Gamma

Before any screen was styled, the core flows were laid out in low fidelity: the workflow canvas, the traces list and the trace it opens. The wireframes settled hierarchy and density first, and the shortest path from a failing run to its cause.

The spec then turned them into numbers engineering could build from: a 54 px icon rail, 28 px page gutters, 16 px between blocks, 38 px controls and 62 px table rows, all on an 8-point rhythm and taken straight from the Figma auto layout.

A visual builder lets anyone connect inputs, an AI model, knowledge and real tools such as Gmail on a canvas, then run the flow and watch each step before publishing.

Business teams that understood the work could finally build agents themselves, without waiting weeks for engineering.

Experiments compare every new version with production on real cases, and releases move to production gradually, with automatic rollback if error, latency or cost leave their limits.

Once live, every run becomes a trace that can be replayed span by span, with automatic evaluations on each answer.

An agent in production needs to be explainable. Tracing shows each execution as a tree: what the agent received, which tools it called, how long each step took and what it cost. Monitors turn that data into alerts with a probable cause, not just a red number.

Enterprises only scale what they can govern. Guardrails are written as policies anyone can read, versions go out in gradual rollouts and budgets show cost per agent, so security, engineering and finance look at the same product.

Make the invisible visible: trust in AI comes from evidence, so every run, change and cost had to be something people could see and replay.

Governance is part of the UX. Guardrails, approvals and audit logs designed in from the start turned security from a blocker into a reason to adopt.