{"schemaVersion":1,"kind":"hakomiro-daily","note":"Public reviewed source only. A missing edition means no publication, not \"no change\".","latest":"2026-11-01","editions":[{"schemaVersion":1,"editionDate":"2026-11-01","kind":"catch_up","revision":1,"revisionLog":[{"revision":1,"at":"2026-11-01T18:56:16+09:00","summary":"We edited the pre-publication founding candidate. We checked the primary sources, comparison conditions and cost coverage of six items, and distinguished trial proposals from observed facts."}],"coverageNote":"This covers six primary sources published October 26 – November 1, 2026, read through to the body text. There are four business and two technical items (about 67:33), and the guide for the last seven days is roughly 7:3. Subjects are a UK local authority, company surveys in Spain and Mexico, a US company's worldwide office workers, and Japanese-language technical experiment articles. The location of the authors of the two technical articles is unconfirmed. The source languages checked were Japanese, English and Spanish; it is not a survey covering every region and industry in the world.","period":{"from":"2026-10-26","to":"2026-11-01"},"checkedThrough":"2026-11-01T18:43:05+09:00","finalCheckedAt":"2026-11-01T18:56:16+09:00","status":"changes_published","statusNote":"This is the catch-up edition for the founding issue. We read six primary sources published October 26 – November 1, 2026, and included the parts that bear on judgments at work. They are not events of November 1 itself.","checks":[{"target":"Body text of the UK government (MHCLG Digital) blog, 2026-10-30","state":"done","note":"On 2026-11-01 we read the full text at the official URL and checked the figures and limitations."},{"target":"Body text of the Cotec (Spain) report page and announcement, 2026-10-26","state":"done","note":"On 2026-11-01 we read both pages and checked the data period (full-year 2025 and Q1 2026) and the scope (companies with 10+ employees, eight kinds of AI)."},{"target":"Body text of the KPMG Mexico press release, 2026-10-28","state":"done","note":"On 2026-11-01 we read the text. It does not give the number of respondents in Mexico or the denominator for each question, and we have not checked the full report."},{"target":"Body text of the Estée Lauder announcement and the Microsoft article, 2026-10-30","state":"done","note":"On 2026-11-01 we read both and confirmed that they are the same announcement and that it has no outcome figures. The Microsoft page could be read on re-fetching."},{"target":"Body text of the Zenn article by tappers, 2026-10-31","state":"done","note":"On 2026-11-01 we read the text and the comparison table. It is the author's own experiment report, and independent reproduction is unconfirmed."},{"target":"Body text of the Zenn article by mochiai, 2026-10-31 (body updated 2026-11-01)","state":"done","note":"On 2026-11-01 we read the text. It is a verification in the author's own environment, and reproduction in other environments is unconfirmed."}],"backgroundNote":"As background, you can read reviews of 15 primary sources from August–October 2026 and a list of 26 materials. These are sources checked in the past, not today's developments.","items":[{"id":"streetlink-ai-prompts","topicId":"streetlink-alert-quality","relation":"new","previous":null,"area":"society","track":"business","title":"UK rough-sleeper reporting service StreetLink: operators report fewer \"person not found\" reports after AI guidance at input","changed":"The UK Ministry of Housing, Communities and Local Government (MHCLG) and the service provider Home Connections trialed AI input guidance in 10 local authorities for StreetLink, where the public reports rough sleepers in England and Wales. When a description of a location is vague, it prompts for more, such as landmarks and ways of access. According to the report, failed visits due to missing information went from 36% to 18%, the share of reports after which the person was found went from 16% to 23%, and descriptions of the location grew by 45% and of the person by 54%. About 89% of users said it \"helped them write in more detail\", and the report says a full rollout has been carried out.","whyItMatters":"This practical case suggests that if you change the design so that, at the point of input, AI asks follow-up questions about what is missing, instead of people fixing entries afterwards, wasted visits in the field may fall. It can be used to review situations where input quality causes rework downstream in your own inquiry, application or reporting intake. However, the figures are the operators' self-report and are not an effect that necessarily applies to your organization.","affected":"People in government or companies who run reception, counters, call centers or application forms, and the departments that respond on site to reports or applications.","action":"First count the cases where missing input at your intake causes rechecks or wasted visits, and their reasons. Try the