> ## Documentation Index > Fetch the complete documentation index at: https://docs.heroboost.me/llms.txt > Use this file to discover all available pages before exploring further. # JEV > Evaluate content with JEV micro apps — inventory, rubric, runs, results, and rewrite loops on HeroBoost Starter Agent. **JEV** is the evaluation workspace on **HeroBoost Starter Agent** chat. You create **micro apps** that score inventory (items you upload, load, or generate) against a **rubric**, review **run history**, and optionally run a **rewrite loop** to improve items that score below your threshold. Open chat → switch the side panel to **JEV**. > [!NOTE] > > JEV is for the **agent owner**. Subscriber chat does not show the JEV panel. Optional API access uses keys with scopes such as `jev_read` / `jev_run` when you enable them for your workflow. ## Words on the panel | Label | Meaning | | - | - | | **Micro app** | One evaluation configuration for this agent (you can keep several). | | **Inventory** | The set of items to score — uploaded, loaded, or generated. | | **Rubric** | Dimensions and rules used when a run scores each item. | | **Run** | One evaluation pass (System One) over the current inventory. | | **Rewrite loop** | System Two — rewrite items under the threshold, then re-run (manual or auto with early stop). | | **Send to…** | Hand off a result into another surface (for example Automation or the composer) when the product offers that destination. | ## Typical flow **1. Open JEV on your Starter Agent** From **My Agents**, find the agent → click the **chat icon** ![Chat icon on My Agents — opens Custom Chat UI](https://mintcdn.com/hb-bb10ae76/3n5pI14RaH2qkMCR/images/guides/starter-agent/jev/chat-icon.svg?fit=max\&auto=format\&n=3n5pI14RaH2qkMCR\&q=85\&s=f34ff547b9386cb9d45b01a33f8c8501) (to enter **Custom Chat UI**). In the header, choose **JEV** so the side panel shows the JEV workspace. **2. Create or select a micro app** Create a micro app, or select an existing one. You can rename or delete apps you no longer need. The selected app is remembered for this agent on this browser. **3. Build inventory** Add items by **upload**, **load**, or **generate**, depending on what your micro app supports. Confirm the inventory list before you run. **4. Set questions and rubric** Edit questions and rubric dimensions so a run knows how to score. Keep dimensions clear enough that results stay comparable across runs. **5. Run evaluation** Start a **Run**. When it finishes, open **history** / **results**. You can insert a summary into the chat composer when the panel offers that action. **6. Optional — rewrite loop** For items under your threshold, use the **rewrite loop**: revise those items into a new inventory, then run again. Auto mode can stop early when improvement stalls (product defaults exist for threshold and max rounds — adjust only if the UI exposes them). ## Settings and access * Use JEV settings on the panel for micro-app options that belong with evaluation (not the global Configure tabs for model hosting). * If you issue API credentials for JEV, keep scopes limited to what you need (`jev_read` / `jev_run`). * Subscriber-facing JEV (if you turn on any “enabled for subscribers” option in agent config) is a separate product choice — default owner chat remains the primary path documented here. ## Tips * Treat the **first successful run** as your baseline before you change the rubric mid-stream. * Prefer one micro app per evaluation purpose so history stays readable. * Pair JEV digests with [Automation](https://docs.heroboost.me/guides/starter-agent/automation.md) when you want scheduled follow-up — use **Send to…** only for destinations the UI lists. ## Related * [Starter Agent overview](https://docs.heroboost.me/guides/starter-agent/overview.md) * [Automation](https://docs.heroboost.me/guides/starter-agent/automation.md) * [Configure your agent](https://docs.heroboost.me/guides/configure-agent.md) ## Screenshots UI walkthrough