FeaturedApp Integrations#Football#Live Score#Commentary#WebSocket#Redis#Discord

Live Football Score Commentary with Dedupe

Normalize live match events, suppress provider retries with Redis, write grounded fan commentary, and post each new update to Discord.

Workflow at a glance

The full canvas, before you import it

Click any node to see its config.

#Football#Live Score#Commentary#WebSocket#Redis#Discord

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

11 nodes · Free & source-available

Live Football Score Commentary with Dedupe

Turn a football data provider's WebSocket events into concise supporter updates without posting the same goal twice. The workflow filters socket lifecycle events, normalizes the provider payload, checks a Redis idempotency key, and asks an LLM to write commentary using only the score and event details supplied.

What this workflow does

  1. FootballFeed listens for live score-provider messages
  2. HasMatchEvent ignores connection and heartbeat events
  3. NormalizeMatchEvent maps provider fields to a stable event object
  4. SeenFootballEvent checks Redis for a six-hour dedupe key
  5. New events go to WriteFanCommentary, then Discord, then Redis
  6. Duplicate and lifecycle events end in separate lightweight receipts

Use cases

  • Football fan Discord updates
  • Live score overlays and match rooms
  • Club community automation
  • Idempotent sports-event relays

Setup

Replace the WebSocket URL, headers, and field mappings with your licensed live-score provider. Connect Redis, an LLM, and a Discord webhook. Confirm the provider's event ID stability and data-use terms. The commentary prompt may rephrase supplied facts but must never invent scorers, assists, cards, statistics, or context.

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