idea of AI asking follow-ups in the input field first in a small scope, in a form that leaves judgment with people. Do not use this article's figures as expectations for your own organization.","limits":"This is the operators' self-report, and we have not confirmed third-party verification. The article does not give the comparison period, the denominators such as the number of reports, or whether there was a control group. We cannot say that the improvement in the \"found\" share is due to the AI guidance alone. The figures do not show the effect on protecting or helping rough sleepers. It is stated that the design leaves decisions to staff.","decisionChange":null,"importance":{"impact":2,"evidence":1,"novelty":2,"actionability":2,"reason":"Impact: suggestive for designing public intake. Evidence: low, because it is a self-report with unknown denominators and controls. Novelty: an operational report of AI guidance at input. Actionability: can start with measuring missing input at your intake."},"sources":[{"url":"https://mhclgdigital.blog.gov.uk/2026/10/30/helping-more-people-off-the-streets-how-ai-is-improving-streetlink/","publisher":"MHCLG Digital (UK government)","title":"Helping more people off the streets: how AI is improving StreetLink","claimBasis":"operator_report","publishedAt":"2026-10-30","eventAt":null,"researchedAt":null,"checkedAt":"2026-11-01"}],"backgroundObservationIds":[],"correction":null,"provenance":{"publisherRegion":"UK (government and contractor)","subjectRegion":"10 local authorities in England and Wales","language":"English","readScope":"Read the full English original blog text (no translation used)","japanConfirmed":"For Japanese readers, only an outline of the idea (asking follow-ups about missing information at input) could be confirmed.","japanUnconfirmed":"The article does not state the name, cost, Japanese-language support or personal-data handling conditions of the AI service used, so these are unconfirmed."},"result":{"status":"reported","value":"Failed visits due to missing information 36%→18%; share of reports after which the person was found 16%→23%","unit":"Percentage (%)","period":"No comparison period given (trial in 10 local authorities)","basis":"provider_claim","unknownReason":null},"cost":{"status":"unknown","value":null,"unit":null,"period":null,"basis":null,"unknownReason":"The primary source gives no introduction, operating or checking costs, so the amount is unknown. It cannot be read as free or zero.","covers":{"setup":"unconfirmed","reviewCorrection":"unconfirmed","operations":"unconfirmed","dataPrep":"unconfirmed"}},"experiment":{"label":"editorial_proposal","goal":"Before using AI, count the rework that missing input at intake creates downstream","prerequisites":["Staff who can read intake records","Intake records of the last one to two months"],"steps":["Count the cases that became rework, split into \"missing input\" and \"other\"","Write out the top three reasons for missing input","For those reasons, draft on paper one follow-up prompt to add to the input field (do not introduce AI)"],"successCriteria":["The numbers show that missing input accounts for a large share of all rework","The draft follow-up prompts pass checking by staff in the field"],"stopCriteria":["The reasons cannot be classified from the records","If missing input is only a part of the rework, do not proceed to AI guidance and investigate other causes"]},"lifecycle":{"stage":"adoption","stageBasis":"The primary source says a full rollout was carried out after the trial in 10 local authorities.","expected":"Reduce failed visits with guidance at input","observed":"Failed visits from 36% to 18% (operator's report)","unknownReason":null,"nextQuestion":"Whether the same level continues after the full rollout, and whether anyone other than the operators has verified it."},"engineering":{"details":"This is input guidance that asks follow-up questions about landmarks and ways of access when a description of a location is vague. The primary source does not state the AI service or model used, or how personal information is handled.","handoff":{"sourceUrl":"https://mhclgdigital.blog.gov.uk/2026/10/30/helping-more-people-off-the-streets-how-ai-is-improving-streetlink/","objective":"Organize the requirements for a mechanism that returns additional questions when input is insufficient","inputs":["List of intake form fields","Past examples of missing input (excluding personal information)"],"expectedOutput":"Drafts of follow-up prompts for each kind of gap, and the conditions under which judgment stays with people","constraints":["Staff judgment stays in place","First check where personal information is sent and the storage conditions","The service used cannot be known from the primary source"],"verification":["Compare the completeness of input with and without follow-ups","Spot-check for errors in content that the follow-ups led people to enter"]}}},{"id":"cotec-spain-firm-ai-use","topicId":"spain-firm-ai-adoption","relation":"new","previous":null,"area":"work","track":"business","title":"Spanish