for the same JEV flow — switch tabs in order (create app → inventory → questions → run → results → rewrite). **1 Create** ![Create micro app modal with Name and Source type label fields](https://mintcdn.com/hb-bb10ae76/3n5pI14RaH2qkMCR/images/guides/starter-agent/jev/01-create-micro-app.png?fit=max\&auto=format\&n=3n5pI14RaH2qkMCR\&q=85\&s=3ec8f61dc3b24cfa5a633224fc1d4296) Create micro app — name and optional source type label **2 Home** ![JEV home panel with micro apps and Workspace cards](https://mintcdn.com/hb-bb10ae76/3n5pI14RaH2qkMCR/images/guides/starter-agent/jev/02-jev-home.png?fit=max\&auto=format\&n=3n5pI14RaH2qkMCR\&q=85\&s=6ad0666acbe890b4914ddcf984ae7641) JEV home — micro apps plus Inventory, Questions, Run evaluation, and History **3 Inventory** ![Inventory versions screen with upload, generate, export, and paste JSON](https://mintcdn.com/hb-bb10ae76/3n5pI14RaH2qkMCR/images/guides/starter-agent/jev/03-inventory-versions.png?fit=max\&auto=format\&n=3n5pI14RaH2qkMCR\&q=85\&s=6f3fc436b6e3fb46c45dd5883643a231) Inventory versions — upload, generate with AI, export, and privacy notes **4 Questions** ![Questions list showing score criteria and weights](https://mintcdn.com/hb-bb10ae76/3n5pI14RaH2qkMCR/images/guides/starter-agent/jev/04-questions-list.png?fit=max\&auto=format\&n=3n5pI14RaH2qkMCR\&q=85\&s=65a525b06871f3e09a82c8d6e73e5493) Questions list — rubric rows with weights and Add question **5 Add question** ![Add question modal with question type dropdown open](https://mintcdn.com/hb-bb10ae76/3n5pI14RaH2qkMCR/images/guides/starter-agent/jev/05-add-question-modal.png?fit=max\&auto=format\&n=3n5pI14RaH2qkMCR\&q=85\&s=9212367f15ed05e9c4eb871c778dbb7d) Add question — label, instructions, type, and weight **6 Run** ![Run evaluation configuration with All records selected](https://mintcdn.com/hb-bb10ae76/3n5pI14RaH2qkMCR/images/guides/starter-agent/jev/06-run-evaluation.png?fit=max\&auto=format\&n=3n5pI14RaH2qkMCR\&q=85\&s=046f6e433a6bc0b506f7dcd8dd51f9f1) Run evaluation — scope chips, estimated API calls, model, questions to include **7 Top results** ![Completed JEV run with top results and Send to chat](https://mintcdn.com/hb-bb10ae76/3n5pI14RaH2qkMCR/images/guides/starter-agent/jev/07-completed-top-results.png?fit=max\&auto=format\&n=3n5pI14RaH2qkMCR\&q=85\&s=544b1ff7dd80a8a908d5802c469c006c) Completed run — top results and export actions in the panel **8 Results** ![Evaluation results modal table ranked by Score](https://mintcdn.com/hb-bb10ae76/3n5pI14RaH2qkMCR/images/guides/starter-agent/jev/08-evaluation-results-modal.png?fit=max\&auto=format\&n=3n5pI14RaH2qkMCR\&q=85\&s=212f04644fa36ffdbd6fb487d2c42c85) Evaluation results table in a modal **8b Full page** ![Full-page Evaluation results table with HeroBoost sidebar](https://mintcdn.com/hb-bb10ae76/3n5pI14RaH2qkMCR/images/guides/starter-agent/jev/08b-evaluation-results-full-page.png?fit=max\&auto=format\&n=3n5pI14RaH2qkMCR\&q=85\&s=c7dee84d8dce446307020bd29d242c67) Evaluation results table in the full-page popup view **9 History** ![JEV History with run export and Rewrite loop actions](https://mintcdn.com/hb-bb10ae76/3n5pI14RaH2qkMCR/images/guides/starter-agent/jev/09-history-export.png?fit=max\&auto=format\&n=3n5pI14RaH2qkMCR\&q=85\&s=cd1f94337de1dadebb2861ecbb5370c4) History — run history plus JSON, CSV, Markdown, Send to chat, Rewrite loop **10 Manual** ![Rewrite loop modal with Manual mode selected](https://mintcdn.com/hb-bb10ae76/3n5pI14RaH2qkMCR/images/guides/starter-agent/jev/10-rewrite-loop-manual.png?fit=max\&auto=format\&n=3n5pI14RaH2qkMCR\&q=85\&s=a9371828799ef9bd8c524bd123169f17) Rewrite loop — Manual mode **11 Auto** ![Rewrite loop modal with Auto mode, max rounds, and early stop](https://mintcdn.com/hb-bb10ae76/3n5pI14RaH2qkMCR/images/guides/starter-agent/jev/11-rewrite-loop-auto.png?fit=max\&auto=format\&n=3n5pI14RaH2qkMCR\&q=85\&s=bcad9b2365881b54cddf17ffcd1e9958) Rewrite loop — Auto mode This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.