Add versionable self-improving agents blog post#279
Draft
just-be-dev wants to merge 1 commit into
Draft
Conversation
Deploying with
|
| Status | Name | Latest Commit | Updated (UTC) |
|---|---|---|---|
| ❌ Deployment failed View logs |
just-be-dev | 10dde2a | Jun 06 2026, 03:07 AM |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds a draft blog post arguing that 'self-improving agents' require separating the harness (code) from a versioned configuration (model, system context, skills, tools, MCP, evals).
The post walks through the anatomy of an agent, proposes a
package.json-style config where the agent's identity isname@version, and shows how an eval loop improves the agent by editing config rather than redeploying the harness. It also argues configs should be session-scoped and frozen for the life of a session rather than hot-swapped mid-task.Post is marked
draft: true.