# Section 09 · Execution resilience An agentic system composes nondeterministic, fallible dependencies: model, sidecars, external services. Resilience is designed in by default, not after the incident. ## Classify the error before reacting Each failure is first classified, because the right response depends on the type of error. We distinguish transient errors, validation errors, and business errors. | Error type | Strategy | | --- | --- | | Transient (network, timeout, overload) | Retry with bounded exponential backoff. | | Validation (output not conforming to the contract) | Single retry with the diagnostic reinjected into the context. | | Business (missing resource, impossible action) | Delegation to a diagnostic step, or escalation for human review. | | Model provider unavailable | Automatic failover to a fallback provider, behind the same port. | | Non-critical service unavailable | Degraded mode; the application continues without the affected function. | ## 1 Fail-open for the non-critical, fail-closed for the sensitive A non-critical dependency that goes down must not bring down the system: cache, observability, enrichment switch to silent degraded mode. Conversely, a sensitive action (mutation, write, external push) fails closed and explicitly rather than executing in doubt. The rule: degrade reads, never actions. ## 2 Feature detection and bimodal deployment At startup, the system detects the services actually available according to the configuration. A missing dependency cleanly disables the associated function, without crashing. The result is a bimodal deployment: a minimal mode that runs on the bare essentials, and a full mode when all dependencies are present. The interface signals what is active rather than failing silently. ## Diagram, failover and degradation > Diagram : MODEL CALL · NON-CRITICAL DEPENDENCY · primary provider · ok · response · failure · fallback provider · same port · cache · observability · enrichment · ok · response · failure · degraded mode · silent, signaled in the UI · SENSITIVE ACTION: no silent fallback. Failure closed, explicit, traced. **Key takeaways** - Classify the error first: transient, validation, business, provider, non-critical. - Fail-open for reads and the non-critical, fail-closed and explicit for sensitive actions. - Multi-provider failover behind the same port, with no rewrite. Distinct from promoting a new model, which is first validated in shadow deployment (section 12): the availability fallback is immediate, promotion is earned. - Feature detection at startup and bimodal deployment, minimal or full. --- © 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