# Writing — Shivansh Sen

Canonical: https://shivanshsen.com/blogs

This is a page overview.

AI, agents, and enterprise software.

[Read the full page](https://shivanshsen.com/blogs)

- [Agent loops, graphs, and factories: what each one controls](https://shivanshsen.com/blogs/agent-loop-graph-factory.md)
- [The API is overloaded. What should your client do?](https://shivanshsen.com/blogs/api-overloaded-client-retries.md)
- [How to tell whether an agent skill helps](https://shivanshsen.com/blogs/evaluating-agent-skills.md)
- [Deploying Salesforce metadata with GitHub Actions](https://shivanshsen.com/blogs/github-actions-salesforce-metadata.md)
- [Structure skills so agents find the right instruction](https://shivanshsen.com/blogs/structuring-agent-skills.md)
- [Write a skill an agent can find and follow](https://shivanshsen.com/blogs/writing-effective-agent-skills.md)
- [Decision Note: What building real docs with Blume took](https://shivanshsen.com/blogs/nebula-logger-docs-demo.md)
- [Decision Note: Recursive Language Models for messy business investigations](https://shivanshsen.com/blogs/rlm-explainer.md)
- [Decision Note: Claude Code in Action — A Practitioner's Take](https://shivanshsen.com/blogs/claude-code-in-action-course-review.md)
- [Decision Note: Track Code Changes with Ticket IDs in Git Commit Messages](https://shivanshsen.com/blogs/track-code-changes-with-ticket-ids-in-git-commit-messages.md)
This is my independent, unsponsored blog. I share personal views and opinions informed by my professional experience. They do not represent my current or former employers, who are not involved in this site.
