{"observation":{"id":"8a3bac73-a767-41c2-a295-f2f33f5aacf4","tool":"zep","tool_name":"Zep","criterion":"update-and-correction-handling","criterion_name":"Update and Correction Handling","criterion_definition":"Checks whether the tool can replace or invalidate outdated memories when corrected.","criterion_evidence_type":"transformation","criterion_rank_role":"decisive","criterion_rank_role_reason":"A memory system has to replace or invalidate outdated information, or it will keep feeding the agent wrong context. (3 of 3 judges)","scenario":"client-relationship-memory","scenario_name":"Client Relationship Memory","group_tag":"memory-for-ai-agents","scenario_description":"A client-support memory test that checks whether the assistant remembers prior troubleshooting, handles a changed rollout context, keeps client scope isolated, and avoids leaking one client’s history into another client’s support reply.","modality":"text","input_text":"Session 1:\nUse this under account_id: client_acme_001\n\nACME is a client using our AI support assistant. They prefer clear next steps and do not like repeated troubleshooting. Their team already tried password reset, clearing browser cache, and switching browsers. The issue is still happening only for users with SSO enabled.\n\nSession 2:\nUse this under account_id: client_acme_001\n\nACME came back today and said: \"Our users still cannot log in with SSO. What should we try next?\"\n\nDraft a support reply that respects what they already tried and moves to the next useful step.\n\nSession 3:\nUse this under account_id: client_acme_001\n\nUpdate the client memory: ACME is no longer using SSO for this rollout. They moved to email-password login for the first launch. Do not keep treating SSO as the active issue unless they mention it again.\n\nSession 4:\nUse this under account_id: client_acme_001\n\nACME says: \"Some users are still unable to log in during launch testing.\"\n\nDraft the next support reply.\n\nSession 5:\nUse this under account_id: client_beta_002\n\nBetaCorp is a new client. They say: \"Our users cannot log in for the first time.\"\n\nDraft the first support reply for BetaCorp.","input_artifact_refs":[],"stresses":["client history recall","avoid repeating troubleshooting","update handling","scope isolation between clients","support response continuity"],"verdict":"failed","score":null,"score_total":null,"note":"After a correction that ACME had moved from SSO to email-password login, the next reply still reused SSO/SAML/IdP troubleshooting, showing that one explicit update did not retire the stale context.","evidence_state":"verified","source":null,"artifacts":[{"url":"https://d3epheqghktydj.cloudfront.net/zep-zep-input2-acme-memory-update-acknowledg-3b9d5bcbd3a3.png","role":"output","alt":null},{"url":"https://d3epheqghktydj.cloudfront.net/zep-zep-input2-acme-update-handling-sso-cont-03a763c0c9d9.png","role":"output","alt":null}],"run_id":"6e31afbb-34d7-459a-b688-68ef76fc615a","study_title":"Memory for AI Agents","study_kind":"generation","research_task":"86ba16xrp","tested_at":null,"completeness":"input-and-output","input":{"state":"text","text":"Session 1:\nUse this under account_id: client_acme_001\n\nACME is a client using our AI support assistant. They prefer clear next steps and do not like repeated troubleshooting. Their team already tried password reset, clearing browser cache, and switching browsers. The issue is still happening only for users with SSO enabled.\n\nSession 2:\nUse this under account_id: client_acme_001\n\nACME came back today and said: \"Our users still cannot log in with SSO. What should we try next?\"\n\nDraft a support reply that respects what they already tried and moves to the next useful step.\n\nSession 3:\nUse this under account_id: client_acme_001\n\nUpdate the client memory: ACME is no longer using SSO for this rollout. They moved to email-password login for the first launch. Do not keep treating SSO as the active issue unless they mention it again.\n\nSession 4:\nUse this under account_id: client_acme_001\n\nACME says: \"Some users are still unable to log in during launch testing.\"\n\nDraft the next support reply.\n\nSession 5:\nUse this under account_id: client_beta_002\n\nBetaCorp is a new client. They say: \"Our users cannot log in for the first time.\"\n\nDraft the first support reply for BetaCorp.","files":[],"modality":"text","stresses":["client history recall","avoid repeating troubleshooting","update handling","scope isolation between clients","support response continuity"]},"tool_page_slug":"zep","tool_url":"https://aidemos.com/tools/zep","permalink":"https://aidemos.com/evidence/8a3bac73-a767-41c2-a295-f2f33f5aacf4","api_url":"https://ai.aidemos.com/v1/observations/8a3bac73-a767-41c2-a295-f2f33f5aacf4"},"peers":[{"id":"949a7908-a1c3-4494-ac53-a368498fed52","tool":"cognee","tool_name":"Cognee","verdict":"failed","score":null,"score_total":null,"note":"Accepts an explicit client-memory update that SSO is no longer the rollout path, but the following reply still resurfaces SSO-specific troubleshooting language, so the old context was not fully retired.