Skip to Content
Platform
GuidesOverview

Overview

Guided workflows for connecting an agent, understanding its behavior, measuring improvements, and shipping with confidence.

The Core Concepts pages define the entities. These guides explain how the pieces work together, then let you try each stage. Examples show the JavaScript SDK first and the equivalent CLI path second wherever both are supported.

The loop at a glance

StageWhat you doPrimary concepts
ConnectPackage your agent as a recipe, register a runtime, point staging at it, run a first task.Recipes, Runtimes, Environments, Tasks
ObserveEvery task becomes a conversation; the platform synthesizes observations on completion and clusters them into patterns.Conversations, Observations & Patterns
InvestigateDrill top-down (patterns → observations → conversations) with structured filtering.Observations & Patterns, Conversations
EvaluateWrite a judge: a git-authored YAML rubric that grades each conversation pass / fail / not_applicable at teardown, and trend it across versions.Judges
ExperimentWhen before/after is confounded, run a live A/B between runtime versions, scored by a judge’s pass-rate.Experiments
ShipChoose from the evidence and merge that recipe’s PR; the main push activates production.Recipes, Environments
GuardLeave the judge running as a standing regression guard so quality can’t silently drift.Judges

Why a loop, not a checklist

The stages feed each other. Observations surface a failure mode; a judge encodes the standard the agent should have met; an experiment tests the fix without a confounded before/after; and shipping moves the measured version into production. The same judge stays on as a guard, so the next regression appears as a changed number and starts the loop again from a known baseline.

What stays in git vs. what’s live

A recurring theme across these workflows: behavior lives in git, operation lives on the platform.

  • In git: the recipe (instructions, profiles, skills) and judge rubrics. Iterating means a new commit, which is a new immutable recipe.
  • On the platform: runtimes, environment assignments, experiments, and a judge’s operational state (its off-switch and production sample rate).

This split makes every measurement traceable: a quality number always names the exact recipe commit that produced it, and changing how you run a judge never disturbs what it measures.

Run the four guides in order

  1. Connecting an agent: validate → runtime → staging → first task.
  2. Observing & investigating: conversation → pattern → observation → full transcript.
  3. Evaluating with judges: fixture → local evaluation → deployed judgement → judge ID.
  4. Experimenting & shipping: runtime versions → experiment → evidence → merge → production verification.

In CLI tabs, jq only moves fields from one JSON response into the next command. The CLI’s own --query flag is useful for inspection, but its JSON scalar output is quoted and is not a shell-safe raw value.

Project setup and GitHub integration happen outside these guides, and production changes when a recipe PR is merged. The CLI covers the operational steps between those Git boundaries, but it does not create integrations or merge pull requests.

Next

  • Introduction: the operator loop, framed.
  • Core Concepts: the entities these workflows act on.
  • JavaScript SDK: the primary programmatic surface used by the first tab.
  • CLI: command reference, output contract, and unsupported boundaries.
Last updated on