Planeon.aiDiscuss your workflow
Journey Studio

From a workflow to a working proposal.

My requests
Search 36 use cases

Journey / Follow a business request from understanding to authorization and a verified outcome. Explore each harness’s AML responsibilities as it takes part.

Retail & e-commerce / human-initiated

Redirect a paid order

Maya asks to ship a paid order to her office instead of home.

Review this workflow with Planeon ↗

Illustrative reference scenario, not a live run. Named people, results, scores and durations are teaching examples. 38 live handoffs in this variant, including additional dialogue or repeated work; omitted branches remain inspectable.

1 / 41 frames
Pass 1 · Ingress
1 Compute: The compute, scheduling, networking and resilience substrate every other harness sits on — Kubernetes across public and private cloud, GPU-aware and multi-tenant from the start.2 Model: Serve, version and scale the models — proprietary and open-weight — with predictable latency and cost, and keep them swappable so no single provider becomes load-bearing.3 Gateway: One control point for every model call: authentication, tenant quota, routing, caching, cost metering and the edge layer of guardrail enforcement.4 Interaction: The surfaces where people meet the system — and where they steer it: channels, streaming, sessions, clarification, provenance display and the approval moments that make autonomy safe.5 Secure&Safe: Runtime enforcement on every call, plus the agentic attack surface: non-human identity, injection and PII defence, output validation, supply chain, circuit breakers and kill switches.6 Governance: Decide how much independence each action may have, prove it with policy-as-code and human checkpoints, and run the change control that lets the system improve safely.7 Observability: Make any task reconstructable end to end and attribute its cost: OpenTelemetry GenAI spans carrying trace, thread and task IDs, the acting identity, the policy decision and the token spend.8 Evaluation: Grade the system at five scopes, prove reliability across repeated runs, red-team it adversarially, and gate every promotion on the evidence.9 Protocol: Standard contracts at every boundary so frameworks stay replaceable: MCP downward to tools and data, A2A sideways to peer agents, OpenAPI and AsyncAPI to the rest of the estate.10 Orchestration: Plan and decompose the task, route work to the right agent or tool, checkpoint durably so long tasks survive restarts, and stop cleanly when budget or policy says so.11 Action: The action surface: typed tool contracts, packaged skills, an explicit read-versus-write authority model, and isolation strong enough for code the model wrote.12 ML: Keep discriminative and optimisation models in the architecture as first-class tools and routing signals — often cheaper, faster and more accurate than asking a language model.13 Domain: Shared, machine-usable meaning: ontologies, a semantic layer, agreed metric definitions and regulation expressed as knowledge the agent can reason over.14 Data: Governed access to source systems with lineage and entitlements attached — the data plane behind retrieval, deliberately separate from the tool plane that takes actions.15 Retrieval: Assemble the smallest sufficient context for each step, inside a token budget: hybrid retrieval, reranking, graph traversal, iterative refinement, compaction and tool search.16 Memory: Decide deliberately what persists beyond a task — working, episodic, semantic and procedural memory — with an explicit write policy, retention limits and poisoning controls.THE MODELIntelligenceOne part of the systemUser / channelEvent / triggerExternal systems
Runtime planeTrust planeExecution planeKnowledge plane
RequestResponseEvidence across the live task

Ring position groups concerns, not deployment dependencies. Animation pace is for reading, not measured latency.

Select a named harness
All exchanges and omitted work

Record what can be verified.

Preserve supplied inputs, applied policies, tool actions, approval records and state changes. A useful audit trail reconstructs the operation; it does not expose private chain-of-thought.

Recovery has three different jobs.

Stop future actions; restore a compatible release; compensate for external effects where possible. Restoring software cannot unsend an email or undo every transaction.

Inspect the release bundle ↗

In the canonical reference, messages 16 and 17 are one reasoning request/response pair crossing the model core—not two invocations. Other scenarios may add intent calls, repeat the reasoning loop or omit it. Inspect this scenario in Explorer ↗

Technical reference: the 43 canonical exchanges

Only two exchanges cross the model core.

In this canonical example, messages 16 and 17 are one request/response pair—not two model invocations or a universal scenario count. Other workflows can repeat, omit or add work.

Hover or focus a node for its operation. Open it to inspect the corresponding step in the default retail Journey.

01U → EXPRtask arrives on a channel02EXPR → GWsession and tenant context03GW → GUARDscreen before spending a token04GUARD → GWcleared · scoped agent identity05GW → ORCHplan, inside this budget06ORCH → DOMwhat do these terms mean?07DOM → ORCHresolved entities and metrics08ORCH → RETassemble context for this step09RET → DATAgoverned rows and columns10DATA → RETdata with lineage and entitlements11RET → MEMwhat do we already know?12MEM → RETepisodic, semantic, procedural13RET → ORCHcontext inside the token budget14ORCH → GWreason over this context15GW → INFERrouted, cached, metered16INFER → COREinference on a pinned model17CORE → INFERcompletion18INFER → ORCHnext action, schema-valid19ORCH → GOVscore against autonomy policy20GOV → EXPRapproval at a durable checkpoint21EXPR → GOVhuman decision22GOV → ORCHproceed unattended, logged23ORCH → TOOLexecute the typed tool call24TOOL → INFRAprovision an isolated sandbox25INFRA → TOOLmicroVM, gVisor or Wasm ready26TOOL → MLHclassify, rerank or forecast27MLH → TOOLscore or plan, far cheaper28TOOL → PROTOcross on a standard contract29PROTO → EXTMCP to systems · A2A to peers30EXT → PROTOresult or task handle31PROTO → TOOLtyped result or typed error32TOOL → ORCHobserve, then re-plan33ORCH → MEMwrite back what earns persistence34ORCH → GUARDvalidate the final output35GUARD → GWschema-valid and policy-clean36GW → EXPRmetered and charged to the tenant37EXPR → Uanswer, with provenance38ORCH → OBSa span for every hop39OBS → EVALtraces become eval cases40EVAL → GOVevidence for the release gate41GOV → ORCHredeploy versioned artefacts42GOV → GUARDpolicy compiled into enforcement43INFRA → OBScapacity, cost and availability