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/memory-for-ai-agents-cognee-input2-session3-acme-memory-updat-2d684845392f.png","evidence_url":"https://aidemos.com/evidence/949a7908-a1c3-4494-ac53-a368498fed52"},{"id":"b328e35e-796b-46ed-8164-c24bf6307147","tool":"hindsight","tool_name":"Hindsight","verdict":"mixed","score":null,"score_total":null,"note":"When the later login-testing reply is generated, stale SSO context is still visible in retrieval, but it does not dominate the final answer and the newer rollout context stays primary.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/memory-for-ai-agents-hindsight-input2-acme-update-handled-wit-0acd0a998b24.png","evidence_url":"https://aidemos.com/evidence/b328e35e-796b-46ed-8164-c24bf6307147"},{"id":"133f3e43-ac89-437b-8b33-251e882a8ed0","tool":"mem0","tool_name":"Mem0","verdict":"mixed","score":null,"score_total":null,"note":"Accepts the ACME correction and stores the rollout change, but does not retire the older SSO memory strongly enough to stop later reuse.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/memory-for-ai-agents-mem0-input2-acme-update-memory-stored-393afdeb968e.png","evidence_url":"https://aidemos.com/evidence/133f3e43-ac89-437b-8b33-251e882a8ed0"},{"id":"296fccb1-080f-4f96-af1b-0af153818878","tool":"supermemory","tool_name":"Supermemory","verdict":"struggled","score":null,"score_total":null,"note":"After ACME's rollout context was updated away from SSO, the UI still showed a '0 memory used' tag while the side panel continued to surface the old SSO memory at 71% and then 79% relevance on later replies, so it is not possible to confirm from the UI that the update reliably superseded the stale context.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/memory-for-ai-agents-supermemory-input2-session3-acme-memory--fd8e39cbf155.png","evidence_url":"https://aidemos.com/evidence/296fccb1-080f-4f96-af1b-0af153818878"}],"other_criteria":[{"id":"badceaf9-c01a-4934-9174-99a6a5a50c7c","criterion":"memory-capture-quality","criterion_name":"Memory Capture Quality","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Captured reusable client-support context for ACME: clear-next-step preference, no repeated basic troubleshooting, and the fact that password reset, browser cache clearing, and browser switching had already been tried on an SSO-related login issue.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/badceaf9-c01a-4934-9174-99a6a5a50c7c"},{"id":"4845da75-9170-4894-9f2a-e69e56444b0d","criterion":"relevant-retrieval","criterion_name":"Relevant Retrieval","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"On the follow-up, it retrieved the right ACME history and skipped the three already-tried basics, moving straight to higher-value SSO/IdP troubleshooting.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/4845da75-9170-4894-9f2a-e69e56444b0d"},{"id":"93a526cd-3eea-4b8b-84d0-5e3221af8c8d","criterion":"scope-control","criterion_name":"Scope Control","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Kept client scope isolated: BetaCorp under a different account ID did not inherit ACME's troubleshooting history and received a first-touch support reply instead.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/93a526cd-3eea-4b8b-84d0-5e3221af8c8d"}],"appears_in":[{"page_type":"ranking","slug":"ai-agent-memory-tools","title":"Best AI Tools for Memory for AI Agents","url":"https://aidemos.com/best/ai-agent-memory-tools","binding":"run"}],"same_scenario":[{"id":"949a7908-a1c3-4494-ac53-a368498fed52","tool":"cognee","tool_name":"Cognee","verdict":"failed","score":null,"score_total":null,"note":"Accepts an explicit client-memory update that SSO is no longer the rollout path, but the following reply still resurfaces SSO-specific troubleshooting language, so the old context was not fully retired."},{"id":"b328e35e-796b-46ed-8164-c24bf6307147","tool":"hindsight","tool_name":"Hindsight","verdict":"mixed","score":null,"score_total":null,"note":"When the later login-testing reply is generated, stale SSO context is still visible in retrieval, but it does not dominate the final answer and the newer rollout context stays primary."},{"id":"133f3e43-ac89-437b-8b33-251e882a8ed0","tool":"mem0","tool_name":"Mem0","verdict":"mixed","score":null,"score_total":null,"note":"Accepts the ACME correction and stores the rollout change, but does not retire the older SSO memory strongly enough to stop later reuse."},{"id":"296fccb1-080f-4f96-af1b-0af153818878","tool":"supermemory","tool_name":"Supermemory","verdict":"struggled","score":null,"score_total":null,"note":"After ACME's rollout context was updated away from SSO, the UI still showed a '0 memory used' tag while the side panel continued to surface the old SSO memory at 71% and then 79% relevance on later replies, so it is not possible to confirm from the UI that the update reliably superseded the stale context."}]}