Discovery suite
Stage 1 of the pipeline. Discovery runs the pre-build phase of an engagement: it ingests meeting transcripts, emails and a client questionnaire, and maintains a citation-backed requirements-catalog.yaml plus an ADR-style decision log, surfacing contradictions and gaps as it goes. The goal is to cut billable discovery hours while producing a defensible "who decided what, and why" trail.
Client fit and value
Any data or transformation engagement
Discovery is technology-agnostic and works for greenfield, brownfield, migration and remediation programmes—especially where knowledge is dispersed across stakeholders.
Clarity without losing the evidence
Teams get an agreed catalogue, decision trail, ownership queue and meeting-ready follow-ups instead of disconnected notes and undocumented assumptions.
A reusable governance habit
The engagement record becomes a living, version-controlled asset the client can maintain after KPMG leaves, reducing reliance on individual memory.
The six sub-agents
| Agent | Role |
|---|---|
extractor | high-recall extraction of cited items from artefacts (citations enforced in code) |
maintainer (catalog_merge) | high-precision merge into the catalogue; preserves approved, supersedes/retires |
decision_tracker (decision_lifecycle) | ADR drafting + lifecycle state machine |
contradiction_finder | surfaces genuine contradictions as open questions (never auto-resolves) |
approval_capture | email/meeting/Teams evidence → finalises ADR approvals |
gap_analyst | drafts next-meeting agenda + follow-up emails, chases TBD owners |
The intake workflow
Every artefact goes through the same pipeline: normalize → extract → contradiction-find → catalog-maintain → decision-track → gap-analyse. One ingestion event in, one updated and defensible engagement record out. Alongside the agents sit a Foundry coordinator (multi-tenant tools, model swapping) and a Teams bot surface for chat and adaptive-card approvals.
Outputs and guarantees
The catalogue and decision records are the contract the modelling suite consumes — and the same requirements-catalog.yaml is what renders the navigable catalogues under Engagements (see the Meridian worked example).
The invariants are enforced in code, not prompts: no requirement without a source citation; no decision marked approved without approval evidence; no silent contradiction resolution; and no catalogue write without recording the prompt version and input hashes.