mirror/temporal-ai-agent
1
0
Fork 0
mirror of https://github.com/temporal-community/temporal-ai-agent.git synced 2026-03-17 06:58:09 +01:00
Code Issues Packages Projects Releases Wiki Activity

- dynamic agent prompt based on multi goal or not

Browse Source 
- made choose_agent_goal be dynamically included
- made tool selection not be required in all toolchains
- changes to get env vars easier in workflow
- Updated docs/guides, todo based on aboe
This commit is contained in:
Joshua Smith
2025-04-08 15:01:11 -04:00
parent f567583b3a
commit c18a40b502
11 changed files with 150 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
todo.md
View File

@@ -1,11 +1,15 @@
# todo list
[ ] goal change management tweaks <br />
- [ ] maybe make the choose_Agent_goal tag not be system/not always included? <br />
- [ ] try taking out list-agents as a tool because agent_prompt_generators may do it for you <br />
- [ ] make goal selection not be a system tool but be an option in .env, see how that works, includes taking it out of the goal/toolset for all goals <br />
- [x] maybe make the choose_Agent_goal tag not be system/not always included? <br />
- [x] try taking out list-agents as a tool because agent_prompt_generators may do it for you <br />
- [x] make goal selection not be a system tool but be an option in .env, see how that works, includes taking it out of the goal/toolset for all goals <br />
- [x] test single-goal <br />
- [x] test claude and grok<br />
- [x] document in sample env and docs how to control <br />
[ ] expand [tests](./tests/agent_goal_workflow_test.py)<br />
[ ] try claude-3-7-sonnet-20250219, see [tool_activities.py](./activities/tool_activities.py) <br />
[x] try claude-3-7-sonnet-20250219, see [tool_activities.py](./activities/tool_activities.py) <br />
[x] test Grok with changes
[ ] adding fintech goals <br />
- Fraud Detection and Prevention - The AI monitors transactions across accounts, flagging suspicious activities (e.g., unusual spending patterns or login attempts) and autonomously freezing accounts or notifying customers and compliance teams.<br />