{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XXPEHMODY3QY46UONJEHM4ZSU6","short_pith_number":"pith:XXPEHMOD","schema_version":"1.0","canonical_sha256":"bdde43b1c3c6e18e7a8e6a48767332a7897bd368d90ac131fd9e083c85526709","source":{"kind":"arxiv","id":"2605.10907","version":3},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.10907","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-05-11T17:46:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e628fff59a68483bf2aee7a6647e9dced7d34ee89e3ddea525a7aaf1cf421343","abstract_canon_sha256":"48633943e6f16b3d2df6a401be7f5d886d74cd8407d92ce0b61af34dda3338a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:37.375180Z","signature_b64":"IE7NLVINM2oRVPAshTY8olgsT4AXVIxDQMWopZ7zHuDCVbNh/uyU+EQdOfJ/r4Km5IBX7wOIPEKIt+/blAaQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdde43b1c3c6e18e7a8e6a48767332a7897bd368d90ac131fd9e083c85526709","last_reissued_at":"2026-06-11T01:10:37.374452Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:37.374452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.10907","created_at":"2026-06-11T01:10:37.374544+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.10907v3","created_at":"2026-06-11T01:10:37.374544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10907","created_at":"2026-06-11T01:10:37.374544+00:00"},{"alias_kind":"pith_short_12","alias_value":"XXPEHMODY3QY","created_at":"2026-06-11T01:10:37.374544+00:00"},{"alias_kind":"pith_short_16","alias_value":"XXPEHMODY3QY46UO","created_at":"2026-06-11T01:10:37.374544+00:00"},{"alias_kind":"pith_short_8","alias_value":"XXPEHMOD","created_at":"2026-06-11T01:10:37.374544+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XXPEHMODY3QY46UONJEHM4ZSU6","json":"https://pith.science/pith/XXPEHMODY3QY46UONJEHM4ZSU6.json","graph_json":"https://pith.science/api/pith-number/XXPEHMODY3QY46UONJEHM4ZSU6/graph.json","events_json":"https://pith.science/api/pith-number/XXPEHMODY3QY46UONJEHM4ZSU6/events.json","paper":"https://pith.science/paper/XXPEHMOD"},"agent_actions":{"view_html":"https://pith.science/pith/XXPEHMODY3QY46UONJEHM4ZSU6","download_json":"https://pith.science/pith/XXPEHMODY3QY46UONJEHM4ZSU6.json","view_paper":"https://pith.science/paper/XXPEHMOD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.10907&json=true","fetch_graph":"https://pith.science/api/pith-number/XXPEHMODY3QY46UONJEHM4ZSU6/graph.json","fetch_events":"https://pith.science/api/pith-number/XXPEHMODY3QY46UONJEHM4ZSU6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XXPEHMODY3QY46UONJEHM4ZSU6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XXPEHMODY3QY46UONJEHM4ZSU6/action/storage_attestation","attest_author":"https://pith.science/pith/XXPEHMODY3QY46UONJEHM4ZSU6/action/author_attestation","sign_citation":"https://pith.science/pith/XXPEHMODY3QY46UONJEHM4ZSU6/action/citation_signature","submit_replication":"https://pith.science/pith/XXPEHMODY3QY46UONJEHM4ZSU6/action/replication_record"}},"created_at":"2026-06-11T01:10:37.374544+00:00","updated_at":"2026-06-11T01:10:37.374544+00:00"}