Agentic AI systems violate the implicit assumptions of database design
1–10 of 115 posts
Re: Agentic AI systems violate the implicit assumptions of database design
#2Giving LLM agents direct, autonomous access to a real production databases with write access seems insane to me.
NO ONE, agent or human, should have direct write access to production databases outside of emergency break glass scenarios. This is why we have stored routines and API layers to pre-define what writes are allowed. The facts that agents CAN autonomously write to a database does not imply that they should.
For the point about query optimization, again your agents should not be issuing random queries against a production database. We have had the concept of separate analytics databases with different architectures to support exporatory queries for decades.
Re: Agentic AI systems violate the implicit assumptions of database design
#3Who the hell let agents directly use a database? Even humans don’t get this privilege. So, of all things, we forgot how to write APIs now? The article suggests creating a role for the agent directly in the database. What is wrong with you people? The very title of the article defeats its own purpose. They are not designed for this so don’t let them be used like this, ffs.
Re: Agentic AI systems violate the implicit assumptions of database design
#4Giving LLM agents direct, autonomous access to a real production databases with write access seems insane to me. NO ONE, agent or human, should have direct write access to production databases outside of emergency break glass scenarios. This is why we have stored routines and API layers to pre-define what writes are allowed. The facts that agents CAN autonomously write to a database does not imply that they should. F…
LLM agents are unlocking demand and supply for applications that wouldn't have been possible before due to time constraints though. There's a growing demand for single user or smaller scoped apps where giving LLM agents direct access means velocity. The failure/rollback model is much easier with these as long as we have good backup hygiene.
Re: Agentic AI systems violate the implicit assumptions of database design
#5This article has all the correct conclusions and solutions based on one assumption that doesn’t have any hold in reality - that someone would be insane enough to allow direct DB access to an AI agent.
Re: Agentic AI systems violate the implicit assumptions of database design
#6Giving LLM agents direct, autonomous access to a real production databases with write access seems insane to me. NO ONE, agent or human, should have direct write access to production databases outside of emergency break glass scenarios. This is why we have stored routines and API layers to pre-define what writes are allowed. The facts that agents CAN autonomously write to a database does not imply that they should. F…
I totally i agree! even read access specialty when databases has some sensitive/personal information about users.
Re: Agentic AI systems violate the implicit assumptions of database design
#7Giving LLM agents direct, autonomous access to a real production databases with write access seems insane to me. NO ONE, agent or human, should have direct write access to production databases outside of emergency break glass scenarios. This is why we have stored routines and API layers to pre-define what writes are allowed. The facts that agents CAN autonomously write to a database does not imply that they should. F…
LLM agents are unlocking demand and supply for applications that wouldn't have been possible before due to time constraints though. There's a growing demand for single user or smaller scoped apps where giving LLM agents direct access means velocity. The failure/rollback model is much easier with these as long as we have good backup hygiene.
This makes no sense whatsoever.
It's not news that if you just give all developers at a company write access to the production databases, owner permissions on all resources, etc. that velocity can be increased. But at what cost?
The reason we don't do that in most cases is that "move fast and break things" only makes sense for trivial, non-critical applications that don't have any real importance, like Facebook.
Re: Agentic AI systems violate the implicit assumptions of database design
#8Giving an LLM write access is insane but I gave LLM’s read-only access to our database and it’s been a huge productivity win.
Executives who wouldn’t take the time to build a report are happy to ask an AI agent to do so.
Re: Agentic AI systems violate the implicit assumptions of database design
#9There are two broad types of databases: operational and analytical.
Operational databases store transactions and support day-to-day application workflows.
For analysis, data is often copied into separate analytical databases (data warehouses), which are structured for efficient querying and large-scale data processing. These systems are designed to handle complex, random queries and heavy workloads.
LLM agents are the best way to analyze data stored in these databases. This is the future.
Re: Agentic AI systems violate the implicit assumptions of database design
#10Giving an LLM write access is insane but I gave LLM’s read-only access to our database and it’s been a huge productivity win. Executives who wouldn’t take the time to build a report are happy to ask an AI agent to do so.
How do you validate that the reports are correct? What if an executive makes a wrong business decision because the LLM wrote a wrong SQL query?