companies' AI use: 33.6% of companies with 10+ employees in 2025, with a large gap by size (Cotec report)","changed":"Cotec, the Spanish innovation foundation, published a report on October 26, 2026. It analyzed public statistics (INE) for full-year 2025 and Q1 2026: the share of companies with 10+ employees using AI rose from 21.1% in 2024 to 33.6% in 2025 (+12.5 points). In 2025 it was 74.4% for large companies and 21.4% for micro companies, a gap of 53.0 points. Spanish companies using AI are estimated at about 726,000, and micro companies make up 92.6% of the users. The biggest barrier cited by non-users is a lack of in-house knowledge, named by about 80%.","whyItMatters":"The story that \"more companies are using AI\", regardless of your size, looks very different by size. Looking at the gap between large and micro companies and the reasons given by non-users gives a way to check, starting from \"people and knowledge\", why your own adoption is lagging. However, these are Spanish statistics and not figures that apply directly to Japanese companies.","affected":"Owners of small and medium-sized companies, and AI adoption leads at companies with trading partners of different sizes.","action":"Check why your company is \"not using\" it by starting not with cost or technology but with \"do we have people and knowledge in-house who can make the judgment\". For comparison, use only figures for your own size, and do not make the overall average a target.","limits":"These figures are companies' answers to a statistical survey and do not measure AI's outcomes or costs. AI counts companies using any of eight kinds of technology, so it is not a figure for generative AI alone. Regional and industry analysis is limited to companies with 10+ employees. We have not checked how well this applies to Japanese companies.","decisionChange":null,"importance":{"impact":2,"evidence":2,"novelty":2,"actionability":2,"reason":"Impact: shows adoption gaps by size and barriers. Evidence: a report analyzing public statistics, but it does not measure outcomes. Novelty: the latest analysis of full-year 2025. Actionability: can be used to check your own barriers."},"sources":[{"url":"https://cotec.es/informes/uso-de-la-ia-en-las-empresas/","publisher":"Cotec (Spain)","title":"Uso de la IA en las empresas","claimBasis":"survey_report","publishedAt":"2026-10-26","eventAt":null,"researchedAt":null,"checkedAt":"2026-11-01"},{"url":"https://cotec.es/noticias-cpt/publicamos-el-informe-uso-de-la-ia-en-las-empresas/","publisher":"Cotec (Spain)","title":"Publicamos el informe «Uso de la IA en las empresas»","claimBasis":"survey_report","publishedAt":"2026-10-26","eventAt":null,"researchedAt":null,"checkedAt":"2026-11-01"}],"backgroundObservationIds":[],"correction":null,"provenance":{"publisherRegion":"Spain (innovation foundation Cotec)","subjectRegion":"Spanish companies","language":"Spanish","readScope":"Read the announcement page and report page text (original read, no machine translation used)","japanConfirmed":"For Japanese readers, only an outline of the tendency that adoption differs by size could be confirmed.","japanUnconfirmed":"Comparable figures for Japanese companies, differences from Japan in how the survey population is defined, and the full tables of the report are unconfirmed."},"result":{"status":"reported","value":"AI use by companies with 10+ employees 21.1%→33.6% (+12.5 points). In 2025: large companies 74.4%, micro companies 21.4%","unit":"Percentage (%) and percentage points","period":"2024 and 2025 (analysis includes Q1 2026 data)","basis":"survey_response","unknownReason":null},"cost":{"status":"unknown","value":null,"unit":null,"period":null,"basis":null,"unknownReason":"The announcement and published text we checked this time do not give actual amounts such as introduction or operating costs. The cost items in the questionnaire and full report are unconfirmed.","covers":{"setup":"unconfirmed","reviewCorrection":"unconfirmed","operations":"unconfirmed","dataPrep":"unconfirmed"}},"experiment":{"label":"editorial_proposal","goal":"Check whether the reason your company is not using AI lies in in-house knowledge or judgment","prerequisites":["Head of the responsible department","Three candidate AI uses you would like to try at work"],"steps":["For each candidate, write out \"who decides and who checks\"","Mark the candidates for which there is no one who can decide","Make the marked candidates the target of ways to build knowledge (training, outside consultation)"],"successCriteria":["A decider and a checker are set for each candidate","The candidates for which lack of knowledge is the reason can be identified"],"stopCriteria":["Stop considering adoption for candidates where no decider can be placed","Do not move on to cost or contract discussions until this check is finished"]},"lifecycle":{"stage":"unknown","stageBasis":"These are aggregate statistics and do not show the stage of any individual effort.","expected":null,"observed":"Use among companies with 10+ employees went from 21.1% to 33.6% (companies' answers)","unknownReason":"These are overall statistics, not a specific initiative, and no expected level is stated.","nextQuestion":"Whether use is established at smaller companies, and what happened as a result of continued use."