My workflow is simple, step 1) THINK hard about the problem by yourself, 2) Define rough sketches of function names, params, flow, etc. adapt to your problem 3) Iterate with any LLM and create an action plan, this is where you correct everything, before any code is written 4) Send the plan to one the CLI LLM thingies and attack the points one by one so you don't run out of context.
So far has been working beautifully for real work stuff, sometimes the models do drift, but if you are actually paying attention to the responses, you should be able to catch it early.
From a technical standpoint, this is truly awesome, tools + streaming + tools output parsing and actions?, also, very good use of the tools available:
"I have four tools available in this workspace:
run_query – run SQL against your data source
search – look up saved queries/metadata in the data catalogue
run_python_code – transform query results with Python
display_chart – create visualizations from query results"