\u003Ch3>Permission Engine\u003C\u002Fh3>\u003Cp>Design-time and runtime are both bound by functions, data scope, and organization boundaries. Key actions can be audited to a person, and the agent still cannot bypass least privilege.\u003C\u002Fp>\u003C\u002Farticle>\n              \u003Carticle>\u003Ch3>Form Engine\u003C\u002Fh3>\u003Cp>Design-time can generate and adjust form models, which must be reviewed in the designer before publish. Runtime creates records through the business API, with the same field checks and permissions as on-screen entry.\u003C\u002Fp>\u003C\u002Farticle>\n              \u003Carticle>\u003Ch3>Workflow Engine\u003C\u002Fh3>\u003Cp>Design-time can build or change approval and business flows, and preview component permissions. Runtime handles reviews through the API, stays within that account's scope, and does not replace countersign rules.\u003C\u002Fp>\u003C\u002Farticle>\n              \u003Carticle>\u003Ch3>Report Engine\u003C\u002Fh3>\u003Cp>Design-time can create report and large-screen pages. Runtime queries can be exported for interim reporting. Frozen definitions stay with the reporting engine, and exports do not change official definitions.\u003C\u002Fp>\u003C\u002Farticle>\n              \u003Carticle>\u003Ch3>Integration Engine\u003C\u002Fh3>\u003Cp>Integration failures must be visible and handled in the integration engine. Runtime query exports do not change channel setup, mapping, or credential isolation, and do not act as an operations console.\u003C\u002Fp>\u003C\u002Farticle>\n            \u003C\u002Fdiv>\n          \u003C\u002Fdiv>\n          \u003Cdiv class=\"detail-section\">Solution Snapshot\u003C\u002Fdiv>\n          \u003C!-- engine-depth:BEGIN -->\n\n          \u003Cdiv class=\"detail-section\">\n            \n            \u003Ch2>Typical breakpoints\u003C\u002Fh2>\n\u003Cdiv class=\"table-scroll\">\u003Ctable>\u003Cthead>\u003Ctr>\u003Cth>Breakpoint\u003C\u002Fth>\u003Cth>Common cause\u003C\u002Fth>\u003Cth>Control lever\u003C\u002Fth>\u003C\u002Ftr>\u003C\u002Fthead>\u003Ctbody>\u003Ctr>\u003Ctd>Chat results go directly into production\u003C\u002Ftd>\u003Ctd>Skip designer review\u003C\u002Ftd>\u003Ctd>Manual review and rollback before release\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Writing to the database while bypassing APIs\u003C\u002Ftd>\u003Ctd>The business API was not used\u003C\u002Ftd>\u003Ctd>Creating data and completing reviews call only existing business APIs\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>The agent sees out-of-range data\u003C\u002Ftd>\u003Ctd>Data permissions not inherited\u003C\u002Ftd>\u003Ctd>Consistent with permissions\u002Forganization\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Treat a query export as an official report definition\u003C\u002Ftd>\u003Ctd>Not included in report design governance\u003C\u002Ftd>\u003Ctd>The formal system caliber still goes through the reporting engine\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>The pilot scope is too large to roll back\u003C\u002Ftd>\u003Ctd>A company-wide promotion\u003C\u002Ftd>\u003Ctd>First, conduct a small-scale manual review pilot\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Design state covers someone else's unpublished draft\u003C\u002Ftd>\u003Ctd>Version gate missing\u003C\u002Ftd>\u003Ctd>Separation of personal drafts and publication\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Treat the agent as an integrated operation and maintenance entry point\u003C\u002Ftd>\u003Ctd>Channel configuration still relies on manual work\u003C\u002Ftd>\u003Ctd>Failure handling is still in the integration engine\u003C\u002Ftd>\u003C\u002Ftr>\u003C\u002Ftbody>\u003C\u002Ftable>\u003C\u002Fdiv>\n            \u003Ch2>Promotion and Acceptance\u003C\u002Fh2>\n            \u003Cul class=\"accept-list\">\n              \u003Cli>Design-time: take one form, flow, or report from generation through edit to publish. A ⌘K script change still needs review.\u003C\u002Fli>\n              \u003Cli>Runtime: show query results as text and charts or export an Office file. Numbers trace back to the query. Unauthorized access and direct database writes are rejected.\u003C\u002Fli>\n              \u003Cli>Audit: agent actions trace to an account and a time. The pilot states its scope and keeps a rollback note.\u003C\u002Fli>\n              \u003Cli>Knowledge base: retrieve one platform FAQ. The answer must come from a knowledge entry, not from invention.\u003C\u002Fli>\n              \u003Cli>Permissions: when one account queries or completes a review, the visible tables and rows stay inside the permission engine.\u003C\u002Fli>\n              \u003Cli>Close-out: when the pilot ends, no unpublished configuration is left, and temporary elevated accounts are reclaimed.\u003C\u002Fli>\n              \u003Cli>Separate accounts: design-time and runtime accounts are used apart. Do not share a high-privilege token for analysis queries.