},"engineering":{"details":"Using survey data from the public statistics INE, companies using any of eight kinds of AI technology are counted as users. Regional and industry analysis covers only companies with 10+ employees.","handoff":{"sourceUrl":"https://cotec.es/informes/uso-de-la-ia-en-las-empresas/","objective":"Choose the statistical category matching your size and organize it so it can be compared","inputs":["The report's tables by size","Your company's employee size"],"expectedOutput":"Usage rate for your own size category and a note on definitions","constraints":["The definition of AI technology is broad","It is not a figure for generative AI alone","The definition may differ from Japanese statistics"],"verification":["Check that the figures you cite match the report text","State the definition and the scope of companies together"]}}},{"id":"kpmg-mexico-ai-value-evidence","topicId":"kpmg-ai-pulse-mexico","relation":"new","previous":null,"area":"work","track":"business","title":"KPMG survey: 90% of large Mexican companies say AI delivers value, but only 14% have a mechanism to compare it with investment","changed":"In October 2026, KPMG Mexico announced the Q3 2026 results of the \"Global AI Pulse\", a survey of more than 2,100 executives in 20 countries (conducted July–August 2026, covering companies with annual revenue above US$50 million). In Mexico, 37% of companies (34% globally) had deployed AI agents on a large scale. 90% (89% globally) said they were getting measurable value from AI, but only 14% (12% globally) have a consistent mechanism to compare value with investment. In Mexico, 41% plan to invest up to US$499 million over the next 12 months.","whyItMatters":"There is a large gap between the self-assessment that \"AI is creating value\" and the share that has a mechanism to compare that value with the amount invested. When reporting AI outcomes in your own company, it gives a way to check whether outcome figures and costs are set side by side on the same basis. However, these are self-reports by respondents at large companies and do not measure actual outcomes.","affected":"People who report the effect of AI investment to executives, and staff in corporate planning and finance at large companies.","action":"Check whether the outcome reports for your AI initiatives list costs (introduction, checking and fixing, operation, data preparation) on the same basis. For initiatives where only outcome figures come first, set out the costs side by side before evaluating.","limits":"This is a survey based on respondents' self-reports, and neither value nor investment amounts were measured by a third party. The investment amounts are plans, not actual spending. The press release does not give the number of respondents in Mexico or the denominators for each question. It covers companies with annual revenue above US$50 million and does not apply to small businesses. We have not checked Japanese companies.","decisionChange":null,"importance":{"impact":2,"evidence":1,"novelty":2,"actionability":2,"reason":"Impact: shows weak evaluation of AI investment. Evidence: low, because it is only a press release and the Mexican denominator is unknown. Novelty: a new survey for Q3 2026. Actionability: can be used to check your own outcome reports."},"sources":[{"url":"https://kpmg.com/mx/es/sala-de-prensa/comunicados-de-prensa/2026/10/cp-tres-de-cada-cuatro-organizaciones-en-mexico-buscan-tener-un-mayor-control-sobre-la-inteligencia-artificial.html","publisher":"KPMG Mexico","title":"Tres de cada cuatro organizaciones en México buscan tener un mayor control sobre la inteligencia artificial","claimBasis":"survey_report","publishedAt":"2026-10-28","eventAt":null,"researchedAt":null,"checkedAt":"2026-11-01"}],"backgroundObservationIds":[],"correction":null,"provenance":{"publisherRegion":"Mexico (KPMG Mexico)","subjectRegion":"Large companies in Mexico and 20 countries worldwide","language":"Spanish","readScope":"Read the Spanish press release text (the full survey report is unconfirmed)","japanConfirmed":"For Japanese readers, only an outline of the tendency that there is a gap between self-assessed outcomes and mechanisms to compare with investment could be confirmed.","japanUnconfirmed":"Figures for Japanese companies, the number of respondents in Mexico and the denominators for each question, and the full report are unconfirmed."