Point One Zero Platform architecturev11 · generated viewSign in to edit
Playbook › Build: agent development

Build: agent development

The build phase: agent development through the ADLC. The four tracks hand their outputs to one disciplined pipeline. The differentiating construct is the mini-output: every agent produces a bounded, independently reviewable piece of the final deliverable, and only the orchestrator assembles the whole. No single agent ever writes the final artifact.

Step by step

Enter the pipeline

  1. ADLC entry. One-page spec plus an architecture decision record per capability, referencing its PRD-evals from Track 2 and its pattern (P1 to P7).
  2. Split per the determination rule. Everything with a testable right answer goes to the domain rule library as deterministic code; only judgment steps become agent work. The split was drafted in Tracks 2 and 3; here it is enforced by review.
  3. Author to the SSRA contract. One skill per use case; agent definitions carrying the four-part delegation spec (objective, output format, tools and sources, boundaries); run contracts with a machine-checkable end state, a token budget, and effort scaling for the job class.

Mini-outputs and assembly

  1. Mini-outputs. Each agent's run contract names the mini-output it owes: a section, a reconciled table, a risk register entry, a cited analysis. Mini-outputs are structured content, small enough to review in minutes and to regenerate cheaply.
  2. Orchestrated assembly. The orchestrator collects mini-outputs, checks completeness against the dependency graph, and assembles the final deliverable through the deterministic rendering boundary: immutable template plus approved structured data. The orchestrator submits; it never authors.

Quality engineering

  1. Guardrails on every output. Every mini-output passes deterministic checks before it is eligible for assembly: schema validity, citation presence, no unapproved values, classification respected.
  2. Loop engineering. Each mini-output is scored against its evals; a failing output regenerates with the eval verdict fed back, bounded by the run contract's budget; persistent failure escalates to a person rather than burning budget.
  3. Automated unit tests as evals. Every agent is mapped to its capability and target metrics; the PRD-evals run as pre-deploy gates in CI, alongside the deterministic test suite. Nothing ships scoring below its predecessor, and nothing unregistered can reach client data.
  4. Integration wiring. The parametrized requirements from Track 3 are configured, never coded: connections, contracts, mappings, and schedules land as plane values and the pipelines run from templates.

Exit criteria per capability

CheckEvidence
Evals pass at targetPRD-eval scores at or above threshold on golden exemplars
Tests greenDeterministic suite plus tool-layer evals in CI
Human review configuredHITL placement, approvers, and escalation timers set in the plane
Pattern and antipattern reviewBuild maps to one of the seven patterns; antipattern checklist clean