MBSE methodology packs
These packs drive retrieval filters, diagram pacing, and review prompts inside the engineering knowledge base and AI4MBSE. In a live session you can switch packs — next-diagram suggestions and knowledge focus follow the active pack.
MagicGrid
Common in rail, energy, and complex infrastructure. Typical next views after structure: activity and sequence.
OOSEM
Strong for regulated domains. Typical path: requirements and use cases before structure and verification clues.
Cases: mine positioning · infusion pump
Harmony-SE
Strong for embedded and robotics. Typical path: scenarios and interactions, then states and internal structure.
Cases: robot vacuum · AGV
Nine common views · one at a time
The experiment paces familiar SysML views — package, block definition, internal block, use case, requirements, activity, state machine, sequence, and parametric — without claiming every project must use all nine. The active methodology pack only changes which view is suggested next.
- PKG
- BDD
- IBD
- UC
- REQ
- ACT
- STM
- SD
- PAR
Interactive sketch (methodology switch + next chips): AI4MBSE local demos.
Locale-aware method names
When the host UI locale is Chinese or English, methodology display names and next-step prompts follow the chrome language. Modeling dialogue may still mix languages — the pack itself is engineering rhythm, not a translation gimmick.
AI Agent methodology · ADPS patterns
As Agents move from “models that answer” to systems that join workflows, engineering focus shifts to context, evidence, state, tools, permissions, collaboration, and audit. This personal lab uses the public ADPS pattern catalog as vocabulary for experiment design reviews — not a product certification.
Two-axis framework
ADPS organizes patterns on two axes. The vertical axis is cognitive function — what the Agent is doing. The horizontal axis is execution topology — how data and control flow.
| Cognitive function | One-line definition |
|---|---|
| Perception | What the Agent can see now, and in what form |
| Memory | Which experience, evidence, and state survive across turns |
| Reasoning | Compile inputs, evidence, and state into executable judgment |
| Action | Ground judgment in tools, APIs, files, workflows, and the real world |
| Reflection | Evaluate, revise, and retain outputs, failures, and trajectories |
| Collaboration | Divide, parallelize, review, and hand off among Agents |
| Governance | Bound permissions, risk, audit, and accountability |
| Topology | Verb | Fits when |
|---|---|---|
| Chain | Pass | Stable steps; prior output feeds the next |
| Route | Choose | Classify first, then pick model, tool, flow, or human review |
| Parallel | Fan out | Run branches together; trade cost for quality or latency |
| Orchestrate | Coordinate | A coordinator owns goals, task ledger, and aggregation |
| Loop | Iterate | Generate, observe, revise, until converge or trip a fuse |
| Hierarchy | Layer | Layered duty, permission, memory, or protection boundaries |
Core pattern matrix (v0.3)
ADPS v0.3 catalogs 28 core patterns, 5 extensions, and 1 candidate (34 specs). Empty matrix cells are intentional — they mean no stable first-order structure yet, or an existing pattern already covers the main problem.
| Function | Chain | Route | Parallel | Orchestrate | Loop | Hierarchy |
|---|---|---|---|---|---|---|
| Perception | P2 | P1 | P4 | P3 | — | — |
| Memory | M2 | M3 | M2 / M4 | M1 | — | — |
| Reasoning | R1 | R2 | R3 | R4 | — | — |
| Action | A3 | A1 | A2 | A4 | — | — |
| Reflection | F1 | F2 | F4 | F3 | — | — |
| Collaboration | C4 | C2 | C3 | C1 | — | — |
| Governance | G3 | G1 | G4 | G2 | — | — |
- Perception — P1 Context Triage · P2 Semantic Compaction · P3 Progressive Discovery · P4 Multi-Modal Fusion
- Memory — M1 Hierarchical Retention · M2 RAG · M3 Progress Tracking · M4 Failure Diary · M5 Procedural Memory (ext.)
- Reasoning — R1 Chain of Thought · R2 Complexity Routing · R3 Parallel Exploration · R4 Iterative Hypothesis · R5 Talker-Reasoner (ext.)
- Action — A1 Tool Dispatch · A2 Plan-Execute · A3 Prompt Chaining · A4 Guardrail Sandwich · A5 Minimal Tool Set (ext.)
- Reflection — F1 Generate-Critique · F2 Skill Pack · F3 Experience Replay · F4 Self-Heal Loop
- Collaboration — C1 Hierarchical Delegation · C2 Fan-out Aggregate · C3 Adversarial Review · C4 Handoff Chain · C5 Sub-Agent Isolation (ext.) · C6 Choreography (candidate)
- Governance — G1 Approval Gate · G2 Blast-radius Control · G3 Progressive Commitment · G4 Observability · G5 Hooks Pipeline (ext.)
Five engineering contracts
v0.3 recommends that production Agents make these contracts explicit — the main control surface between model judgment and engineering state:
- Context — what enters context, what is a handle, what is deferred or dropped (Perception).
- Evidence — source, version, scope, citation, provenance, trace (Memory / RAG).
- Decision — how model output becomes structured Route / Reasoning / Plan decisions (Reasoning).
- Action — tool metadata, parameter provenance, permissions, approval, human review, rollback (Action · Governance).
- Trace — LLM calls, tool calls, handoffs, guardrails, approvals, and state updates under one trace id (Governance).
Source & lab stance
This section summarizes the public ADPS white paper Pattern catalog & selection framework (v0.3). It offers architecture vocabulary for experiment reviews — not certification of a product. This personal lab treats ADPS as shared pattern language for Agent technical exploration, and is glad to learn from / contribute notes as a community participant. Full specs follow the ADPS source.
Related write-up: personal AI4MBSE simulation experiment report (author’s peer technical-experiment site — not an enterprise product case).
Peer research link
- ADPS · Agent Design Patterns Society Peer research community for Agent pattern language — linked as a technical-exchange reference.
How the AI4MBSE experiment uses both layers
MBSE packs shape retrieval rhythm and next-diagram hints; ADPS vocabulary frames Agent experiment review (route intent, human approval gates, evidence-aware memory). Details: AI4MBSE and KB notes · Disclaimer。