},"result":{"status":"reported","value":"Mexico: deployed AI agents on a large scale 37% (global 34%); getting measurable value 90%; have a mechanism to compare value with investment 14%","unit":"Percentage (%)","period":"Survey of July–August 2026","basis":"survey_response","unknownReason":null},"cost":{"status":"unknown","value":null,"unit":null,"period":null,"basis":null,"unknownReason":"The announcement text we checked this time has no actual cost or total cost figures. The cost items in the questionnaire and full report are unconfirmed. Planned investment over the next 12 months is not treated as actual cost.","covers":{"setup":"unconfirmed","reviewCorrection":"unconfirmed","operations":"unconfirmed","dataPrep":"unconfirmed"}},"experiment":{"label":"editorial_proposal","goal":"Check whether, for one AI initiative of your own, outcomes and costs can be set side by side on the same basis","prerequisites":["One initiative that is reporting outcomes","The person in charge of that initiative and someone in finance"],"steps":["Write down the source and period of the outcome figures","Write the costs of introduction, checking and fixing, operation and data preparation item by item, as far as known","Write \"unknown\" for items you do not know"],"successCriteria":["Outcomes and costs line up over the same period and unit","Unknown items are made explicit"],"stopCriteria":["If half or more of the cost items remain unknown, do not expand on the basis of outcome figures alone"]},"lifecycle":{"stage":"unknown","stageBasis":"The survey aggregates answers from large companies and does not show the stage of any specific initiative.","expected":"Investment plans for the next 12 months (41% of companies have plans of up to US$499 million)","observed":"14% have a consistent mechanism to compare value with investment","unknownReason":"These are statistics for the survey as a whole, and the stage of each initiative is not given.","nextQuestion":"Were the planned investments carried out, and were their outcomes evaluated against the investment?"},"engineering":{"details":"The survey covers more than 2,100 executives in 20 countries, and the Mexican portion is only the figures in the press release.","handoff":{"sourceUrl":"https://kpmg.com/mx/es/sala-de-prensa/comunicados-de-prensa/2026/10/cp-tres-de-cada-cuatro-organizaciones-en-mexico-buscan-tener-un-mayor-control-sobre-la-inteligencia-artificial.html","objective":"Build an evaluation table that sets outcomes and investment on the same basis","inputs":["Outcome indicators and period","Amount for each cost item"],"expectedOutput":"A table setting outcomes and costs side by side over the same period and unit","constraints":["The Mexican denominator is unknown","Answers are self-reports, not third-party measurements"],"verification":["Check that the cited shares match the press release","Check that global values and Mexican values are not mixed up"]}}},{"id":"estee-lauder-copilot-expansion","topicId":"estee-lauder-microsoft-ai","relation":"new","previous":null,"area":"work","track":"business","title":"Estée Lauder partners with Microsoft and expands Copilot to more than 14,000 office employees worldwide (no outcome figures)","changed":"On October 30, 2026, The Estée Lauder Companies announced a strategic partnership with Microsoft. It is investing in an integrated consumer data foundation and extending Copilot to its worldwide office employees (more than 14,000). Employees are described as being at the stage of trying productivity agents, and improved productivity, expanded margins and growth are given as future goals. Microsoft's article reports the same announcement.","whyItMatters":"Announcements of AI adoption at large companies tend to mix \"expanded use\" with \"produced results\". This announcement covers only the former and shows no usage, productivity or costs. It is an example of separating the number given access from the results of actual use when you read AI adoption reports in your own organization.","affected":"AI adoption leads at large companies, and executives and procurement staff who read adoption reports to make decisions.","action":"When reading adoption reports, check \"the number given access\" separately from \"the amount actually used and the results\". Read an announcement without outcome figures as a statement of goals, and do not use it as evidence of cost-effectiveness.","limits":"In the company's and Microsoft's announcements, there are no figures on usage, productivity, cost-effectiveness or contract terms. The number who can use Copilot and the number who actually use it are different. Goals are future hopes, not achievements. We have not checked rollout in Japan.","decisionChange":null,"importance":{"impact":1,"evidence":1,"novelty":2,"actionability":2,"reason":"Impact: shows the scale of a large company's adoption. Evidence: low, because there are no outcome figures. Novelty: an announcement of a new partnership. Actionability: can be used to check how you read adoption reports."