← Back to Stack
Architecture

Multi-agent orchestration

Specialist agents under one orchestrator, with explicit handoffs, retries and a human approval gate before anything irreversible runs.

Core principles

01

One orchestrator, many specialists

A single planning agent decomposes work and dispatches. Each specialist has narrow tools and one job, so failures stay contained.

02

Failure is a normal path

Timeouts, bad tool output and refused calls are expected. Retries are bounded, and exhausted retries escalate rather than loop.

03

Humans hold the gate

Anything that spends money, contacts a person or changes regulated data pauses for explicit approval. The pause is visible, not hidden.

04

Every run is observable

Each step writes a timestamped trace: who acted, which tool ran, what it cost, and why it stopped.

Agents

Orchestrator

Plans, decomposes, dispatches and reconciles results

Research

Collects and verifies external information

Code

Writes, executes and repairs implementation work

Data

Queries, reconciles and shapes structured records

Outreach

Composes and sends outbound communication

Security

Checks permissions and exposure before release

Compliance

Maps behaviour to the applicable framework

Memory

Holds durable context across runs