# Section 13 · Summary decision matrix Everything above fits in one decision table. Each row is a trade-off, with its recommended default and the signal that commands a change. ## The trade-off matrix | Decision | Recommended default | Evolve when | | --- | --- | --- | | Core language | TypeScript (orchestration and interface) | Never without a reason; polyglot goes through a sidecar or a service. | | Specialized capability | Sidecar in the library's language | As soon as a mature library lives in another ecosystem. | | Component on the critical path | Compiled service behind a contract | Latency or throughput proven insufficient. | | Decomposition | Hexagonal modular monolith | Load, lifecycle, isolation, or high availability demand it. | | Integration with legacy systems | Anticorruption layer behind the port | Progressive replacement, feature by feature, never in one block. | | Number of agents | Single orchestrator directing specialists | Parallelizable complexity, never for sequential reasoning. | | Model abstraction | Single port, three tiers, direct SDK | Never a heavy chaining framework by default. | | State | Stateless agent, immutable journal plus derived working view | Multi-instance: externalize the in-memory structures. | | Crossing the process boundary | As late as possible, on an objective trigger | Then accept eventual consistency, compensation, and explicit causal order. | | Contract evolution | Versioned, additive, read with a tolerant reader | Breaking change: expand then contract, under consumer-driven verification. | | Memory and forgetting | Value score, invalidation (not deletion), consolidation with pointers to the source facts | Physical deletion reserved for invalidated derivatives under retention. | | Evaluation | Tests, plus a continuous, guarded evaluation loop | Bounded self-tuning only, guarded, under human override. | | Multi-agent budget and discovery | Central aggregated counter, in-memory registry | Block allocation and shared capability cards as soon as you leave the process. | | Model unavailable | Multi-provider failover behind the port | Available from real go-live onward. | | Changing the model (new or updated) | Validate in shadow deployment, then in stages | Never in a single move; rollback at the slightest divergence. | | Waiting for a human approval | Suspend and release (durable state), rehydrate on decision | Never block the process; low-urgency requests batched in a queue. | | Non-critical service | Fail-open, signaled degraded mode | Sensitive action: explicitly fail-closed instead. | | Delegation autonomy | Bounded: templates, budgets, approvals | Widen only if the outcome actually improves. | | Untrusted inputs | Retrieved content untrusted, least privilege, approval on the action | High privilege: dedicated patterns (frozen plan, quarantine of the untrusted). | | Agent identity | Its own principal, distinct from the user served; explicit delegation, bounded in time and scope | Never borrowing the user's full rights; an agent outside the registry = a security anomaly. | | Runtime secrets | Placeholder on the agent side, real key attached at the network boundary, allowed destinations | Never a key in the model's context or in the execution environment. | | Shared building block (connectors, skills, cross-application memory, delivery) | Consumed via a port; adapter = discovery client via an index (section 15) | The index stays an index; delivery delivers; the orchestrator decides. | ## Quick decision tree > Diagram : Does the capability depend on a mature library in another language? · YES · sidecar in that language · NO · stay in the TypeScript core · Does a component have its own load, lifecycle, or isolation? · YES · extract it as a service · NO · stay in the modular monolith · Is the task parallelizable and highly complex? · YES · several agents under one orchestrator · NO · single orchestrator, one single thread · Must the load be carried across several instances? · YES · externalize the state, then replicate · NO · single instance, in-memory state ok **Key takeaways** - Every decision has a sober default and an explicit evolution trigger. - The cross-cutting rule: start simple, isolate behind contracts, add complexity only on evidence. - None of these decisions is irreversible, because all of them are made behind a boundary. --- © Thibault Souris, 2026 · Creative Commons BY-ND 4.0 (https://creativecommons.org/licenses/by-nd/4.0/) · the work’s text unaltered, as plain text for this page; the PDF version is the reference: https://runward.dev/docs/en/reference/doctrine/Designing-and-Running-Agentic-Systems-2026.pdf