FeaturedEducation & Learning#PDF Assignment#Rubric Feedback#Assessment#Grading Assistant#LlamaParse#Education

PDF Assignment Rubric Feedback Agent

Accept a PDF assignment upload, parse it, apply a teacher rubric, and draft formative feedback with a human-review gate.

Workflow at a glance

The full canvas, before you import it

Click any node to see its config.

#PDF Assignment#Rubric Feedback#Assessment#Grading Assistant#LlamaParse#Education

Click a node to select it — same as the Heym editor; the panel shows its settings.

7 nodes · Free & source-available

PDF Assignment Rubric Feedback Agent

This education assessment template handles PDF upload evaluation without turning the model into the final grader. The agent parses the uploaded assignment, applies a rubric, drafts formative feedback, and flags uncertain cases for teacher review.

What this workflow does

  1. AssignmentUpload creates a single-use PDF upload link
  2. llamaParseAssignment parses the PDF into Markdown
  3. RubricFeedbackAgent drafts rubric-aligned feedback and evidence
  4. TeacherReviewGate branches when the agent includes TEACHER_REVIEW
  5. NotifyTeacherReview posts uncertain cases to Slack
  6. EmailStudentFeedback sends review-ready feedback to the teacher inbox
  7. RubricFeedbackResult returns the feedback packet

Setup

Replace YOUR_LLAMAPARSE_KEY, connect an LLM credential, and paste your rubric into RubricFeedbackAgent before using real student work.

How to import this template

  1. 1Click Import → Copy JSON on this page.
  2. 2Open your Heym and navigate to a workflow canvas.
  3. 3PressCmd+V/Ctrl+V— nodes appear instantly.
  4. 4Add your API keys in the node config panels and click Run.
More workflow templates
View all templates
Heym
incident analysis · production AI
Observed across 100s of AI rollouts

AI workflows don't fail because of prompts.
They fail because of orchestration.

symptom · glue code01
5 tools
Scripts, vector DB, approval bot, tracing, browser runner — none of them talk.
symptom · visibility02
~0%
Observable behavior across the stack. Debugging is guesswork.
with heym · one runtime
1 canvas
Agents, RAG, HITL, MCP, traces & evals. Self-hosted. Observable.
AI-Native RuntimeProduction-Grade
github.com/heymrun/heym