Rename Agent Self-Improvement to The Eval Loop#916
Merged
Conversation
Reframe the page around evals as a closed loop for AI coding assistants: the assistant writes agent code, runs evals, reads a pass/fail result, and iterates automatically until the agent is better. Add a REPL analogy to the intro. - Rename agent-self-improvement.mdx -> the-eval-loop.mdx and update title, description, and cross-references (overview, quickstart, suites, scenarios). - Trim Next steps sections that duplicated Mintlify's automatic prev/next footer: drop the suites.mdx section, reduce scenarios.mdx to the Eval Loop card, and drop the redundant Quickstart card on overview.mdx. - Rename the scenario seed key reset: -> context: in scenarios.mdx.
Contributor
|
🔍 Mintlify preview for this branch: https://daily-aleix-the-eval-loop.mintlify.app |
# Conflicts: # pipecat/evals/scenarios.mdx
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Reframes the Agent Self-Improvement page as The Eval Loop. The old name implied the agent improves itself at runtime; the page is really about a development-time loop where an AI coding assistant writes agent code, runs evals, reads a pass/fail result, and iterates automatically until the agent is better. A REPL analogy is added to the intro to make the mental model land.
Changes
agent-self-improvement.mdx→the-eval-loop.mdx; update title, description, intro, and all cross-references (overview, quickstart, suites, scenarios). No redirect added since the page was never published.suites.mdxsection (linked only to the literal next two nav pages).scenarios.mdxto the single Eval Loop card.overview.mdx.reset:→context:inscenarios.mdx.Verification
mint broken-linkspasses (no broken links).🤖 Generated with Claude Code