{ "notes": "EPISODE 1 (2026-11-03). Fresh goal: 1000 items, 100 workers, 15 episodes, nothing run yet. Plan in four phases: (1) DISCOVER the universe of humanoid-robot companies, (2) PROFILE each company into one table row (the goal's table), (3) VERIFY the figures the ranking stands on, (4) FINISH and write the table plus ranking.\n\nDEFINITION used in every brief (keep it stable): a company counts when it designs and builds its own general-purpose humanoid robot (torso, two arms, head, on legs or a wheeled base) meant for sale, deployment or research use, as a product or a publicly shown prototype; automaker/big-tech divisions, listed companies and startups all count. Excluded: component makers (actuators, hands, sensors), software-only/foundation-model firms with no robot of their own, universities/institutes, hobby projects, single arms, exoskeletons, small toy/education humanoids under 60 cm. Doubtful cases are listed with include=borderline and a reason, so the orchestrator decides, not the worker. Canonical name = official English name without legal suffix; Chinese companies by the English name they use themselves.\n\nSPAWNED THIS EPISODE (19 items): batch `discover`, 14 research items, json output, merge groupSize 7 (so merges merge-01 and merge-02). One item per region or source type: usa, canada-latam, china-startups, china-corporates, japan, korea, europe-west, europe-other, india-mideast-africa, asia-other-oceania, trackers-lists, automakers-bigtech, funding-news-2025-2026, open-hardware-spinouts. Overlap between items is intended; the merge dedups. Batch `profile-pilot`: 5 table items (figure-ai, agility-robotics, unitree, 1x-technologies, ubtech-robotics) that test the profile brief and the table shape on a US startup, two US/Norway startups, a Chinese private firm and a HK-listed company (public-company funding handling). Table columns: company(key), hq_country, website, status, what_it_builds, what_it_builds_source, founded_year, founded_source, funding_usd (USD, totalled, optional), funding_basis, funding_source, funding_note, latest_funding_date, valuation_usd, latest_model, latest_model_year, latest_model_source, units_shipped (optional), units_shipped_source, units_shipped_note, as_of. Reads requested: every discover item, both merges, all 5 pilot rows. Wake when both batches settle or after 180 minutes.\n\nEPISODE 2 SHOULD: (a) Check goal.json for refusals. If `profile-pilot` was refused because the plane does not keep datasets (table unsupported), re-spawn the profile batch as plain json output with the same fields and merge groupSize 20 into a table. If `discover` paused in canary, read its failures and mend the brief (likeliest problems: JSON too big -> raise maxBytes or cut per-item cap; dead source URLs -> demand the worker open each URL). (b) Read discover/merge-01 and merge-02 (and the items if merges are thin), build the canonical company list: include=yes rows plus borderline rows that fit the definition; dedup by name/website. Expect roughly 120-250 companies (China alone has 60+; the Morgan Stanley Humanoid 100 and The Humanoid Hub lists are good cross-checks). (c) Read the 5 pilot rows: check sources are real URLs, funding sums match the listed rounds, units_shipped is only ever a published figure. Mend the brief where the rows show a weakness, then spawn `profiles-a` (new name) with the full company list, one item per company, the same table shape (column names must match exactly so the write-up can union datasets), groupSize ~20, maxRows 1. Keep ~400 items of budget for later verification and gap-filling. (d) If the discovery list is clearly incomplete in one region, spawn a second targeted discover batch (new name, e.g. `discover-2`) alongside.\n\nEPISODE 3-5 SHOULD: read profiles failures and disputed cells; re-run failed items with a mended brief via itemsFrom; spawn `verify-top` with replicas {size:3} for the ~30 best-funded companies (funding_usd, valuation_usd, units_shipped, latest_model) since the ranking rests on those; spawn a `signals` batch for the top ~25 collecting ranking evidence not in the table (paid deployments and named customers, production capacity/targets, headcount, notable demos, autonomy claims vs teleoperation) with sources, output markdown, so the ranking has reasons. Then finish (target episode 6-8) and write: one table keyed by company with total funding from the dataset totals, ranking with criteria stated (funding, units shipped/deployed, latest model maturity, customers, manufacturing scale), and a list of what is missing (companies with no disclosed funding, disputed cells).