VI · Multi-AgentEmerging★

Pipeline Triad Pattern

also known as Creator-Critic-Arbiter Triad, Maker-Checker-Approver for Agents

Staff each pipeline stage with a triad — Creator generates an artifact, Critic finds flaws, Arbiter makes a binding PASS/FAIL/PARTIAL decision — with four explicit human gates between stages.

This pattern helps complete certain larger patterns —

  • specialisesGenerator-Critic Separation★— Strict role separation between a Generator agent that produces drafts and a Critic agent that judges them against pre-defined criteria; the Critic never generates.

Context

A team replaces a sequential human pipeline (analyst → developer → reviewer → tester) with agents. Naive replacement (one agent per stage) loses the cross-check that human pipelines had built-in. Critical decisions get rubber-stamped because no agent has the role of Arbiter.

Problem

Single-agent-per-stage pipelines lose the maker-checker-approver structure that gave human pipelines their robustness. Without explicit Creator/Critic/Arbiter triads, agents drift, errors propagate, and there's no binding decision point. Russian Habr 2026 source documents this as the pattern from banking compliance applied to agent pipelines.

Forces

  • Triads triple per-stage cost compared to single-agent stages.
  • Human gates between stages add latency.
  • Arbiter role requires clear authority to pass/fail/partial — not just another reviewer.

Example

A bank's customer-onboarding pipeline replaces analyst→developer→tester with three triads. Stage 1 (KYC document analysis): Creator extracts fields, Critic flags inconsistencies, Arbiter rules PASS/FAIL/PARTIAL. Human gate 1 (requirement validation): officer reviews high-PARTIAL cases. Stage 2 (risk-scoring): another triad. Human gate 2 (readiness). And so on. Mirrors how a human team would have worked, with cross-check baked in.

Diagram

Solution

Therefore:

Per stage: Creator agent produces the artifact (spec, code, test, doc). Critic agent finds flaws with detailed reasoning. Arbiter agent makes PASS/FAIL/PARTIAL decision with citation to both Creator's output and Critic's flaws. Between stages: four human gates structurally enforce review at requirement, readiness, deployment, production-confirmation transitions. Mirrors banking maker-checker-approver compliance. Pair with supervisor-plus-gate, policy-gated-agent-action, human-in-the-loop.

What this pattern forbids. No pipeline stage executes without all three triad roles (Creator + Critic + Arbiter); no inter-stage transition without passing the appropriate human gate.

And the patterns that stand alongside it, or against it —

  • complementsSupervisor-Plus-Gate★— Supervisor controller that validates and gates LLM outputs against deterministic checks before they commit to side-effects.
  • complementsPolicy-Gated Agent Action (KRITIS)★— Each agent action passes through a policy gate (NIS2, EU the agent Act, BSI rules) and is tagged with Run ID + Model Digest + Policy Hash for WORM-audit reconstruction.
  • complementsHuman-in-the-Loop★★— Require explicit human approval at defined points before the agent performs an action.
  • complementsApproval Queue★★— Queue agent-proposed actions for asynchronous human review while the agent continues other work.

Neighbourhood

Click any neighbour to follow the language. Scroll to zoom, drag to pan.

References

Provenance