README: sharpen "Why this exists" and restructure use cases by audience#14
Merged
Conversation
The section asserted its conclusion in one-liners and followed with a flat ten-item feature list. It now names the three failure modes of one-off LLM recommendations - no accountability, no reaction to change, no learning - which map onto the engine's provenance/versioning, signal-driven replanning, and outcome loops. The feature keywords survive embedded in prose, and "explores" no longer undercuts the production-oriented tagline.
"Example use cases" was a flat list of ten domains. Replace it with a "Use cases" section organized by the three builders the engine serves - AI agents that act, decision-support products, and anything that must answer "why did it recommend that?" - each with the concrete mechanisms it gets: MCP tools and machine-actionable moves with kill criteria for agents; ranked alternatives, domain packs, live context, materiality thresholds and the calibration/backtest loop for products; input snapshots, provenance, immutable history and outcome addressing for audits. "Why this exists" gains a closing hook linking to the section.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Two content changes to the README, following the new flow diagram (#13):
"Why this exists" rewritten as an argument. The section asserted its conclusion in staccato one-liners followed by a flat ten-item feature list. It now names the three failure modes of one-off LLM recommendations — no accountability, no reaction to change, no learning — which map one-to-one onto the engine's provenance/versioning, signal-driven replanning, and outcome loops. Closes with a hook naming the audience and linking to the use cases.
"Example use cases" → "Use cases", organized by who needs it. Instead of a list of ten domains, the section now answers "what do we provide" for each of three builders:
Every claim corresponds to a shipped mechanism (MCP server, webhooks,
dde calibrate, backtest metrics, domain packs, source enrichment).