\n\nBUDGET NOTE: 19 of 1000 items used after this episode. Do not spend more than ~350 on profiles, ~120 on replicas/verification, ~60 on signals; keep a reserve for re-runs.", "spawn": [ { "name": "discover", "mode": "research", "brief": "Find every company in this segment that builds humanoid robots: {{segment}}. Starting points: {{hints}}. Then search the open web (company sites, trade press such as The Robot Report and IEEE Spectrum, funding news, exhibitor lists from CES, ICRA, the World Robot Conference in Beijing, Humanoids Summit, investor lists such as the Morgan Stanley Humanoid 100 and The Humanoid Hub) until new searches stop turning up new names. A company counts when it designs and builds its own general-purpose humanoid robot: a torso with two arms and a head on legs or a wheeled base, meant for sale, deployment or research use, as a product or a publicly shown prototype. Automaker and big-tech divisions, listed companies and startups all count. Do not count pure component makers (actuators, hands, sensors), software-only or foundation-model companies without their own robot, universities and research institutes, hobby projects, single arms, exoskeletons, or small toy or education humanoids under 60 cm unless the company also builds a larger one; list such doubtful cases with include set to \"borderline\" and a one-line reason instead of dropping them. Use the company's official English name without legal suffix (Inc, Ltd, GmbH, Co) as its canonical name; for Chinese companies use the English name the company itself uses and put the Chinese name in note. Open every source_url you cite and confirm it shows the company building a humanoid; a company you cannot source is left out. Result: one JSON object and nothing else: {\"segment\": string, \"companies\": [ {\"company\": string, \"hq_country\": string (English short country name), \"website\": string, \"humanoid_product\": string (robot name and one phrase on what it is), \"founded_year\": integer or null, \"source_url\": string, \"include\": \"yes\" or \"borderline\", \"note\": string} ], \"sources_checked\": [ strings, the URLs you used ]}. Up to 120 companies per result.", "items": [ { "key": "usa", "vars": { "segment": "companies headquartered in the United States", "hints": "Tesla (Optimus), Figure AI, Agility Robotics, Apptronik, Boston Dynamics (Atlas), 1X's US operations only if HQ is US, Sanctuary AI is Canada so skip it, Reflex Robotics, Persona AI, Foundation Robotics, K-Scale Labs, Dexterity, Mentee is Israel so skip it, plus any US startup funded since 2023" } }, { "key": "canada-latam", "vars": { "segment": "companies headquartered in Canada, Mexico, Central or South America", "hints": "Sanctuary AI (Vancouver), Kinova only if it builds a humanoid, Latin American startups shown at local robotics fairs" } }, { "key": "china-startups", "vars": { "segment": "privately held startups headquartered in mainland China (not listed companies, not automaker or big-tech divisions)", "hints": "Unitree, AgiBot (Zhiyuan), Galbot, Fourier Intelligence, LimX Dynamics, Robotera (Xingdong Jiyuan), Astribot, EngineAI, Booster Robotics, Kepler Robotics, PNDbotics, Dataa Robotics, Noetix, DeepRobotics, MagicLab, Spirit AI, TARS, Leju Robotics, Qihang, AI2Robotics; Chinese sources: 36Kr, IT之家, 机器人大讲堂, Beijing and Shanghai humanoid innovation centres' lists" } }, { "key": "china-corporates", "vars": { "segment": "listed companies, state-owned groups and corporate divisions headquartered in mainland China or Hong Kong that build humanoid robots", "hints": "UBTech (HKEX 9880), XPeng (Iron), Xiaomi (CyberOne), GAC (GoMate), Chery (Mornine), BYD, Dobot, Siasun, Efort, Estun, Midea (KUKA humanoid), Shanghai Electric, China Mobile joint ventures, Huawei partners, plus HKEX and A-share filings mentioning humanoid robot products" } }, { "key": "japan", "vars": { "segment": "companies headquartered in Japan", "hints": "Toyota (T-HR3), Honda (ASIMO successors), Kawasaki (Kaleido), Hitachi, Tokyo Robotics, Preferred Networks only if it has a humanoid, Jinki Ittai, SoftBank Robotics (Pepper, NAO are borderline), Toyota Research Institute, Japanese robotics fairs (iREX)" } }, { "key": "korea", "vars": { "segment": "companies headquartered in South Korea", "hints": "Rainbow Robotics, Samsung Electronics' humanoid programme, Hyundai Motor Group's own humanoid work apart from Boston Dynamics, Naver Labs, LG Electronics, Doosan Robotics, Angel Robotics is an exoskeleton maker so borderline, Korean startups funded 