Band of Agents
Multi-agent marketing-compliance board for global campaigns
Band Review Board is a compliance war-room staffed by AI agents. A brand drops a whole marketing campaign (a hero video, its cutdown posts, banners, images) into a shared band.ai room, and a cast of specialist agents clears every material against the advertising and regulatory rules of each market it will run in: US FTC, EU health-claim and GDPR rules, LATAM. The agents do not run a checklist in a line. They hold competing mandates and argue. When a claim is legal in the US but a banned health claim in the EU, the region reviewers debate it on the record, holding or conceding their block, and only a genuine deadlock reaches the human. Every verdict traces back to a specific rule and the agent that raised it.

- Role
- Product design and engineering
- Year
- 2026
- Platform
- Software project
- Status
- shipped
The problem
A single asset sold into several markets carries stacked, parallel legal liability, because each jurisdiction sets its own rules, ceilings, and required disclosures. Miss one cross-border conflict and the downside is real: GDPR fines reach 20M euro or 4% of global turnover, the UK's DMCC Act up to 10%, US FTC penalties per violation. Band Review Board surfaces the exact conflict a lone legal team misses and proves every call with an audit trail.
What I built
The work includes band-review-board-web, server, agents.
The choices behind it.
Solo · design + engineering
Implementation choice
Real agent-to-agent debate, not a merged checklist: when two region reviewers split on a claim (one blocks the span, another clears it), the Reg Lead runs a one-round rebuttal where each blocking region holds or concedes on the record. A conceded block drops to a warning; a held block is logged as a conflict (hold/concede stance schema in pod-region-reviewer.ts, wired through pod-lead.ts).
Implementation choice
Two orchestration topologies coexist: a pods cast (Claims / Regulatory / Brand pods on a deterministic decision spine, 17 agents at full size) and a lighter classic cast (coordinator to region/brand reviewers to reconcile). The live band.ai room runs a compact 10-agent variant of the pods cast to fit the room's agent cap, keeping the Regulatory pod's full US/EU/LATAM debate.
Implementation choice
The orchestration spine is deterministic on purpose: the Conductor, pod leads, and Risk Adjudicator call no model, so routing and the terminal verdict (published / spiked / escalated) are auditable rather than left to an LLM.
Implementation choice
Multi-model by design: MODEL_MODE (aiml | dev | vertex) swaps the whole fleet behind one ModelClient. Each agent runs the family that fits its job (GPT-5, Gemini 2.5 Pro, an open Llama, Claude Haiku/Sonnet/Opus, DeepSeek, and Nano Banana for localized image regen), and MODEL_MODE=vertex runs the entire fleet on one GCP credential.
Implementation choice
Multimodal perception pre-pass: one vision model sees each video and image (ffmpeg-sampled keyframes), one Whisper-class model hears the audio, and the resulting text artifacts (description, on-screen text, detected claims, transcript) cascade to every reviewer, even the text-only ones.
Implementation choice
Runs end-to-end with zero API keys on an in-process fake band.ai transport, covered by 53 Vitest files. A Hono + SSE backend streams the negotiation into a React/Tailwind console with a live material x region verdict matrix.
- Build detail
- 17-agent full pods cast (+ 1 human)
- Build detail
- 10-agent compact cast for the live band.ai room
- Vitest test files
- 53
- model-routing modes (aiml / dev / vertex)
- 3
- regional rulebooks (US / EU / LATAM)
- 3
- input modalities (text, image, audio)
- 3
Under the surface.
band-review-board-web
appReact, Tailwind, and React Router console (web/) that streams a live review over SSE: the campaign board, the material by region verdict matrix, the analyzing panel, and the rulebook editor.
server
serviceHono HTTP and SSE backend (src/server) that starts a review locally or against a live Band room and relays every board event to the web console.
agents
libraryThe full cast in src/agents: Conductor, Scout, Claim and Evidence, Precedent, Disclosure, the US, EU, and LATAM reviewers, the brand reviewers, the Mediator, the Risk Adjudicator, and Remediation, plus the lighter classic Coordinator and Reconcile board.
board
libraryThe orchestration engine in src/board: board, campaign, and pod sessions, the pod hub, and the event model that carries findings and verdicts through a deterministic decision sequence.
band
libraryThe Band.ai coordination seam in src/band: a real @band-ai/sdk transport and an in-process fake for tests, shared-context rehydration, and cross-framework wiring.
models
libraryA provider-agnostic ModelClient in src/models whose MODEL_MODE routing fans each agent across AIML, Vertex/Gemini, Bedrock/Claude, and Featherless, with per-call spend tracking and retry.
perception
workerThe multimodal pre-pass in src/perception that samples video keyframes, runs vision, and transcribes audio so every text reviewer can see and hear the asset before it grades.
domain
libraryCampaign, asset, rulebook, and finding Zod types in src/domain, plus rulebook smart-import from .md or .json and curated per-market presets (US FTC, EU health claims, LATAM).
Build details Stack, scope, and implementation
Built with
- TypeScript 5.7
- Node 22 (ESM)
- Hono 4
- band.ai SDK
- React + Tailwind
- Vite
- Vitest
- Zod
- OpenAI SDK (AIML gateway)
- Google GenAI / Vertex
- AWS Bedrock
- Featherless
Areas
- multi-agent
- AI agents
- compliance
- band.ai
- multimodal
- LLM orchestration
More about the project
Built solo for the Band of Agents hackathon, it ships two orchestration shapes: a pods cast of up to 17 agents on a deterministic decision spine (a compact 10-agent subset connects to the live band.ai room to fit its agent cap), and a lighter classic coordinator/reconcile cast. A multi-model routing layer runs each agent on the model that fits its job, and a multimodal pre-pass watches the video and reads the audio before any reviewer sees the asset. A Hono + SSE backend streams the whole negotiation into a React console.
Try the product.
Interactive demo · Open full screen