
Overview
Pengwin puts event coordination and office operations in one Slack channel. Mike asked Concierge to plan a Salesforce Park meetup for 30 founders, source 24 water bottles, draft invitations, and review the swag budget. Concierge saved one project and delegated the work. Events proposed October 27–29 and found the official park inquiry route. Buyer checked Printful and estimated $486–$561.84 for 24 bottles. Treasurer reviewed that estimate against the recorded $1,100 allocation and identified the delivered total needed for approval. Follow-up questions to each agent recalled the same saved project. The public page shows their work and shared memory. Slack is the workspace; Vultr Cloud Compute and DeepSeek V4.1 Flash power the crew; Eventbrite API supports approved RSVP publishing; Airwallex connects currency-specific wallet balances to local-currency payouts. For Challenge 1, the separate /sandbox page shows Vultr-generated code running on an isolated, networkless VM with a ten-second limit, cleanup, and a subsequent successful run. A small sandbox scaffold predates kickoff; the deployed integrations and event workflow were built after kickoff.
Note: the demo URL is substituted with the GitHub repository link.
Tech stack
No comments yet
Be the first to comment on this project.

sentinel
Full-Stack Self-Healing DevOps & Security Copilot The Concept: An AI operations engineer that doesn't just suggest code fixes—it monitors cloud infra, detects uptime/security drops, automatically provisions fixes, and generates audit reports for enterprise compliance.

Agency Compiler
Agentic creative project compiler. Most creatives, agencies and designers dont know how to use ai, none the less agents. We created a platform that allows a creative agency or studio owner to instantly spin up agents based on the project ask, resources and scale.

ProofRun
ProofRun helps developers answer a critical question before shipping: will this update break behavior users rely on? An AI agent inspects two Git revisions, designs targeted experiments, and proposes repairs. An independent Docker-based verifier runs those experiments against both versions, preserves the original tests, and checks whether the repair actually works. Developers receive an update, skip, or postpone recommendation with recorded evidence and a reviewable patch. In a live synthetic…


