> ## 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.

# Expert tasks without code

> Turn your files and professional judgment into graded tasks in the web app, check them with QA, and review them as a team.

For analysts, consultants, lawyers, scientists, and other domain experts who know what good work
looks like. You write a task in the web app from three parts: the files the agent works from, a
prompt, and a rubric. HUD runs models on it, and QA agents check that the rubric grades what you
meant. New to HUD? The [quickstart](/platform/quickstart) builds one on bundled records first.

## What a task is made of

Tasks like this use the `review_files` template of the featured **file-analysis** environment.
For example, a lease review:

| Part | What you write | Example |
| - | - | - |
| **Files** | The material the agent works from, uploaded to [Data](/platform/data). | `lease-2024.md`, `rent-roll.csv` |
| **Prompt** | The work, and everything the answer is judged on. | "Summarize the tenant's obligations under the lease, and flag every term that disagrees with the rent roll." |
| **Rubric** | Weighted criteria the answer is checked against. | "States that rent rises 3% each January" (weight 2), "Says the tenant may sublet without consent" (weight -1) |

The agent reads the files in a sandboxed shell with no network access and writes a report. An LLM
judge then checks the report against each criterion. The judge reads the prompt and the report,
not your files, so a criterion has to say what the right answer is. A missing or empty report
scores 0.

The agent has Python's standard library and no way to install more, so it works best with text:
Markdown, CSV, JSON, or plain text. Export spreadsheets to CSV and documents to Markdown or text
before you upload them. For other formats or tools, an engineer can build an environment from the
**Argument Hints** template (`hud init my-env --template argument-hints`); its tasks get the same
editors in the web app.

## Build and check a task

<Steps>
  <Step title="Upload your files">
    Upload them on [Data](https://hud.ai/data) and keep them team-shared, so everyone who runs the
    task can use them. See [upload files](/platform/data#upload-files).
  </Step>

  <Step title="Create the task">
    Open a [taskset](/platform/tasksets), select **Task**, choose **Public**, and pick
    `review_files` under **file-analysis**.
  </Step>

  <Step title="Write the prompt, files, and rubric">
    Write the prompt, select **Add files** under **attachments** to pick your uploads, and add one
    criterion per requirement. To reuse a rubric, import it from a CSV file or a Markdown table.
    See [write a rubric](/platform/create-tasks#write-a-rubric).
  </Step>

  <Step title="Run it">
    Run the task on a few models, with several repetitions each. Each trace shows what the agent
    read and wrote, and each criterion's verdict with the judge's reason. See
    [evaluations](/platform/evaluations).
  </Step>

  <Step title="Check it with QA">
    Run QA on the traces. **Prompt Alignment** finds criteria the prompt never asks for,
    **False Positive** finds passing answers that are wrong, and **False Negative** finds correct
    answers the rubric failed. Fix the task and run it again. See [run QA](/platform/run-qa).
  </Step>

  <Step title="Send it for review">
    Mark the task ready. A reviewer verifies it or asks for a revision. See
    [task lifecycle](/platform/task-lifecycle).
  </Step>
</Steps>

Every save creates a new task version, and traces keep the version they ran, so you can improve a
task without losing earlier results.

## Write rubrics that hold up

* **Put the answer in the criterion.** The judge never sees your files. "Identifies the duplicate
  EUR 900 payment on invoice NORTH-1048" can be checked; "Finds the duplicate payment" cannot.
* **Put one requirement in each criterion.** Each criterion is met or not, so a combined one loses
  partial credit.
* **Say in the prompt what the rubric checks.** A requirement only the rubric knows about grades
  the agent on something it was never asked to do. Prompt Alignment flags these.
* **Penalize with negative weights.** Write the behavior itself, such as "Claims to have contacted
  the supplier", and give it a negative weight.
* **Weight what matters.** The reward is the weight of the met criteria divided by the total
  positive weight.
* **Expect variance.** Run several repetitions before trusting a score, and read what QA says about
  the failures.

## Work as a team

At scale, a few reviewers check the work of many authors:

* **Authors.** Invite contract authors as [External members](/platform/team#roles), so they see
  only their own work and what is shared with them.
* **Projects.** Organize the work in [projects](/platform/projects) and grant access per project.
* **Review.** Add review stages, such as an expert check, to a taskset, and reviewers work from one
  [review queue](/platform/task-lifecycle#the-review-queue).

<Columns cols={3}>
  <Card title="Quickstart" icon="rocket" href="/platform/quickstart">
    Build and grade a first task on bundled records.
  </Card>

  <Card title="Create tasks" icon="https://mintcdn.com/hud-f5fd7c15/9ozVUWR-rlBrAGzN/platform/icons/task.svg?fit=max&auto=format&n=9ozVUWR-rlBrAGzN&q=85&s=58c9fac5728b943f15db08fc292f109d" href="/platform/create-tasks" width="24" height="24" data-path="platform/icons/task.svg">
    Every editor, versions, and bulk upload.
  </Card>

  <Card title="Fix what QA finds" icon="wrench" href="/platform/qa-results#fix-what-qa-finds">
    Turn findings into task fixes.
  </Card>
</Columns>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.