2024-2026" } }, { "key": "europe-west", "vars": { "segment": "companies headquartered in the United Kingdom, Ireland, France, Germany, Netherlands, Belgium, Luxembourg, Switzerland, Austria, Italy, Spain or Portugal", "hints": "Humanoid (London), Engineered Arts (Ameca), Neura Robotics (4NE-1), Devanthro, Wandelbots only if humanoid, PAL Robotics (TALOS, Kangaroo), Pollen Robotics (Reachy, now Hugging Face), Mimic Robotics, RobCo only if humanoid, Agile Robots, Generative Bionics, Enchanted Tools (Mirokai, borderline), The Bot Company's location if European" } }, { "key": "europe-other", "vars": { "segment": "companies headquartered in the Nordic countries, Poland, Czechia, the Baltics, the Balkans, Ukraine, Russia, Turkey or any other European country not in the western list", "hints": "1X Technologies (Norway), Clone Robotics (Poland), Halodi is 1X's old name, Promobot (Russia, borderline service robot), Russian and Ukrainian humanoid projects, Estonian and Finnish startups" } }, { "key": "india-mideast-africa", "vars": { "segment": "companies headquartered in India, Israel, the Gulf states, the wider Middle East or Africa", "hints": "Mentee Robotics (Israel), Muks Robotics (India), Svaya Robotics, Vegavisor, Indian startups shown at Bharat robotics events, UAE and Saudi humanoid ventures and joint ventures announced 2024-2026" } }, { "key": "asia-other-oceania", "vars": { "segment": "companies headquartered in Taiwan, Singapore, Hong Kong only if not covered as a China listing, Southeast Asia, Australia or New Zealand", "hints": "Taiwanese ODMs and startups announcing humanoids (Foxconn, Pegatron, Wistron programmes), Singapore startups, Australian startups; Hong Kong startups that are not mainland listed companies" } }, { "key": "trackers-lists", "vars": { "segment": "any country: companies named on public humanoid-robot trackers, indexes and lists", "hints": "The Humanoid Hub company list, humanoid.guide, the Morgan Stanley Humanoid 100 (February 2025), Wikipedia's list of humanoid robots, GitHub awesome-humanoid-robot lists, Crunchbase or Tracxn humanoid robot hubs, CB Insights humanoid market maps; collect every company they name that fits the definition and give the tracker page as source_url only if it shows the company's humanoid, otherwise the company's own page" } }, { "key": "automakers-bigtech", "vars": { "segment": "any country: automakers, electronics groups and big technology companies with their own humanoid robot programme", "hints": "Tesla, Hyundai Motor Group, Toyota, Honda, XPeng, Xiaomi, BYD, GAC, Chery, Samsung, LG, Foxconn, Nvidia only if it builds a robot itself (otherwise leave out), Amazon, Meta, Apple and Google only where a public prototype or product exists; mark investors and partners who build nothing as left out" } }, { "key": "funding-news-2025-2026", "vars": { "segment": "any country: companies that announced a funding round, grant, IPO or major investment for humanoid robots between January 2025 and today", "hints": "search Reuters, Bloomberg, TechCrunch, The Robot Report, 36Kr, Crunchbase News and PitchBook news for humanoid robot funding announcements by month from January 2025 to now; give the funding article as source_url and put the round size and date in note" } }, { "key": "open-hardware-spinouts", "vars": { "segment": "any country: open-hardware humanoid makers, university or lab spin-outs and small firms selling research-grade humanoids", "hints": "K-Scale Labs, Pollen Robotics, Open Droids, ToddlerBot and Berkeley Humanoid makers only if a company sells them, Unitree and Booster for the research market are covered elsewhere so just confirm, humanoid platforms sold to universities (PAL, Robotis is borderline with its small humanoids), spin-outs from ETH, IIT (iCub via a company), KAIST, Tsinghua, MIT" } } ], "output": { "format": "json", "maxBytes": 48000 }, "merge": { "groupSize": 7, "brief": "Merge these discovery results into one deduplicated JSON object {\"companies\": [...], \"merged_from\": [item keys]} with the same company fields. Two entries are the same company when their canonical names match after removing legal suffixes and case, or their websites share a domain; keep one row, the most specific humanoid_product, the earliest non-null founded_year, every distinct source_url in a \"source_urls\" array, include=\"yes\" if any entry says yes, and join the notes. Sort by hq_country then company. No prose outside the JSON." } }, { "name": "profile-pilot", "mode": "research", "brief": "Profile one humanoid-robot company: {{company}} ({{hint}}). Use only public web sources and give a URL for