{"paper":{"title":"Engineering Robustness into Personal Agents with the AI Workflow Store","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"AI agents must incorporate rigorous software engineering through reusable hardened workflows to achieve production-grade reliability and security.","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Lillian Tsai, Mariana Raykova, Pierre Tholoniat, Roxana Geambasu, Trishita Tiwari, Wen Zhang, Wen Zhang (Google)","submitted_at":"2026-05-11T17:46:33Z","abstract_excerpt":"The dominant paradigm for AI agents is an \"on-the-fly\" loop in which agents synthesize plans and execute actions within seconds or minutes in response to user prompts. We argue that this paradigm short-circuits disciplined software engineering (SE) processes -- iterative design, rigorous testing, adversarial evaluation, staged deployment, and more -- that have delivered the (relatively) reliable and secure systems we use today. By focusing on rapid, real-time synthesis, are AI agents effectively delivering users improvised prototypes rather than systems fit for high-stakes scenarios in which u"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"By focusing on rapid, real-time synthesis, are AI agents effectively delivering users improvised prototypes rather than systems fit for high-stakes scenarios in which users may unwittingly apply them?","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the extra compute and time required for rigorous SE processes can be amortized through reuse across a broad user community without losing the responsiveness users expect.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"AI agents should shift from on-the-fly plan synthesis to invoking pre-engineered, tested, and reusable workflows stored in an AI Workflow Store to gain reliability and security.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"AI agents must incorporate rigorous software engineering through reusable hardened workflows to achieve production-grade reliability and security.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a0993dab057b2bc5cfd735124be4f5acc79317f3cc527541e72e7ec230172f66"},"source":{"id":"2605.10907","kind":"arxiv","version":3},"verdict":{"id":"25bf6b1d-59e6-459b-bfc7-fca9b2b4e9b5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T03:05:35.197055Z","strongest_claim":"By focusing on rapid, real-time synthesis, are AI agents effectively delivering users improvised prototypes rather than systems fit for high-stakes scenarios in which users may unwittingly apply them?","one_line_summary":"AI agents should shift from on-the-fly plan synthesis to invoking pre-engineered, tested, and reusable workflows stored in an AI Workflow Store to gain reliability and security.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the extra compute and time required for rigorous SE processes can be amortized through reuse across a broad user community without losing the responsiveness users expect.","pith_extraction_headline":"AI agents must incorporate rigorous software engineering through reusable hardened workflows to achieve production-grade reliability and security."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.10907/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T05:02:00.967985Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T14:33:29.499229Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T10:31:17.278263Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T08:54:29.679251Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"997b118c6e31f4a216bec2275c4145c6f118bb2487233dffadce94ebf18bf828"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}