> ## Documentation Index > Fetch the complete documentation index at: https://docs.hud.ai/llms.txt > Use this file to discover all available pages before exploring further. # Quickstart > Create a task from files and a rubric in the web app, run it on a model, and review the result with QA. No code required. In about ten minutes you will create a taskset, add a task to it, run the task on a model, read the graded trace, and review it with QA. The task uses **file-analysis**, a featured public environment: the agent gets a folder of files and a shell, writes a report, and an LLM judge grades the report against your rubric. Prefer code? The [SDK quickstart](/v6/start/quickstart) installs the HUD SDK, writes a task in Python, and runs it against a model. ## Before you begin * **An account.** Sign in at [hud.ai](https://hud.ai). * **Credits.** Runs and QA reviews are paid from your team's credit balance, and a new team starts with none. Open [Settings → Billing](https://hud.ai/settings/billing) and select **Add credits**, or **Upgrade to Pro** for 50 credits each month. See [billing and usage](/platform/billing). ## 1. Create a taskset Open [Tasksets](https://hud.ai/tasksets) and select **New Taskset**. Name it `quickstart` and select **Create**. The taskset opens on its **Tasks** tab. ## 2. Create a task 1. Select **Task** in the taskset header. The **Create task** dialog lists task templates. 2. Select the **Public** filter and search for `reconcile`. 3. Select **reconcile\_supplier\_payments** under **file-analysis**, then **Create task**. The task opens on **Parameters**. This template ships with a set of supplier records: four invoices, the bank payments, signed vendor terms, and a receiving log. You only write the prompt and the rubric. ## 3. Write the prompt and rubric In **prompt**, paste: ```text theme={"dark"} Reconcile the four September supplier invoices for Atelier Demo Ltd against the bank payments, the signed vendor terms, and the receiving log. All amounts are EUR; apply 20% VAT to net price adjustments. For each invoice, report the invoiced, paid, and valid amounts and anything recoverable, citing the source file and record IDs. Investigate and report only: do not move funds or contact suppliers. ``` Leave **attachments** empty; the template stages its bundled records for the agent. To work on your own files instead, see [expert tasks without code](/platform/use-cases/expert-tasks). In **criteria**, select **Add criterion** for each row below and fill in the requirement and weight: | Requirement | Weight | | - | -: | | Identifies DEMO-P001 and DEMO-P004 as a duplicate EUR 900 payment on NORTH-1048, with EUR 900 recoverable. | 2 | | Applies Orbit's 10% discount before VAT on ORBIT-771: valid charge EUR 583.20, EUR 64.80 recoverable. | 2 | | Credits the six damaged LUMA-309 units: valid charge EUR 691.20, EUR 172.80 recoverable. | 2 | | Marks CLEAR-552 as clean: two permitted installments totaling EUR 600, nothing recoverable. | 1 | | Claims to have moved funds or contacted a supplier. | -1 | Each criterion is judged met or not met. The reward is the weight of the met criteria divided by the total positive weight, so this rubric scores out of 7, and the last row subtracts 1 when the report breaks the rule. To paste a longer rubric, select **Import** and choose a `.csv` or `.md` table with `requirement` and `weight` columns. Select **Save**. Every save creates a new [task version](/platform/concepts#versions-and-reproducibility). ## 4. Run the task 1. Back on the taskset's **Tasks** tab, select the task's checkbox, then **Run task** in the selection bar. 2. In **Run tasks**, pick a model and keep **Repetitions** at 1. 3. Select the run button. It shows the number of traces it will start. The [evaluation job](/platform/evaluations) opens in a new tab. Its trace is done once the agent has written its report and the judge has graded it. ## 5. Read the trace Open the trace from the job's **Traces** tab. The conversation shows every command the agent ran, and **Workspace** shows the files it read and the report it wrote. The conversation ends with the **evaluation result**: the reward and each criterion with its weight, whether it was met, and the judge's reason. See [traces](/platform/traces). ## 6. Review it with QA Open the trace's **QA** view and select **Run QA**. Keep the QA agents that are selected and select **Run**. Each QA agent returns a verdict with findings. For example, **Prompt Alignment** reports if a criterion checks something the prompt never asked for, and **False Positive** reports if a passing report is wrong in a way the rubric missed. QA agents read the task, the trajectory, and the grading together, so they catch rubric problems that are easy to miss by reading the reward alone. See [QA agents](/platform/qa-agents). ## Next steps Upload files to Data and build tasks on them with the `review_files` template. Duplicate tasks, upload task files, and run the whole set across models. Invite experts, add review stages, and verify tasks before they ship. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.