every figure: the company's own site, filings (SEC, HKEX, SSE), press releases, then reputable press (Reuters, Bloomberg, FT, TechCrunch, The Robot Report, IEEE Spectrum, 36Kr for China). Fill exactly one row of the table you are given, keyed by company = \"{{company}}\". what_it_builds: one or two sentences on its humanoid line and intended use. hq_country: English short country name of the headquarters. founded_year: year of incorporation. funding_usd: total disclosed equity capital raised to date in US dollars, the sum of the rounds you list in funding_note, each with its date, amount and URL; convert other currencies at the rate of the announcement date and state the rate; exclude debt, grants and valuation. funding_basis: one of \"disclosed rounds\", \"public company\", \"parent funded\", \"undisclosed\". If the company is listed or a division and discloses no humanoid-specific raise, leave funding_usd empty, set funding_basis accordingly and give IPO proceeds or parent in funding_note. latest_funding_date: date of the newest round. valuation_usd: the latest reported post-money valuation, else empty. latest_model: the newest humanoid model publicly announced, with latest_model_year and latest_model_source. units_shipped: only a number the company, a filing or a named reputable report has published (delivered, sold or deployed units; say which, with the date, in units_shipped_note); never an estimate; empty when no public figure exists. status: \"active\", \"acquired\" or \"defunct\". as_of: today's date. Every *_source column is one URL that actually shows the figure in the same row; open each URL to confirm; a figure without a source is left empty rather than guessed. Put the row and nothing else in your JSON result.", "items": [ { "key": "figure-ai", "vars": { "company": "Figure AI", "hint": "Sunnyvale, California; Figure 01, 02 and 03 humanoids" } }, { "key": "agility-robotics", "vars": { "company": "Agility Robotics", "hint": "Salem, Oregon; Digit humanoid for logistics" } }, { "key": "unitree", "vars": { "company": "Unitree", "hint": "Hangzhou, China; H1, G1, H2 humanoids; Chinese name 宇树科技" } }, { "key": "1x-technologies", "vars": { "company": "1X Technologies", "hint": "Norway and California; EVE and NEO humanoids; formerly Halodi Robotics" } }, { "key": "ubtech-robotics", "vars": { "company": "UBTech Robotics", "hint": "Shenzhen, China; listed on HKEX as 9880; Walker S series humanoids" } } ], "output": { "format": "json", "maxBytes": 8000 }, "table": { "columns": [ { "name": "company", "type": "string" }, { "name": "hq_country", "type": "string" }, { "name": "website", "type": "string", "required": false }, { "name": "status", "type": "string" }, { "name": "what_it_builds", "type": "string" }, { "name": "what_it_builds_source", "type": "string" }, { "name": "founded_year", "type": "integer", "required": false }, { "name": "founded_source", "type": "string", "required": false }, { "name": "funding_usd", "type": "decimal", "unit": "USD", "required": false }, { "name": "funding_basis", "type": "string" }, { "name": "funding_source", "type": "string", "required": false }, { "name": "funding_note", "type": "string", "required": false }, { "name": "latest_funding_date", "type": "date", "required": false }, { "name": "valuation_usd", "type": "decimal", "unit": "USD", "required": false }, { "name": "latest_model", "type": "string", "required": false }, { "name": "latest_model_year", "type": "integer", "required": false }, { "name": "latest_model_source", "type": "string", "required": false }, { "name": "units_shipped", "type": "integer", "unit": "units", "required": false }, { "name": "units_shipped_source", "type": "string", "required": false }, { "name": "units_shipped_note", "type": "string", "required": false }, { "name": "as_of", "type": "date" } ], "key": ["company"], "totals": ["funding_usd", "units_shipped"], "maxRows": 1 } } ], "read": [ "discover/usa", "discover/canada-latam", "discover/china-startups", "discover/china-corporates", "discover/japan", "discover/korea", "discover/europe-west", "discover/europe-other", "discover/india-mideast-africa", "discover/asia-other-oceania", "discover/trackers-lists", "discover/automakers-bigtech", "discover/funding-news-2025-2026", "discover/open-hardware-spinouts", "discover/merge-01", "discover/merge-02", "profile-pilot/figure-ai", "profile-pilot/agility-robotics", "profile-pilot/unitree", "profile-pilot/1x-technologies", "profile-pilot/ubtech-robotics" ], "cancel": [], "wake": { "batches": ["discover", "profile-pilot"], "afterMinutes": 180 }, "finish": false }