},"sources":[{"url":"https://www.elcompanies.com/en/news-and-media/newsroom/press-releases/2026/10-30-2026-132320540","publisher":"The Estée Lauder Companies","title":"Estée Lauder Companies press release (2026-10-30)","claimBasis":"operator_report","publishedAt":"2026-10-30","eventAt":null,"researchedAt":null,"checkedAt":"2026-11-01"},{"url":"https://news.microsoft.com/source/features/digital-transformation/estee-lauder-expands-ai-across-beauty-business/","publisher":"Microsoft","title":"Estée Lauder expands AI across its beauty business","claimBasis":"operator_report","publishedAt":"2026-10-30","eventAt":null,"researchedAt":null,"checkedAt":"2026-11-01"}],"backgroundObservationIds":[],"correction":null,"provenance":{"publisherRegion":"United States (The Estée Lauder Companies, Microsoft)","subjectRegion":"Office employees worldwide","language":"English","readScope":"Read the text of the English corporate announcement and the Microsoft article (no translation used)","japanConfirmed":"For Japanese readers, only an outline of what the adoption announcement says could be confirmed.","japanUnconfirmed":"Rollout in Japan, costs, contract terms and usage are unconfirmed."},"result":{"status":"unknown","value":null,"unit":null,"period":null,"basis":null,"unknownReason":"The announcement gives only the number who can use Copilot (more than 14,000), and no figures on usage volume, productivity or cost-effectiveness. Granting access cannot be read as a result."},"cost":{"status":"unknown","value":null,"unit":null,"period":null,"basis":null,"unknownReason":"Costs, contract terms and the work required for adoption are not stated.","covers":{"setup":"unconfirmed","reviewCorrection":"unconfirmed","operations":"unconfirmed","dataPrep":"unconfirmed"}},"experiment":{"label":"editorial_proposal","goal":"Check whether, in your own AI adoption reports, you can read \"number who can use it\" separately from \"results of use\"","prerequisites":["One adoption report or adoption plan document"],"steps":["Classify the figures in the document as \"number who can use\", \"actual use\", \"results\" and \"cost\"","Write out the categories that are left blank","Ask the person in charge what records are needed to fill the blanks"],"successCriteria":["A list shows where information exists in the four categories"],"stopCriteria":["If both the results and cost categories stay blank, do not use that document as grounds for expansion"]},"lifecycle":{"stage":"adoption","stageBasis":"It says Copilot access was extended to office employees worldwide.","expected":"Improved productivity, expanded margins and growth (the company's goals)","observed":null,"unknownReason":"The announcement has no figures on usage volume or results, so no observed results can be confirmed.","nextQuestion":"Will usage and results be published a year later? How do they compare with the goals?"},"engineering":{"details":"Investment in an integrated consumer data foundation and the expansion of Copilot are included in the same announcement. The technical configuration, permission design and data handling are not stated.","handoff":{"sourceUrl":"https://www.elcompanies.com/en/news-and-media/newsroom/press-releases/2026/10-30-2026-132320540","objective":"Organize the facts that can be confirmed from the adoption announcement, and the unknowns","inputs":["Company announcement","Microsoft article"],"expectedOutput":"Table of confirmed and unknown categories","constraints":["Granting access is separate from actual usage","The technical configuration cannot be known from the primary source"],"verification":["Confirm that the two primary sources are the same announcement","Record as facts only the items that have figures"]}}},{"id":"agent-test-output-filter","topicId":"agent-tool-output-filtering","relation":"new","previous":null,"area":"work","track":"engineer","title":"AI coding input tokens fall from 92,385 to 5,445 with structured test output (experiment in the author's isolated environment)","changed":"On an isolated virtual machine, using the same model and the same task of fixing a payment-processing bug, the author compared passing the raw test output as-is with passing structured JSON containing only the names, lines and diffs of failing tests. Cumulative input to completion (model calls: three for raw output, two for structured) went from 92,385 to 5,445 tokens, estimated cost from about $0.077 to about $0.010, and time from about 25.9 to about 16.9 seconds; the independent tests reportedly passed 20 of 20 under both methods.","whyItMatters":"This is one experiment report suggesting that, when you hand development work to AI, cost and time may depend not only on the AI's intelligence but on the volume of logs you have it read. It is one reason to include formatting of tool output among the items when estimating a development team's running costs.","affected":"Engineers who use AI coding agents in development, and development leads who decide their running costs and how to proceed.","action":"In your own team's agent operation, measure how much test and build output accumulates in the conversation. If you try a mechanism to format the output, check on your own team's tasks that the correct-answer rate does not fall.","limits":"This is an experiment by the author on one task and one model (gemini-3.8-flash in the article). We have not confirmed independent reproduction. It uses an artificially built payment task, so the effect on real business code is unknown. Tokens and costs are estimates in the article.","decisionChange":null,"importance":{"impact":2,"evidence":1,"novelty":2,"actionability":2,"reason":"Impact: bears on development running costs. Evidence: low, a single experiment by the author. Novelty: a quantitative comparison report. Actionability: you can measure output volume in your own environment."},"sources":[{"url":"https://zenn.dev/tappers/articles/ai-labo-e16-cli-token-killer","publisher":"Zenn (tappers)","title":"テスト出力の垂れ流しでコンテキストが汚染される！「生ターミナル出力」vs「構造化JSON差分フィルタ」で入力94.1%削減","claimBasis":"user_report","publishedAt":"2026-10-31","eventAt":null,"researchedAt":null,"checkedAt":"2026-11-01"}],"backgroundObservationIds":[],"correction":null,"provenance":{"publisherRegion":"The author's location is unconfirmed from the primary source (an individual's technical article in Japanese)","subjectRegion":"The author's isolated virtual machine (no regional limit)","language":"Japanese","readScope":"Read the Japanese original article text and comparison table","japanConfirmed":"We checked the steps and figures written in Japanese.","japanUnconfirmed":"We have not checked the availability or cost in Japan of the compression tools or models the article tried."},"result":{"status":"reported","value":"Cumulative input to completion 92,385→5,445 tokens (model calls 3→2), time about 25.9→about 16.9 seconds, tests 20/20 under both methods","unit":"Tokens, seconds","period":"The author's single experiment (no period stated)","basis":"measured","unknownReason":null},"cost":{"status":"reported","value":"Estimated cost about $0.077→about $0.010","unit":"US dollars (estimated)","period":"One run of the same experiment","basis":"estimated","unknownReason":null,"covers":{"setup":"unconfirmed","reviewCorrection":"unconfirmed","operations":"included","dataPrep":"unconfirmed"}},"experiment":{"label":"editorial_proposal","goal":"In your own environment, measure how much the amount passed to AI falls when test output is trimmed","prerequisites":["A development environment where tests can run","Records that show the input volume passed to AI"],"steps":["Measure the output volume once without trimming","Set it up to pass only a summary of failures and run the same work","Compare input volume, time and test results"],"successCriteria":["Input volume falls and test results do not change","The cause of failures can be read from the trimmed output"],"stopCriteria":["Test results change, or the cause of failures cannot be read","The effort of building the trimming exceeds the savings"]},"lifecycle":{"stage":"poc","stageBasis":"This is a report of the author trying an artificial payment task once on an isolated VM.","expected":"Trimming the output reduces input volume and time","observed":"Input volume down about 94%, tests the same at 20/20 (the author's single measurement)","unknownReason":null,"nextQuestion":"Does it fall by the same amount in real maintenance work and with other models? Does trimmed output cause things to be missed?"},"engineering":{"details":"The author ran an artificial payment task on an isolated VM and compared each method until completion with the same model, gemini-3.8-flash. Raw output took three model calls and structured output two, so it is not a comparison fixed at the same three turns.","handoff":{"sourceUrl":"https://zenn.dev/tappers/articles/ai-labo-e16-cli-token-killer","objective":"Measure in your own environment the effect of preprocessing that summarizes test output before passing it","inputs":["Test execution command","Output before it is passed to AI","Record of input tokens"],"expectedOutput":"Comparison table of input volume, time and test results before and after trimming","constraints":["AI does not misjudge the cause because of missing output","The author's result is from a single experiment"],"verification":["Run the same task several times and look at the variation","Check that the cause of failure remains in the trimmed output"]}}},{"id":"xcode-mcp-tool-scoping","topicId":"xcode-mcp-tool-scoping","relation":"new","previous":null,"area":"work","track":"engineer","title":"When passing Xcode operations to AI, the subagent tools setting could not narrow the tools, and they had to be removed with disallowedTools (author's environment)","changed":"In the author's environment (Xcode 27.2, Claude Code 2.1.316), of the 54 tools exposed by Xcode's MCP, writing only 4 in a subagent's tools setting still showed all 54, and XcodeWrite, which was not listed, also went through and created a file. Removing the 50 other than the 4 to be used with disallowedTools left only 4 visible, and preview capture also went through, the author reports. The author runs regular builds and tests with xcodebuild and limits MCP to uses such as preview