Dently - Dental AI Scribe

DreamXV AI Studio

DreamXV AI Studio is a cinematic multi-agent AI platform built to transform game creation from a complex workflow into an intelligent collaborative experience. Created by Sahir Ali (Dream XV), DreamXV AI Studio demonstrates how multiple AI agents can work together like a real game studio. Instead of relying on a single model, the platform orchestrates specialized agents using the Band SDK to simulate a professional game development pipeline. When a creator enters an idea such as "Create a Zombie RPG Shooter", the system launches a collaborative workflow: Chief Agent analyzes the project and creates the development plan. Story Agent generates lore, narrative arcs, and themes. Character Agent creates playable characters, NPCs, abilities, and personalities. World Agent designs environments, atmosphere, progression systems, and world-building. Gameplay Agent generates mechanics, combat systems, progression loops, and difficulty balancing. Art Agent creates concept art prompts and visual references using AI image generation. QA Agent reviews the project for consistency and quality. Documentation Agent generates game design documentation for future development. The platform provides real-time execution tracking, agent status visualization, progress monitoring, and AI-powered project generation directly inside a premium web interface. DreamXV AI Studio runs entirely on Vercel serverless infrastructure, requiring no external backend setup for judges. AI processing is powered by Featherless AI with AIMLAPI as a fallback layer for reliability. The project showcases the future of collaborative AI systems where agents do not merely generate text but actively coordinate, review, and improve each other's work. While built for game development, the underlying architecture can be extended to software engineering, creative studios, and enterprise workflows. Dream XV's vision is simple: "Born at 15. Built for Infinity."

Novus - Research Intelligence Assistant

Novus is a multi-agent AI platform that transforms enterprise R&D workflows by automating the entire research intelligence pipeline — from duplication detection to grant proposal generation — in under 3 minutes. The Problem: Fortune 500 companies lose $28 billion annually funding research that already exists. R&D teams spend months writing grant proposals across disconnected tools with no unified system to check duplication, find grants, and ensure compliance simultaneously. Our Solution: Novus deploys 6 specialized AI agents coordinated through Band SDK: 1. Intake Agent — Parses R&D proposals and extracts competitive intelligence signals 2. Duplication Scout — Scans 200M+ papers across Semantic Scholar, OpenAlex and arXiv in real time 3. Relevance Agent — Scores proposals against current industry funding trends 4. Eligibility Agent — Matches to live grants from Grants.gov and NIH Reporter, surfaces already-funded competing research 5. Proposal Writer — Drafts complete, funder-aligned grant proposals automatically 6. Compliance Agent — Reviews against grant requirements before submission Key Features: - Real academic paper search with authors, years and source links - Live grant matching with direct Apply Now links - Already-funded similar research discovery with award amounts - International funder recommendations including EU Horizon, Wellcome Trust and Gates Foundation - Full audit trail via AgentOps - Beautiful React Flow live agent pipeline visualization Tech Stack: Band SDK, Anthropic Claude, AI/ML API, Featherless AI, Semantic Scholar, OpenAlex, arXiv, Grants.gov, NIH Reporter, Next.js, React Flow, AgentOps, Qdrant

Contract Redline War Room

Contract Redline War Room is a regulated, multi-agent contract review desk where five specialized AI agents - Coordinator, Legal, Risk, Finance, and Compliance - collaborate through Band to redline a contract, quantify financial exposure, and assemble an approval packet that no single agent can sign off on alone. The Coordinator opens a Band room, discovers its peers with band_lookup_peers, and recruits the specialists with band_add_participant. Legal redlines clauses and cites the exact source text. Risk scores severity and dollar exposure. Finance computes worst-case financial impact. Compliance runs a policy check using Featherless AI's open-source inference and can VETO the recommendation, forcing a visible Coordinator re-plan loop - this is real coordination, not a fixed pipeline. Every agent-to-agent handoff, finding, state change, and discovery is a genuine Band primitive (band_send_message with @mentions, band_send_event, band_lookup_peers, band_add_participant, band_create_chatroom) driven through the real Band SDK, with each agent authenticating with its own API key. Once the agents converge on an aggregated exposure score and redline packet, a human reviewer holds the only key: Approve, Reject, or Request Changes. The decision seals a SHA-256 hash-chained audit trail; GET /api/verify/{id} recomputes the entire chain so any later edit is detectable, giving regulators a defensible record of exactly how the recommendation was reached. AI/ML API powers the primary reasoning for Coordinator, Legal, Risk, and Finance, while Featherless AI serves the Compliance agent's open-source policy-classification model - both partner technologies are exercised live and tallied at /api/health. This turns days of cross-functional contract review into minutes, with a tamper-evident sign-off record built for Track 3: Regulated and High-Stakes Workflows.

ClaimPilot

ClaimPilot: Multi-Agent Insurance Claims Resolution Platform Filing an insurance claim is historically a slow, stressful, and opaque process. Policyholders often wait weeks for simple claims to be processed, while insurance providers lose significant resources to manual administrative overhead, inconsistent decisions, and undetected fraud. ClaimPilot solves this problem by transforming insurance claims from human-centric queues into an automated, event-driven multi-agent orchestration. The platform deploys a specialized team of AI agents—acting as Reviewers, Investigators, Adjusters, and Resolvers—that collaborate in real-time inside secure rooms to investigate and resolve claims. For simple, low-risk claims, ClaimPilot processes and approves settlements instantly, providing policyholders with immediate relief. For complex or high-risk claims, the system automatically recruits specialized investigative agents to check timeline gaps and calculate coverage. Once a final decision is reached, the system executes payments, sends notifications, and seals a legally binding, transparent audit trail. By replacing traditional manual delays with automated intelligence, ClaimPilot bridges the gap between speed and compliance. It protects insurance companies from fraud, ensures consistent and fair adjustments, and provides policyholders with clear, fast, and transparent outcomes they can trust.

Recourse — Adversarial Claims Adjudication

Recourse convenes five specialized AI agents in a single Band room to adjudicate disputed insurance claims — and the debate itself becomes a legally-defensible, tamper-evident audit trail. A human claims officer keeps the final word. The problem: appeals on denied claims are usually decided by one overworked reviewer, under time pressure, with no one arguing the other side — and no record of how the call was made. How Band is the coordination layer (not a wrapper): all five agents live in one Band room and act through the official Band Agent API. Context, task handoffs and state changes flow through the room — the Coordinator drives turn order, agents respond only to @mentions (the visibility model is respected), and structured agent-to-agent handoffs move the case from argument → policy → challenge → resolution. The room transcript is the system of record the human officer signs off on. The 5 agents: Coordinator (opens the case, routes handoffs) · Blake (argues for the insured) · Morgan (cites the exact policy clauses via RAG) · Alex (devil's advocate, fights to deny) · Sam (writes the signed, reasoned resolution). Defensible by design: clauses cited by number (§7.3, §12.1), full transcript SHA-256 hashed, deterministic payout math, human approve/override. 🎬 Commercial: https://youtu.be/HhmUWdQ2ZSs 🖥️ Live walkthrough (agents debating end-to-end): https://youtu.be/2hd0-p9l4DE 🔗 Live app: https://recourseband.duckdns.org 💻 Code (MIT): https://github.com/kasbsquall/recourse Stack: Band Agent API · GPT-4o (AI/ML API) for Blake/Morgan/Sam · Hermes-2-Pro (Featherless) for Alex · FastAPI + async SQLAlchemy + SSE · Next.js 14 · PostgreSQL + pgvector (RAG, all-MiniLM-L6-v2) · Docker on a VPS behind OpenLiteSpeed. Track 3 — Regulated & High-Stakes.