Skip to content

Forenly/slack-agent-builder

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

RobotOps · Slack Agent Builder Challenge

Forenly AI Systems' entry for the Slack Agent Builder Challenge (Salesforce / Slack) — build intelligent agents that ship in Slack.

RobotOps is a Slack agent that acts as the human-in-the-loop interface to an autonomous robot fleet. Operators receive live inspection alerts and anomaly reports from robots directly in Slack, approve or reject high-risk robot actions without leaving the workspace, and query real-time fleet status — all through natural language.

Community

Building this in the open — join the team chat on Discord: https://discord.gg/DCmAYYE32h

⚠️ Eligibility check first

This hackathon is 18+ and only specific countries/territories are included (allow-list, not exclude-list). Confirm Turkey is on the eligible list before investing build time — see View Full Rules on Devpost.

Track

  • New Slack Agent — automate workflows / connect systems / surface insights inside Slack

Required tech (use ≥1)

  • Slack AI capabilities — natural-language fleet queries and alert summarisation
  • MCP server integration — robot fleet MCP server exposes live sensor readings, job queue, and action approval endpoints
  • Real-Time Search (RTS) API — surface the latest inspection logs and anomaly reports inline in Slack

Fast on-ramp: slack create agent + ready-made HR/IT/Sales templates → running agent in an afternoon.

What we're building

RobotOps is a Slack agent that sits between an autonomous robot fleet and the human operators who oversee it. Robots surface inspection results, motion-planning conflicts, and anomaly detections as structured Slack messages. When a robot requests a high-risk action — entering a restricted zone, picking up an unrecognised object, pausing a production line — the agent posts an approval card to the relevant operator channel. A single approve/reject click unblocks the robot in real time. Between alerts, operators can ask the agent natural-language questions ("Which units flagged a fault in the last hour?", "What's the current battery level on unit 7?") and get answers sourced from the live fleet MCP server.

Architecture

See ARCHITECTURE.md — required diagram.

Key dates

Date Event
14 Jul 2026, 01:00 GMT+1 Submission deadline

Submission checklist

  • Track selected
  • Text description (features + functionality)
  • Demo video ~3 min, shows the working project
  • Architecture diagram
  • URL to Slack developer sandbox — grant access to slackhack@salesforce.com and testing@devpost.com

Judging criteria

Technological Implementation (uses ≥1 of Slack AI / MCP / RTS) · Design (FE/BE balance) · Potential Impact · Quality of the Idea.

Prizes ($42,000)

Per track (New Agent / for Good / for Orgs): 1st $8,000, 2nd $4,000 (+ Dreamforce 2026 vouchers, certification, swag for 1st). Plus Best UX $2,000, Most Innovative $2,000, Best Technological Implementation $2,000.

Status

Pre-build. Track locked (New Slack Agent). Concept locked. See docs/HACKATHON_REQUIREMENTS.md.

Team

Forenly AI Systems · github.com/Forenly

License

Apache License 2.0

About

Slack HITL agent for autonomous robot fleets — approve robot actions, query fleet status, and receive inspection alerts, all in Slack.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors