Add Datacenter Monitor recipe#57
Draft
khushishelat wants to merge 4 commits into
Draft
Conversation
Live map of ~2,700 US datacenters, each discovered, enriched (25 fields), and AI-impact classified by the Task API, with 31 event-stream monitors and 200 daily snapshot monitors watching the web. Per-field reasoning + citations via output.basis. Facility discovery uses shard-by-state + previous_interaction_id pagination. Moved from khushishelat/datacenter-map-demo. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Sibling recipes ship the app, not a large pre-generated dataset, and the live demo already serves the full ~2,700 facilities. Trim public/data to one facility per state (index-aligned across datacenters/enrichments-compact/ ai-classifications). public/data 5MB -> 164KB. App still renders a real national map on clone; pipeline regenerates the full set. README documents it. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
monitors.json and snapshot-monitors.json carried 231 live Parallel-account resource IDs (31 + 200 monitors, 200 run IDs). Not credentials, but account- specific artifacts not needed to run the recipe. Blank the monitorIds (keep the monitor query definitions, which teach monitor design) and empty snapshot- monitors.json; readers regenerate via setup-monitors.ts / create-snapshots.ts. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Avoid implying a single Task call is weak; frame long-tail enumeration as a decomposition problem the API is designed for. Also drop 'find all' to prevent confusion with the FindAll API, and remove an em dash. Applies to recipe README and the discovery script docstring. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Datacenter Monitor
Moves the datacenter-map-demo into the cookbook as
typescript-recipes/parallel-datacenter-map.A live map of ~2,700 US datacenters — every facility discovered, enriched, and AI-impact classified by the Task API, with 31 event-stream monitors and 200 daily snapshot monitors watching the web for new developments. Per-field reasoning and citations come from
output.basis.Live demo: https://datacenter-demo.app
What it shows
previous_interaction_idpagination (loop-until-dry) to break the single-query plateau (~50) and reach the long tail (~2,700).ultra2x+ Task Groups, structured output, with per-field basis.Notes
public/data/so it runs without re-running the pipeline..env.local.example). Anchored an over-broaddatacenters.jsongitignore rule so the shippedpublic/data/datacenters.jsonis included.🤖 Generated with Claude Code