•1 min read•from Data Science
Agentic Workflows beyond "pull the data"
i've been using the robots to do a lot of my data retrieval and general project planning. i haven't actually used an agent to train/eval a model though. i would like to hear your use cases, if you have.
how did you frame the work to the agent? how did you give the agent feedback to decide if it was "done"? how did you decide if the model/output was "good"? did you let the agent decide?
maybe i am over thinking it. maybe i just say "train a model on this data to predict XYZ. try as many models as you like and report back the best performing model." then i can just sit there and watch it cook.
share your stories please.
[link] [comments]
Want to read more?
Check out the full article on the original site
Tagged with
#big data management in spreadsheets
#generative AI for data analysis
#conversational data analysis
#Excel alternatives for data analysis
#real-time data collaboration
#intelligent data visualization
#data visualization tools
#enterprise data management
#big data performance
#data analysis tools
#data cleaning solutions
#rows.com
#automation in spreadsheet workflows
#agentic workflows
#model training
#predictive modeling
#model performance
#model evaluation
#data retrieval
#output quality