From 585791e826ee148f81ff8e41d9c90008d4bfb68c Mon Sep 17 00:00:00 2001 From: Joshua Smith Date: Fri, 11 Apr 2025 09:36:46 -0400 Subject: [PATCH] todo updates --- todo.md | 15 ++++----------- 1 file changed, 4 insertions(+), 11 deletions(-) diff --git a/todo.md b/todo.md index f06d42b..b43dd41 100644 --- a/todo.md +++ b/todo.md @@ -1,15 +1,5 @@ # todo list -[ ] goal change management tweaks
- - [x] maybe make the choose_Agent_goal tag not be system/not always included?
- - [x] try taking out list-agents as a tool because agent_prompt_generators may do it for you
- - [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
- - [x] test single-goal
- - [x] test claude and grok
- - [x] document in sample env and docs how to control
- [ ] expand [tests](./tests/agent_goal_workflow_test.py)
-[x] try claude-3-7-sonnet-20250219, see [tool_activities.py](./activities/tool_activities.py)
-[x] test Grok with changes [ ] adding fintech goals
- 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.
@@ -17,7 +7,10 @@ - Portfolio Management and Rebalancing - The AI monitors a customer’s investment portfolio, rebalancing it automatically based on market trends, risk tolerance, and financial goals (e.g., shifting assets between stocks, bonds, or crypto).
[ ] new loan/fraud check/update with start
- +[ ] LLM failure->autoswitch:
+ - detect failure in the activity using failurecount
+ - activity switches to secondary LLM defined in .env + - activity reports switch to workflow [ ] ask the ai agent how it did at the end of the conversation, was it efficient? successful? insert a search attribute to document that before return
- Insight into the agent’s performance