State model
Shared case state uses explicit field ownership. Specialist private state remains local; only contract-approved facts, summaries and open work may be promoted.
Meetings mix discussion, proposals, decisions, actions and sensitive material, while later summaries often erase uncertainty and ownership.
The system drafts a typed record that separates proposed, agreed and unresolved items, then routes each statement to the correct owner for confirmation.
Organisations, systems and operating conditions are intentionally anonymised and recomposed. The design demonstrates engineering and banking-domain reasoning; it does not represent a named client estate, vendor product or measured production result.
A shared authority core coordinates independently owned capability cells, domain systems and operating evidence.
Permitted workThe system may summarise approved work information and suggest next steps. Employment, performance and access decisions remain authorised human processes.
Consistency rulePreserve authorship, decision status, supersession and source permissions; a meeting summary cannot create an approved decision.
Hard boundaryThe model is not a system of record, identity provider, policy authority or proof that an external effect occurred.
Several specialist capabilities contribute to one journey while the customer should experience one conversation and one accountable owner.
No action or decision becomes authoritative until its named owner confirms it; restricted content is excluded by role.
A deterministic outer workflow contains model-led work inside typed, observable calls. Dashed messages remain proposals until policy or a human grants authority.
Shared case state uses explicit field ownership. Specialist private state remains local; only contract-approved facts, summaries and open work may be promoted.
Use versioned request, response, error and artefact envelopes. Every edge declares caller, represented subject, purpose, expiry and allowed capability.
One writer owns each shared field. Parallel branches return proposals that the orchestrator merges through deterministic conflict rules.
These roles are deliberately vendor-neutral. Each can be independently owned, versioned and replaced.
Accepts a typed evidence request and returns the minimum permitted facts with source, event time, observation time, validity and exclusions.
Returns candidate entities and typed relationships with match features, contradictions, effective dates and non-merge evidence.
Appends request, versions, policy result, model proposal, approval, action receipt, readback, correction and custody events under one correlation key.
Presents claims beside evidence, alternatives, uncertainty, missing information, permitted actions and current custody.
Evaluates identity, purpose, capability, amount, risk tier and policy version; returns allow, deny, step-up or human-review with reasons.
Durable records carry provenance, authority, effect and custody without turning a transcript into an uncontrolled memory store.
Preserve authorship, decision status, supersession and source permissions; a meeting summary cannot create an approved decision.
The selected design is not universally superior. It is the safer fit for this boundary and failure cost.
Prefetch stable, purpose-safe facts; acquire volatile facts on demand against a time-qualified snapshot.
Load a broad customer profile at session start.
Cost acceptedThe selected design adds source calls and latency, but reduces stale data, excess exposure and accidental reuse.
Bias consequential journeys against false merge and retain unresolved candidates.
Automatically merge the highest-scoring candidate.
Cost acceptedMore cases require clarification, but one person's authority or risk cannot silently attach to another.
Use append-only events plus a rebuildable current-state projection.
Overwrite the case row with its latest status.
Cost acceptedReplay and storage are more complex, but point-in-time reconstruction and correction lineage remain possible.
Keep people at irreversible, ambiguous and policy-exception points; sample lower-risk automated outcomes independently.
Require the same manual approval at every step.
Cost acceptedRisk-tiering reduces review load but needs calibrated thresholds, sampling and immediate withdrawal of authority when drift appears.
Compile stable decision logic and retain retrieval for explanation and residual ambiguity.
Ask a model to interpret the source document for every request.
Cost acceptedRule compilation needs controlled change, but creates repeatable decisions, regression tests and clear exceptions.
Retries are bounded by knowledge of business effect; unknown outcome remains visible, owned and independently reconciled.
Actual thresholds belong to accountable service owners. The design exposes the equations and observables that those owners must baseline.
downstream_calls = routed_turns x average_branch_fanoutp95_route = classifier + max(parallel_branches) + merge + validationreview_load = ambiguous_routes + rejected_handoffs + policy_stepupsApply source permissions at retrieval time and prevent private messages, sensitive HR data or draft content from crossing purpose boundaries.
A design is production-ready only when teams can prove what happened, recover it and change it safely.
source-permission trimming
decision versus discussion classification
sensitive-data exclusion
feedback and correction lineage
Source transcript, speaker mapping, decision status, owner confirmation, redactions and amendment history.
Named participants confirm decisions and actions.
Begin with deterministic routing and explicit handoff. Add dynamic selection and parallel delegation only after edge contracts, loop tests and shared-state ownership are proven.
Business, HR, knowledge, security and information-management owners define permitted uses.