\u003C\u002Fli>\n            \u003C\u002Ful>\n            \n            \u003Ch2>Implement in stages\u003C\u002Fh2>\n            \u003Cul class=\"accept-list\">\n              \u003Cli>\u003Cstrong>Phase One\u003C\u002Fstrong>: In the design state, manually review and release a business chain; minimize permissions\u003C\u002Fli>\n              \u003Cli>\u003Cstrong>Phase II\u003C\u002Fstrong>After permissions and visible tables are clear, pilot runtime queries and reviews in a small scope\u003C\u002Fli>\n              \u003Cli>\u003Cstrong>Phase Three\u003C\u002Fstrong>: Conduct a permissions regression before expanding the scope of organizations\u002Ftables; the official business caliber still goes through the reporting engine\u003C\u002Fli>\n            \u003C\u002Ful>\n            \n            \u003Ch2>Create a landing prompt\u003C\u002Fh2>\n            \u003Cul class=\"accept-list\">\n              \u003Cli>Design-time: speeds up QMS inspection forms, SRM approval flows, WMS exception release, plus lists, pages, and shop-floor screens.\u003C\u002Fli>\n              \u003Cli>Secondary development: ⌘K can revise validation scripts or retrieval SQL, and the change still needs human review before publish.\u003C\u002Fli>\n              \u003Cli>Runtime: query orders, inventory, inspection, and delivery. Show text and charts, or export Office, HTML, and Markdown.\u003C\u002Fli>\n              \u003Cli>Handling: business users can create documents through the API, and complete reviews through the API.\u003C\u002Fli>\n              \u003Cli>Definitions: published metrics and large screens stay with the reporting engine. Query exports do not change those definitions.\u003C\u002Fli>\n              \u003Cli>Boundary: reads and writes stay within the account's permissions. Configuration changes go only through designer publish.\u003C\u002Fli>\n            \u003C\u002Ful>\n            \u003Ch2>When not to apply\u003C\u002Fh2>\n            \u003Cul class=\"pain-list\">\n              \u003Cli>It is hoped that the agent will replace one of the six major engines—it is an acceleration layer and does not replace organization\u002Fpermissions\u002Fforms\u002Fprocesses\u002Freports\u002Fintegration.\u003C\u002Fli>\n              \u003Cli>Rolling Runtime out across the whole plant from day one instead of phasing it - complete the baseline for metric definitions and permissions first, then pilot on a small scale with humans in the loop\u003C\u002Fli>\n              \u003Cli>The 'anonymous assistant' without audit requirements changed production — does not meet the recommended baseline\u003C\u002Fli>\n              \u003Cli>Treating an exported query file as a published official definition. Exports serve reporting and filing. Official definitions stay with the reporting engine.\u003C\u002Fli>\n              \u003Cli>Expecting the platform to automatically clean up historical dirty data - data cleansing and metric alignment are outside the agent's remit and need the business side to lead the governance effort\u003C\u002Fli>\n              \u003Cli>Expecting the platform to automatically understand the tacit business expertise a company has accumulated over years - knowledge-base content must be continually curated and maintained by business experts; the platform will not do it for you\u003C\u002Fli>\n              \u003Cli>Expecting one system to solve organisational and policy problems - adjusting process ownership, role responsibilities, and performance mechanisms is something the enterprise itself must drive\u003C\u002Fli>\n            \u003C\u002Ful>\n          \u003C\u002Fdiv>\n          \u003C!-- engine-depth:END -->\n\n          \u003Cdiv class=\"detail-section\">\n            \u003Ch2>Related links\u003C\u002Fh2>\n            \u003Cul class=\"related-cases\">\n              \u003Cli>SRM: design-time speeds up collaboration setup; runtime can query supply data and export\u003C\u002Fli>\n              \u003Cli>MES: design-time speeds up shop-floor forms and flows; runtime can query and handle, and does not change labor reporting\u003C\u002Fli>\n              \u003Cli>Case Study: Capability Base and Dual Agent Boundary\u003C\u002Fli>\n              \u003Cli>Insight: Design state and runtime state should be separated\u003C\u002Fli>\n              \u003Cli>Insight: four hard problems in enterprise AI adoption\u003C\u002Fli>\n            \u003C\u002Ful>\n          \u003C\u002Fdiv>\n          \u003Cdiv class=\"product-detail-cta scroll-reveal\">\n            \u003Ca href=\"\u002Fengines#agent\" class=\"btn btn-outline\">Back to Platform\u003C\u002Fa>\n            \u003Ca href=\"\u002Fcontact?from=agent\" class=\"btn\">Book a demo\u003C\u002Fa>\n          \u003C\u002Fdiv>\n        \u003C\u002Fdiv>\n      \u003C\u002Fdiv>\n    \u003C\u002Fdiv>\n  \u003C\u002Fsection>\n\n  \u003C!-- GEO:faq-visible:BEGIN · 由 scripts\u002Finject_geo.py 生成，请勿手改 -->\n  \u003Csection class=\"contact-faq page-section\" id=\"faq\">\n    \u003Ch2 class=\"section-title\">FAQ\u003C\u002Fh2>\n    \u003Cp class=\"section-subtitle\">Common questions on responsibility boundaries, adoption prerequisites, and platform division of labour - start here; contact us if anything remains unclear\u003C\u002Fp>\n    \u003Cdiv class=\"faq-list\">\n        \u003Cdetails class=\"faq-item\" open>\n          \u003Csummary>What do design-time and runtime agents do?