Pipeline stages overview

The eight stages your Brief moves through, end to end.

A run proceeds through eight stages, in order. Each stage reads from the running graph + chunked Brief and adds new nodes.

The stages

#StageInputOutput
1IngestYour Brief + support docsChunked, embedded text in the retrieval index
2Brief ParserIngest outputProject metadata, seed constraints, initial stakeholders
3Stakeholder AnalysisBrief Parser + chunksNGOs, MOEs, scenarios, HSI, enabling products
4RequirementsStakeholders + chunksFunctional/performance/interface/constraint requirements, MOPs, TPMs
5DecompositionRequirements + chunksFunctions, components, interfaces, DTRs
6DesignDecomposition + chunksDesign specs, interface specs, verification & validation activities
7CriticEverything generated so farQuality gate; may trigger revisions
8RenderFinal graphArtifact bundle (JSON + Markdown)

Trade studies and risk assessment run alongside the Design stage, operating on graph synthesis (no new chunks). Phase-gate readiness is the final synthesis pass before render.

Why stages matter

Each stage is a checkpoint:

  • Outputs are persisted between stages, so a failure in stage 5 doesn't lose the work from stages 1–4
  • Revisions can target a single stage — you don't have to rerun everything to fix a stakeholder node (see Revisions)
  • Citations flow forward — a requirement cites the stakeholder need it traces to, which cites the Brief passage that defined the need

Cost per stage

Approximate CU consumption for a Phase-1.4 run on a 1,500-word Brief:

StageCU (approx)% of total
Ingest12%
Brief Parser49%
Stakeholder614%
Requirements819%
Decomposition717%
Design1024%
Critic49%
Render25%
Total~42

Actual costs vary with Brief length and complexity. The pre-run estimate uses the median for your Brief size.

Want detail per stage?