Research-First Workflow Enforcement

Resolved 💬 3 comments Opened Dec 1, 2025 by smartwatermelon Closed Jan 30, 2026

Research-First Workflow Enforcement

Priority: HIGH

Problem:
Claude Code implements before understanding. Observed pattern: try commands → fail → research docs → try more commands. Should be: research docs → understand → plan → implement.

Current Behavior:

Line 26-100 of transcript: immediate EAS credential commands
Line 410: first documentation search (after many failures)
Backward workflow wastes time
Expected Behavior:

For complex unfamiliar tasks, offer: "This looks complex. Should I research [topic] first?"
Don't jump to implementation for new problem domains
Read relevant documentation before trying commands
Show what was learned from research before proposing approach
Impact:

Many failed attempts that could be avoided
Solutions based on incomplete understanding
User has to redirect AI to read docs
Suggested Implementation:

Detect complex tasks involving new technologies/APIs
Auto-suggest research phase: "I should review the EAS credential documentation before attempting setup. OK?"
Show research findings before implementation
Let user approve approach after research
Example of Good Flow:

User: "Set up EAS credentials for iOS internal distribution"

AI: "This is a complex credential setup task. Let me first research
the EAS documentation for iOS credential requirements, then propose
an approach. OK?"

[After research]

AI: "I found that EAS requires either:

  1. Interactive credential setup with Apple ID, OR
  2. Pre-existing credentials configured on EAS servers, OR
  3. Local credentials (requires .p12 + .mobileprovision files)

Based on available environment variables [lists them], approach #2
seems most feasible. Should I proceed with checking what credentials
are already configured on EAS?"

View original on GitHub ↗

This issue has 3 comments on GitHub. Read the full discussion on GitHub ↗