\u003C\u002Fsummary>\n          \u003Cp>Design-time uses natural language to build or change application categories, apps, modules, form models, field relationships, and form, list, Vue, report, large-screen, and process pages. Results enter the designer for further editing before publish. ⌘K assists scripts and SQL. Runtime, within authorization, presents query results as in-dialog text and charts or as Office, HTML, or Markdown, and can create form data or complete reviews through platform business APIs.\u003C\u002Fp>\n        \u003C\u002Fdetails>\n        \u003Cdetails class=\"faq-item\">\n          \u003Csummary>Does editor chat or ⌘K count as a bypass publish path?\u003C\u002Fsummary>\n          \u003Cp>No. Chat and ⌘K only speed up draft scripts\u002FSQL or configuration; you must still open, edit, publish, and keep rollback in the designer. Chat output is not a production object.\u003C\u002Fp>\n        \u003C\u002Fdetails>\n        \u003Cdetails class=\"faq-item\">\n          \u003Csummary>Can runtime create data or complete a review?\u003C\u002Fsummary>\n          \u003Cp>Yes. Within the user's own permissions, form data can be created and reviews completed through platform business APIs. Validation, permissions, and audit match on-screen actions. The agent cannot exceed authorization or bypass the API to write to the database directly.\u003C\u002Fp>\n        \u003C\u002Fdetails>\n        \u003Cdetails class=\"faq-item\">\n          \u003Csummary>What is the relationship between runtime state and reports\u002Fdashboards?\u003C\u002Fsummary>\n          \u003Cp>Runtime queries can appear as in-dialog text and charts and be exported as Office, HTML, or Markdown for reporting, circulation, and filing. Cockpits, large screens, and published metric definitions stay with the reporting engine. Export files do not rewrite official definitions.\u003C\u002Fp>\n        \u003C\u002Fdetails>\n        \u003Cdetails class=\"faq-item\">\n          \u003Csummary>Does the JEDP agent require building a separate AI system?\u003C\u002Fsummary>\n          \u003Cp>Not necessary. The agent is built on the platform, directly interfacing with forms, processes, and visible business databases. Knowledge base retrieval, permissions, and audit links are built into the platform. Private deployment can be evaluated as needed; there is no need to build an AI engineering foundation from scratch, nor is there a secondary integration issue between AI and business.\u003C\u002Fp>\n        \u003C\u002Fdetails>\n        \u003Cdetails class=\"faq-item\">\n          \u003Csummary>Can agents replace the six engines?\u003C\u002Fsummary>\n          \u003Cp>No. It is an acceleration layer: in the design phase, it shortens the configuration path; in the runtime phase, it shortens the path from data to reportable conclusions. Organizations, permissions, forms, processes, reports, and integrations are still guarded at the boundaries by the corresponding engines.\u003C\u002Fp>\n        \u003C\u002Fdetails>\n        \u003Cdetails class=\"faq-item\">\n          \u003Csummary>Can queries and reviews be opened plant-wide before permissions are clear?\u003C\u002Fsummary>\n          \u003Cp>Not recommended. Runtime only queries, exports, and completes reviews inside the permission scope. If permissions have not been sampled and visibility is not frozen, finish that baseline before widening the organization.\u003C\u002Fp>\n        \u003C\u002Fdetails>\n        \u003Cdetails class=\"faq-item\">\n          \u003Csummary>Can design-time output go straight to production?\u003C\u002Fsummary>\n          \u003Cp>No. It must be opened in the designer, edited, published, and kept rollback-ready. A chat draft is not a production object.\u003C\u002Fp>\n        \u003C\u002Fdetails>\n        \u003Cdetails class=\"faq-item\">\n          \u003Csummary>Can the platform also solve data governance and organisational problems?\u003C\u002Fsummary>\n          \u003Cp>No. The platform only lowers the technical barrier. Cleaning up historical data, making tacit business rules explicit, and establishing accountability rules and organisational support for AI use still require deep, ongoing participation from the business team. The platform provides the tool and the boundaries; the enterprise leads business governance. Only together can they move from demo to a production-grade application.\u003C\u002Fp>\n        \u003C\u002Fdetails>\n    \u003C\u002Fdiv>\n  \u003C\u002Fsection>\n  \u003C!-- GEO:faq-visible:END -->\n\n  \n  \n  \n  \n  \n  \u003C!-- GEO:software-app:BEGIN · 由 scripts\u002Finject_geo.py 生成，请勿手改 -->\n  \n  \u003C!-- GEO:software-app:END -->\n\n  \u003C!-- GEO:faq:BEGIN · 由 scripts\u002Finject_geo.py 生成，请勿手改 -->\n  \n  \u003C!-- GEO:faq:END -->",1793937990224]