---
title: "Research workflow automation with Codex"
canonical: "https://agenticfeats.com/c/research-workflow-automation-with-codex/"
agents: ["Codex"]
evidence_grade: "C"
outcome: "partial"
job_type: "Research"
roles: ["Developer"]
source_url: "https://aisagroup.substack.com/p/how-i-use-codex-to-automate-parts"
source_date: "2026-07-07"
published: "2026-10-13"
updated: "2026-10-13"
---

> From Agentic Feats: sourced examples of AI agents at work. Map of the site for agents: https://agenticfeats.com/llms.txt

# Research workflow automation with Codex

Codex runs a weekly arXiv search, triages new papers, feeds a Zotero library, and turns hypotheses into cheap experiment tests for an AI safety researcher.

Result: The author cut time on literature triage and experiment setup, and says related-work sections now need less citation double-checking. No numbers are given.

## How it was set up

Codex app with weekly automations, a CSV of seen papers, Zotero with a vector database, subagent threads, Bitwarden Secrets Manager for scoped credentials, and a hook that blocks destructive commands.

## Worth knowing

A temporary HOME variable made Codex run cleanup against the author's real WSL home folder, because the destructive-command hook was not enabled there.

## Prompt

```text
Here is my hypothesis: [hypothesis]. Using the repo context and notes in [paths], propose cheap tests, confounders, success criteria and scrap criteria. Return paths, commands, logs and examples to inspect, plus the next cheapest check.
```

## Evidence note

First-person account with screenshots and a GIF; no figures stated

## Sources

- Original: https://aisagroup.substack.com/p/how-i-use-codex-to-automate-parts

## The receipt

- Agent: Codex
- Evidence: Claim (grade C, claim only)
- Outcome: Partial
- Job type: Research
- Roles: Developer
- Source: Blog
- Published: 2026-07-07
- Added: 2026-10-13