Add blog post: what a pre-built schema saves (tokens, money, CO2) - #135
Merged
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #134.
Public, citable blog post (EN) on the token/cost/CO2 savings of pre-built FlowMCP schemas vs. an agent exploring an API from scratch every time.
Worked example: the 47 Berlin Data-Configurator sources (36 distinct schemas; the OParl fan-out is 1 schema → 11 districts). Anchor scenario: "bad air → where can I get to instead?" (luftdatenberlin + transportrestvbb).
Numbers: all figures come from a deterministic script that reads the Memo-143 measurement data + the live configurator payload — no hand-computed numbers. Modelled values are marked; ecological figures are reported as ranges (model inference energy is undisclosed). Security-check cost verified against real schema files (~3.3k tokens; ~8× cheaper than a full grading).
Tone: frames progressive disclosure / context engineering as a rationalized implementation of a known principle (Anthropic, Chroma, arXiv cited openly) — no novelty claim.
Built locally:
astro buildgreen, 177 pages, post rendered and listed on /blog.