Every change Wellknown observed on this agent, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Recently observed → Live
Live → Recently observed
Recently observed → Live
Certificate changed, valid to 2027-01-07
Added "path_answer", "path_bespoke", "path_estimate" and 4 more; removed "answer_now", "create_analysis", "decide_path" and 5 more; changed the definition of "about" (28 tools before, 27 now)
Platform documentation and info: how it works (Answer,tiersAnalytics, Custom Analytics), usage.
A read of the data (a total, an average, a count, the top group), computed on every row, in this response. When the question is not a read it says so and names the next step. Time: as path_resolver quotes.
Order a custom analysis built for this data from a confirmed estimate, optionally with library tools alongside. Needs the person's yes and an idempotency key; a retry returns the first order. Time: as path_resolver quotes.
Live → Recently observed
Authorization required, Bearer, issuer https://auth0.mcpanalytics.ai/
Certificate changed, valid to 2027-01-07
Authorization required, Bearer, issuer https://auth0.mcpanalytics.ai/
Recently observed → Live
Live → Recently observed
Authorization required, Bearer, issuer https://auth0.mcpanalytics.ai/
Authorization required, Bearer, issuer https://auth0.mcpanalytics.ai/
Changed the definition of "build_status", "datasets_list", "datasets_upload" and 5 more
{"properties":{"pipeline_id":{"description":"pipeline_id fromcreate_analysisa build (modify_analysis)","type":"integer"},"track_token":{ ⟨11 unchanged words⟩
⟨15 unchanged words⟩ each dataset's uuid:// reference for use increate_analysispath_resolver andrun_analysis.path_tool_run.
Authorization required, Bearer, issuer https://auth0.mcpanalytics.ai/
Authorization required, Bearer, issuer https://auth0.mcpanalytics.ai/
Authorization required, Bearer, issuer https://auth0.mcpanalytics.ai/
Authorization required, Bearer, issuer https://auth0.mcpanalytics.ai/
Authorization required, Bearer, issuer https://auth0.mcpanalytics.ai/
Authorization required, Bearer, issuer https://auth0.mcpanalytics.ai/
Authorization required, Bearer, issuer https://auth0.mcpanalytics.ai/
Added "answer_now"; changed the definition of "decide_path" (27 tools before, 28 now)
⟨5 unchanged words⟩ question: which path answers it on thisdata,data.scoredOneperrecord:path.route (reuse(the|reportanswerwe|alreadypackagehave| ask | none
Authorization required, Bearer, issuer https://auth0.mcpanalytics.ai/
Added "decide_path" and "find_precedent" (25 tools before, 27 now)
Step 0 for a new question: which path answers it on this data, scored per path. reuse (the report we already have), tool_run, estimate, bespoke, ask. Deterministic, read-only.
Before estimating: how did we answer this objective before, on this data or any data? Prior packages and library runs with their tools, mappings, bespoke module names, method and verdicts. Platform-wide, read-only.
Authorization required, Bearer, issuer https://auth0.mcpanalytics.ai/
Authorization required, Bearer, issuer https://auth0.mcpanalytics.ai/
Added "my_objects" and "rerun_package" (23 tools before, 25 now)
List and search the objects you own across every question: the curated charts, tables and figures of each delivered package, grouped by objective.
Run a delivered package again, on its own data or new data: the same tools, the same curated objects, the same layout, as a new package with its own link.
Certificate recorded, valid to 2026-11-09
Authorization not required
Certificate recorded, valid to 2026-11-09
Authorization required, Bearer, issuer https://auth0.mcpanalytics.ai/
First tool surface recorded: 23 tools (server version 1.0.5)
Showing the latest 32 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
A rough answer over a sample and the layout of the full report, for the person to confirm before anything is ordered. Time: as path_resolver quotes.
Run a delivered analysis again, on its own dataset or a new one: the same tools and mappings, no rebuild. Time: as path_resolver quotes.
Which path a question about data should take (reuse, rerun, answer, tool_run, estimate, bespoke, ask or none), with the reason, every path's score and time, and the ready input for the path it picks. Executes nothing and charges nothing.
Hand back the report already delivered for this question on this data. Time: as path_resolver quotes.
Run one or more tested library tools on this dataset, with charts and a written report. No custom build. Time: as path_resolver quotes.
A read of the data (average, count, total, highest/lowest by group, a value in a month) answered in this response, in seconds. Not a read -> immediate=false with the reason; continue with decide_path.
Commission a NEW analysis built for your question. tier is REQUIRED. The user picks. Easiest: fuzzy_request (plain language) + dataset_ref + tier. Snapshot = instant automated report (~2-10 min). JSON = a fast computed answer, numbers + method, re-runnable tool you own (~5 min). Brief = the computed answer on a one-page report: chart, numbers, method (~7 min). Deck = commissioned deep analysis, a durable re-runnable module you own (30-45 min). Failed builds are never billed.
Step 0 for a new question: which path answers it on this data. One record: route (reuse | answer | package | ask | none), a score with its reason for each of answer, package, ask and none, the compiled read plan when it is a read, the method family and the library's tool fit when it is a package, and the one question to ask when something is missing. Deterministic, read-only.
Modify an EXISTING analysis into a new version: reword the question, swap the method, or add a variable. Pass tool_name + changes (plain language). Rebuilds on the analysis's own dataset by default; the original stays put. Returns pipeline tracking. Follow with build_status.
Order what the estimate promised after reviewing it: library tools that fit, a bespoke build, or both, computed on the whole dataset; one reviewed page delivered. Credits per tool run; failed runs never billed.
START HERE for a new question: free, ~30 s. A rough answer over a sample plus the layout of the complete package, every place named with the question it will answer, and a page link. Then review_estimate with the user.
Run a delivered package again, on its own data or new data: the same tools, the same curated objects, the same layout, as a new package with its own link.
Run an analysis on your data. Returns a shareable interactive report URL with statistics you can cite, re-run and share, and the method named.
⟨15 unchanged words⟩ dataset immediately and get a dataset_ref ready forcreate_analysis;path_resolver; omit it to get an upload link for ⟨35 unchanged words⟩
⟨31 unchanged words⟩ your own first. Nothing fits? Commission it withcreate_analysis.path_resolver.
⟨3 unchanged words⟩ ":"The report's processing id, returned byrun_analysispath_tool_run or build_status","type":"string"}}, ⟨4 unchanged words⟩
{"properties":{"processing_id":{"description":"Processing ID fromrun_analysispath_tool_run / reports_list","type":"string"}}, ⟨4 unchanged words⟩
⟨23 unchanged words⟩ the page link, a review checklist. Beforeorder_analytics_package.path_bespoke.
Get an analysis's parameter schema. ALWAYS call beforerun_analysis.path_tool_run.
A read of the data (average, count, total, highest/lowest by group, a value in a month) answered in this response, in seconds. Not a read -> immediate=false with the reason; continue with decide_path.