capture.","whyItMatters":"This is one measured report that when you hand development tool operations to AI, assuming that \"I listed the tools to use, so it can't use the others\" may let unintended writes through. It is grounds for a lead introducing AI development tools to check the tools that can actually be used, rather than relying on configuration alone to narrow permissions.","affected":"Engineers who have AI agents operate a Mac app development environment, and leads who decide its permission design.","action":"If you have AI operate tools in your own organization, do not trust settings you \"meant to allow\"; actually output the list of tools visible to the agent and check it. When a tool update adds tools, take the list again.","limits":"This was checked in the author's own environment with one combination of versions. The article itself says the tool configuration changes with the Xcode version. We have not confirmed reproduction in other environments or future versions, nor any universal guarantee. The article was published 2026-10-31, and the body was updated on 2026-11-01.","decisionChange":null,"importance":{"impact":2,"evidence":2,"novelty":2,"actionability":3,"reason":"Impact: a pitfall in AI permission design. Evidence: the author shows steps and measurements, but in a single environment. Novelty: a concrete example where narrowing does not work. Actionability: checking the list can be done right now."},"sources":[{"url":"https://zenn.dev/mochiai/articles/43f5d1900ec604","publisher":"Zenn (mochiai)","title":"Xcode MCPを外部エージェントから使う：設定3ステップとxcodebuildとの使い分け","claimBasis":"user_report","publishedAt":"2026-10-31","eventAt":null,"researchedAt":null,"checkedAt":"2026-11-01"}],"backgroundObservationIds":[],"correction":null,"provenance":{"publisherRegion":"The author's location is unconfirmed from the primary source (an individual's technical article in Japanese)","subjectRegion":"The author's development environment on macOS (no regional limit)","language":"Japanese","readScope":"Read the Japanese original article text","japanConfirmed":"We checked the steps written in Japanese and the results on the version as of 2026-10-31.","japanUnconfirmed":"We have not checked behavior on other versions or consistency with official Apple or Anthropic documentation."},"result":{"status":"reported","value":"Specifying 4 of 54 tools still showed 54 (XcodeWrite worked). Prohibiting the other 50 left 4","unit":"Number of tools","period":"Verification in the author's environment (no period stated)","basis":"measured","unknownReason":null},"cost":{"status":"unknown","value":null,"unit":null,"period":null,"basis":null,"unknownReason":"The primary source gives times of 86 seconds for capture and 32 and 31 seconds for other checks. Total effort and total cost including introduction, setup, checking and fixing, and operation are unconfirmed.","covers":{"setup":"unconfirmed","reviewCorrection":"unconfirmed","operations":"unconfirmed","dataPrep":"unconfirmed"}},"experiment":{"label":"editorial_proposal","goal":"In your own environment, check that the tools shown to AI are narrowed as intended","prerequisites":["An environment that uses the tool integration in question","A way to see the list of available tools"],"steps":["Specify the allowed tools and check the list of tools actually visible","Check that the number of visible tools matches your intent","If not, narrow again with a prohibition setting and recheck"],"successCriteria":["The list of visible tools matches the intended scope"],"stopCriteria":["If the list differs from the intent and a prohibition setting cannot narrow it, do not widen the scope in which that integration is used"]},"lifecycle":{"stage":"unknown","stageBasis":"This is a verification report in the author's personal environment and does not describe the stage of organizational adoption or operation.","expected":null,"observed":"An allow setting did not narrow it, and a prohibition setting did (author's environment)","unknownReason":"There is no statement of the adoption stage, and no expected effect is stated.","nextQuestion":"Is the result the same on other versions and environments? Did the provider confirm or fix the behavior?"},"engineering":{"details":"The author verified this on Xcode 27.2 and Claude Code 2.1.316. Specifying 4 in a subagent's tools still showed 54, and specifying the other 50 with disallowedTools left 4.","handoff":{"sourceUrl":"https://zenn.dev/mochiai/articles/43f5d1900ec604","objective":"Check the setting that narrows permissions with a prohibition list when an allow list does not work","inputs":["The version in use","Output of the tool list"],"expectedOutput":"A setting where only the intended scope is visible, and a record of the check","constraints":["Behavior may change when the version changes","A report from the author's single environment"],"verification":["Record the version and recheck the list","After setting the prohibition, confirm that unneeded tools cannot be called"]}}}]}]}