The harness

Build, Run, And Govern Agents In One Place.

Create chat and worker agents with the model, instructions, tools, knowledge, and policy that define how they operate. Publish only after the required governance checks pass.

Book a WalkthroughRead the Trace Model
What you get

Governance Is Part Of The Build

The builder carries agent configuration, policy assignment, impact assessment, deployment gates, run history, and lifecycle records together. There is no separate governance handoff after the build.

account_tree

Chat And Worker Agents

Build interactive chat agents for people, or worker agents for jobs triggered manually, on a schedule, by webhook, API, workflow step, or file upload.

timeline

Knowledge And Tools

Ground an agent in approved documents, choose its tools, and restrict it to knowledge data when the task demands a bounded answer.

policy

Policy Templates That Enforce

Every agent runs under a policy template that combines data, access, spend, and violation rules. It can lock models, limit tools and sources, require human approval, and determine how a violation is handled.

inventory_2

Publish Gates And Lifecycle

Draft agents do not become Live until required pre-flight checks pass. Published agents retain run history, gate evaluations, and lifecycle changes.

savings

Spend Limits And Alerts

Per-policy model locks, daily spend caps, and alert thresholds set agent guardrails. Alerts warn as a threshold is reached; a spend cap blocks the run.

monitoring

Organization-Wide Spend Controls

Daily and monthly budgets notify the people responsible. A monthly hard limit blocks new worker runs until the limit is raised or the period resets.

One run

Every Run Leaves A Reviewable Record

plan
retrieve
reason
tool: policy_check
write - blocked

Run history records status, inputs, outputs, tools, token use, estimated cost, duration, and any guardrail outcome. Open a run when a result needs review.

Platforms

From Definition To Execution

inventory_2

Draft With Intent

Start with an agent mode, team, policy, trigger, model, instructions, tools, and data.

play_circle

Run In Context

Use the agent canvas for file-upload work, or let schedules, webhooks, APIs, and workflows start runs.

history

Review What Happened

Inspect run history and the governance record beside the agent, including risks, evaluations, data sources, and gate history.