All experiments
Labs · Research

Agent roles

Why a small team of scoped agents beats one generalist trying to do everything.

Why it matters

The problem we're chasing

A single generalist agent has to be an expert at product, architecture and delivery all at once. Splitting responsibility — the way a strong organization does — makes each proposal more grounded, and far easier for a human to review.

What we're exploring

The questions, not the recipe

We publish the direction we're working in — not how we build it. The mechanism is what makes TaskForce different, so it stays in the lab until it ships.

  • H1 Scoping an agent's responsibility so it stays in its lane
  • H2 How specialized roles hand work off to one another
  • H3 Where a human's judgment sits between them

Where it stands. The direction shows up in Orchestration, which is Planned. This is research, not a shipped feature.

Follow where this goes

The roadmap is public. Hold us to it — and start with what ships today.