docs(simulation): Runs & results concept - #748
Merged
Merged
Conversation
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
…s/sim-optimization
Ground the page in the optimiser code and give the reader a path into doing: - correct the run model: candidates are scored against a frozen sample of the source run's conversations, not re-simulated against scenarios - scope what a run changes: the prompt (few-shot examples included), not the agent definition or the evals - replace the pipeline Mermaid with a search-loop diagram: frozen sample in, propose/score/guide loop, best prompt out - add selection guidance per algorithm from each one's mechanism, with Random Search as the starting baseline; drop the unverified GEPA cost and quality ranking - gloss Fix My Agent at first mention, disambiguate the run heading, and route the footer to the three optimization guides Signed-off-by: khushalsonawat <khushalsonawat@gmail.com>
docs(simulation): Optimization concept
Signed-off-by: khushalsonawat <khushalsonawat@gmail.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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Stacked PR 3 of 4 (base:
docs/sim-personas; review just the Runs & results file).The Runs & results concept: the run data model (run test to execution to calls, each carrying transcript, recording, metrics, eval results); statuses; reruns and snapshots; comparability.
Note: this page links to Optimization, which is PR 4 above it in the stack, so that one link resolves once PR 4 lands.
Pending links
concepts/agent-definitions) is Abhijai's parallel page (theagent-definitiontoagent-definitionsrename). Links to it resolve once that merges.