{"id":"https://openalex.org/W4409361381","doi":"https://doi.org/10.1609/aaai.v39i28.35161","title":"Evaluation and Incident Prevention in an Enterprise AI Assistant","display_name":"Evaluation and Incident Prevention in an Enterprise AI Assistant","publication_year":2025,"publication_date":"2025-04-11","ids":{"openalex":"https://openalex.org/W4409361381","doi":"https://doi.org/10.1609/aaai.v39i28.35161"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v39i28.35161","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i28.35161","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/35161/37316","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/35161/37316","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091474850","display_name":"Akash V. Maharaj","orcid":"https://orcid.org/0000-0001-8625-1844"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Akash V. Maharaj","raw_affiliation_strings":["Adobe Inc"],"affiliations":[{"raw_affiliation_string":"Adobe Inc","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063845534","display_name":"David Arbour","orcid":"https://orcid.org/0000-0002-9932-7657"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Arbour","raw_affiliation_strings":["Adobe Research"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392994","display_name":"Daniel C. Lee","orcid":"https://orcid.org/0000-0002-9718-5579"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Lee","raw_affiliation_strings":["Adobe Inc"],"affiliations":[{"raw_affiliation_string":"Adobe Inc","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042584669","display_name":"Uttaran Bhattacharya","orcid":"https://orcid.org/0000-0003-2141-9276"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Uttaran Bhattacharya","raw_affiliation_strings":["Adobe Research"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034026499","display_name":"Anup Rao","orcid":"https://orcid.org/0009-0004-7226-7860"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anup Rao","raw_affiliation_strings":["Adobe Research"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117110916","display_name":"Austin Zane","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Austin Zane","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017768355","display_name":"Avi Feller","orcid":"https://orcid.org/0000-0001-7319-5468"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Avi Feller","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061223996","display_name":"Kun Qian","orcid":"https://orcid.org/0000-0002-8719-1537"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kun Qian","raw_affiliation_strings":["Adobe Inc"],"affiliations":[{"raw_affiliation_string":"Adobe Inc","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037837260","display_name":"Yunyao Li","orcid":"https://orcid.org/0000-0002-3073-3227"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunyao Li","raw_affiliation_strings":["Adobe Inc"],"affiliations":[{"raw_affiliation_string":"Adobe Inc","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5091474850"],"corresponding_institution_ids":["https://openalex.org/I1306409833"],"apc_list":null,"apc_paid":null,"fwci":5.75,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91111111,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"39","issue":"28","first_page":"28931","last_page":"28937"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10809","display_name":"Occupational Health and Safety Research","score":0.8862000107765198,"subfield":{"id":"https://openalex.org/subfields/3614","display_name":"Radiological and Ultrasound Technology"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10809","display_name":"Occupational Health and Safety Research","score":0.8862000107765198,"subfield":{"id":"https://openalex.org/subfields/3614","display_name":"Radiological and Ultrasound Technology"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11357","display_name":"Risk and Safety Analysis","score":0.8751000165939331,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10763","display_name":"Digital Transformation in Industry","score":0.832099974155426,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.3726915717124939},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3610377907752991}],"concepts":[{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.3726915717124939},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3610377907752991}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v39i28.35161","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i28.35161","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/35161/37316","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2504.13924","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.13924","pdf_url":"https://arxiv.org/pdf/2504.13924","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1609/aaai.v39i28.35161","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i28.35161","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/35161/37316","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409361381.pdf","grobid_xml":"https://content.openalex.org/works/W4409361381.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Enterprise":[0],"AI":[1,131,164],"Assistants":[2],"are":[3],"increasingly":[4],"deployed":[5],"in":[6,136],"domains":[7],"where":[8],"accuracy":[9],"is":[10],"paramount,":[11],"making":[12],"each":[13],"erroneous":[14],"output":[15],"a":[16,23,49,70,100],"potentially":[17],"significant":[18],"incident.":[19],"This":[20],"paper":[21],"presents":[22],"comprehensive":[24],"framework":[25,52],"for":[26,53,75,151,159],"monitoring,":[27],"benchmarking,":[28],"and":[29,58,72,79,90,98,110,127,162],"continuously":[30],"improving":[31],"such":[32],"complex,":[33],"multi-component":[34],"systems":[35],"under":[36],"active":[37],"development":[38,85],"by":[39,142],"multiple":[40,84],"teams.":[41],"Our":[42],"approach":[43,148],"encompasses":[44],"three":[45],"key":[46],"elements:":[47],"(1)":[48],"hierarchical":[50],"``severity''":[51],"incident":[54],"detection":[55],"that":[56],"identifies":[57],"categorizes":[59],"errors":[60],"while":[61],"attributing":[62],"component-specific":[63],"error":[64],"rates,":[65],"facilitating":[66],"targeted":[67],"improvements;":[68],"(2)":[69],"scalable":[71],"principled":[73],"methodology":[74],"benchmark":[76],"construction,":[77],"evaluation,":[78,106],"deployment,":[80],"designed":[81],"to":[82],"accommodate":[83],"teams,":[86],"mitigate":[87],"overfitting":[88],"risks,":[89],"assess":[91],"the":[92,108,125,157],"downstream":[93],"impact":[94],"of":[95,112,129,154],"system":[96],"modifications;":[97],"(3)":[99],"continual":[101],"improvement":[102],"strategy":[103],"leveraging":[104],"multidimensional":[105],"enabling":[107],"identification":[109],"implementation":[111],"diverse":[113],"enhancement":[114],"opportunities.":[115],"By":[116],"adopting":[117],"this":[118,145],"holistic":[119],"framework,":[120],"organizations":[121],"can":[122],"systematically":[123],"enhance":[124],"reliability":[126],"performance":[128],"their":[130,134],"Assistants,":[132],"ensuring":[133],"efficacy":[135],"critical":[137],"enterprise":[138],"environments.":[139],"We":[140],"conclude":[141],"discussing":[143],"how":[144],"multifaceted":[146],"evaluation":[147],"opens":[149],"avenues":[150],"various":[152],"classes":[153],"enhancements,":[155],"paving":[156],"way":[158],"more":[160],"robust":[161],"trustworthy":[163],"systems.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}
