cardosofelipe/syndarix
1
0
Fork 0
forked from cardosofelipe/fast-next-template
Code Issues 18 Pull Requests Wiki Activity

Agent Types: Fine-tune personality prompts through testing #103

New Issue
Open
opened 2026-01-06 13:26:36 +00:00 by cardosofelipe · 0 comments
cardosofelipe commented 2026-01-06 13:26:36 +00:00
Owner
Copy Link

Context

The 27 agent types now have comprehensive personality prompts based on SOTA research (Anthropic, CrewAI, role prompting papers). These need real-world testing to refine.

Tasks

  • Run test conversations with each agent type
  • Evaluate if personality traits come through consistently
  • Check for any unwanted behaviors or inconsistencies
  • Refine prompts based on observed performance
  • Validate temperature settings produce expected creativity levels

Structure of current prompts

Each agent has:

  • Core Identity section
  • Expertise & Approach section
  • Working Principles (4-6 bullet points)
  • Communication Style description
  • Scenario Handling guidelines

Temperature ranges used

  • 0.2-0.3: Coding agents (precision tasks)
  • 0.4-0.5: Analytical agents (BA, QA, etc.)
  • 0.5-0.6: Leadership/management agents
  • 0.6-0.7: Creative agents (UX, Technical Writer)

Priority

Medium - Requires actual agent interactions to validate

Labels

enhancement, agents, testing

## Context The 27 agent types now have comprehensive personality prompts based on SOTA research (Anthropic, CrewAI, role prompting papers). These need real-world testing to refine. ## Tasks - [ ] Run test conversations with each agent type - [ ] Evaluate if personality traits come through consistently - [ ] Check for any unwanted behaviors or inconsistencies - [ ] Refine prompts based on observed performance - [ ] Validate temperature settings produce expected creativity levels ## Structure of current prompts Each agent has: - Core Identity section - Expertise & Approach section - Working Principles (4-6 bullet points) - Communication Style description - Scenario Handling guidelines ## Temperature ranges used - `0.2-0.3`: Coding agents (precision tasks) - `0.4-0.5`: Analytical agents (BA, QA, etc.) - `0.5-0.6`: Leadership/management agents - `0.6-0.7`: Creative agents (UX, Technical Writer) ## Priority Medium - Requires actual agent interactions to validate ## Labels enhancement, agents, testing
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
agents
Agent orchestration
 architecture
Architectural decisions
 backend
Backend work
 blocked
Blocked by dependency
 database
Database/migrations
 design
UI/UX design work
 devops
DevOps/Infrastructure work
 epic
Epic/parent issue
 frontend
Frontend work
 infrastructure
Infrastructure / DevOps
 mcp
MCP related
 phase-0
Phase 0: Foundation
 phase-1
Phase 1: Core Platform
 phase-2
Phase 2: MCP Integration
 priority:high
High priority
 spike
Architecture spike / research task
No Label
Milestone
No items
No Milestone
Assignees
Clear assignees
cardosofelipe
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: cardosofelipe/syndarix#103
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?