FeaturedLegal & Compliance#Skills#Python#PDF#Legal#Demand Letter#Agent

Demand Letter Generator (Agent Skill, PDF)

An agent drafts a formal payment demand letter; a bundled Python skill totals the amounts owed and renders a downloadable PDF.

Workflow at a glance

The full canvas, before you import it

Click any node to see its config.

#Skills#Python#PDF#Legal#Demand Letter#Agent

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

3 nodes · Free & source-available

Demand Letter Generator (Agent Skill, PDF)

Chase an overdue balance with a clean, formal demand letter as a PDF. The agent drafts the language, then a bundled Python Agent Skill sums the itemized amounts owed and renders the letter into a valid PDF — exact math and consistent layout, every run.

What this workflow does

  1. demandIntake captures the creditor, debtor, line items, and a payment deadline
  2. demandAgent drafts the demand language, then calls the bundled demand_letter_pdf skill
  3. The skill totals the line items in Python and renders a base64-encoded PDF
  4. demandResult returns the confirmation, total due, file name, and letter text

Why a skill

Money math and document layout belong in code. The Python skill adds the amounts precisely and produces the same correct PDF each time, so the model never has to do arithmetic.

Setup

Open demandAgent, pick an LLM credential, edit the line items and deadline, and run. This is a draft for review, not legal advice — have a qualified professional review it before sending.

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