An AI Agent Paused. What Should Your Code Do Next?

A developer building the Insight oracle SDK has outlined a design pattern for AI trading agents that pause mid-workflow, arguing that applications should preserve three distinct states — assessed risk, insufficient evidence, and service failure — rather than collapsing them into a single failed status. The writeup includes a TypeScript example using the InsightGuard client to check quote coverage and freshness before an ETH-to-USDC swap, and notes that freshness thresholds are application settings rather than universal requirements. The author also warns that evidence keeps aging after authorization, so executors should re-validate deadlines at dispatch.

An automated trading workflow can pause because it detected a risk, lacked sufficient evidence, or encountered a service failure. These conditions need different recovery paths. If your application collapses them into one failed state, operators and retry logic lose information they need. While building Insight, I have been working on making these distinctions visible through coverage, freshness, and assessment diagnostics. Consider a hypothetical ETH → USDC swap. Several quotes agree, but one source is too old and another has no known update timestamp. The application may lack enough eligible evidence to evaluate the trade under its configured policy. That is a different situation from detecting significant disagreement between valid sources. I would preserve three categories in the application's workflow record: These are application design categories, not Insight SDK enum values. A service failure should retain request and error information. It should not be rewritten as zero market coverage. Here is an assessment-only TypeScript example using the Insight SDK: js import { InsightGuard } from 'oracle-insight-guard'; const apiKey = process.env.INSIGHT API KEY; if apiKey throw new Error 'INSIGHT API KEY is required' ; const guard = new InsightGuard { apiKey, freshness: { maxSourceAgeSeconds: 300, maxAssessmentAgeSeconds: 60, minimumRemainingValiditySeconds: 15, }, } ; const coverage = await guard.client.coverage { asset: 'USDC', chainId: 1, probe: true, maxSourceAgeSeconds: 300, } ; const assessment = await guard.assessSwap { source: { asset: 'ETH', destinationAsset: 'USDC', chainId: 1, action: 'swap', tradeAmountUsd: 1 000, }, destination: { asset: 'USDC', destinationAsset: 'ETH', chainId: 1, action: 'swap', tradeAmountUsd: 1 000, }, receipt: { settlementChainId: 1, maxSlippageBps: 50, }, } ; console.log JSON.stringify { coverage, diagnostics: assessment.diagnostics, freshness: assessment.freshness, }, null, 2 ; Install the package with npm install oracle-insight-guard . Run the example in a trusted server or agent runtime with an Insight API key. It makes metered API requests; it does not sign or broadcast a transaction. The freshness thresholds above are example application settings, not universal requirements for every asset or strategy. Important distinctions: A useful recovery policy can specify: A successful retry establishes that the operation succeeded. The application still needs to evaluate the returned evidence. Refreshing an assessment also creates a new evidence commitment. If the previous authorization bound the old commitment, obtain a new authorization before proceeding. Evidence continues to age while a transaction is prepared and signed. An earlier freshness check cannot account for every later delay. The executor should validate the applicable deadlines at actual dispatch, including delays inside its own submission callback. Insight supplies assessment evidence and diagnostics. The application owns its execution policy. When using PriorSeal, authorization and observed execution can be linked to the relevant evidence through an exact-call workflow. For each paused workflow, preserve: Keep credentials and private keys out of these records. The goal is to give the application enough information to decide what recovery requires—and give a reviewer enough information to understand that decision. How does your agent distinguish an assessed risk from an incomplete assessment?