updaates to readme, docs, added some logging in case goal setting goes bad

This commit is contained in:
Joshua Smith
2025-03-19 08:08:38 -04:00
parent c20f5d796f
commit 850404e0d5
6 changed files with 66 additions and 49 deletions

27
todo.md
View File

@@ -1,34 +1,25 @@
# todo list
[ ] add confirmation env setting to setup guide <br />
[x] add confirmation env setting to setup guide <br />
<br />
[x] how to add more scenarios, tools <br />
[ ] make agent respond to name of goals and not just numbers
[ ] L look at slides
[ ] josh to do fintech scenarios
[ ] create tests<br />
[ ] fix logging statements not to be all warn, maybe set logging level to info
[ ] try claude-3-7-sonnet-20250219, see [tool_activities.py](./activities/tool_activities.py) <br />
[ ] make agent respond to name of goals and not just numbers <br />
[x] L look at slides <br />
[ ] josh to do fintech scenarios <br />
[ ] expand [tests](./tests/agent_goal_workflow_test.py)<br />
[x] fix logging statements not to be all warn, maybe set logging level to info <br />
[ ] create people management scenarios <br />
[x] create people management scenarios <br />
[ ] 2. Others HR goals:
[ ] 2. Others HR goals: <br />
-- book work travel <br />
-- check insurance coverages <br />
-- expense management <br />
-- check in on the health of the team <br />
[x] demo the reasons why: <br />
- Orchestrate interactions across distributed data stores and tools <br />
- Hold state, potentially over long periods of time <br />
- Ability to self-heal and retry until the (probabilistic) LLM returns valid data <br />
- Support for human intervention such as approvals <br />
- Parallel processing for efficiency of data retrieval and tool use <br />
[ ] 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 agents performance <br />
[x] customize prompts in [workflow to manage scenario](./workflows/tool_workflow.py)<br />
[x] add in new tools? <br />
[ ] non-retry the api key error - "Invalid API Key provided: sk_test_**J..." and "AuthenticationError" <br />
[ ] make it so you can yeet yourself out of a goal and pick a new one <br />