The lab

About the squad

A living experiment in autonomous software delivery.

AI Alpha Squad started as a question: what if a small team of specialized agents could run a full delivery cycle — from a vague business ask to a tagged release — with a human Director keeping final authority?

This is an open experiment, not a finished product. It is a governed pipeline where every decision is auditable on GitHub Issues and every agent has a narrow mandate. Business Owner analyzes and seeks approval. Architect designs. Developer ships code to a target repository. QA, Security, DevOps, and Tech Writer validate in parallel. Release Manager gates the release.

Infrastructure & models

The squad runs on GitHub Actions as the runner and Hugging Face Inference Providers for the models behind every agent. Planning roles — Business Owner, Architect, QA, Security, Tech Writer, Release Manager — call the Hugging Face router and post their deliverables straight to the issue. Developer and DevOps run an Actions agent that clones the target repo and drives a Hugging Face tool loop to open a PR. Models are configurable per agent via SQUAD_HF_DEFAULT_MODEL and per-role overrides, with cost-first provider routing by default.

A GitHub Copilot coding-agent path still exists as a legacy, optional runtime, but Hugging Face on Actions is the default and the direction we build toward.

The lab is intentionally experimental. We iterate on orchestration, agent prompts, open models, and runtimes while keeping the same contract: Issues are truth. Releases need Director sign-off. WhatsApp is for speed, not for secrets.

Delivery flow

From the Director's first signal to a production release on the target repository:

AI Alpha Squad automated delivery flow Director submits work via GitHub Issues, API, or WhatsApp. The squad orchestrator dispatches agents by lifecycle label through analysis, design, implementation on the target repo, parallel validation, and release, with Director approval gates only where required. Authority Intake Work Queue Orchestrator SDLC Pipeline Delivery Director Approval gates only GH Issue REST API WhatsApp GH Issues Labels = phases Orchestrator squad-orchestrator squad-actions-agent Label → dispatch Auto-advance phases PHASE 1 Business Owner label: new Director APPROVE awaiting-approval PHASE 2 Architect director-approved PHASE 3 Developer Actions + HF label: designed Auto PR merged → implemented Target Repo PR / CI/CD PHASE 4 - PARALLEL VALIDATION label: implemented → orchestrator dispatches all QA Security DevOps Tech Writer Auto Reports in → validation PHASE 5 Release Mgr label: validation Director APPROVE release-candidate PHASE 6 Released label: released Ship Tag / Release Agent teams / validation Orchestrator dispatch Auto-advance (phase watch) Director gate (human) Squad agents (Actions + HF)

Supported communication

Three intake paths converge on the same work queue. Pick what fits your workflow:

GitHub Issues The canonical queue. Labels track lifecycle: new → awaiting-approval → approved → designed → implemented → validation → release-candidate → released.
REST API Automate issue creation, labeling, and project board updates with the GitHub REST API. Ideal for CI hooks, internal tools, and agent-to-agent handoffs.
WhatsApp Director channel for approvals and release go/no-go. Only Business Owner and Release Manager agents send outbound messages; inbound replies are classified and posted back to the issue within minutes.