I am a 9/11 survivor. Every year my mother calls to remind me what that day was like for her. Sixteen years ago I wrote about what surviving Tower 2 meant to me; twenty-five years on, I still think those words hold. A personal note, not a technical one.
Je suis un survivant du 11 septembre. Chaque année, ma mère m’appelle pour me rappeler ce que cette journée a représenté pour elle. Il y a seize ans, j’ai écrit ce que signifiait pour moi avoir survécu à la tour 2 ; vingt-cinq ans plus tard, ces mots sonnent encore juste. Un texte personnel, pas un article technique.
Building an AI Financial Analyst with Oracle Select AI Agent — Part 5
The Builder, and Where I Let the LLM Near the Code
After building the same agent stack twice by hand I wrote a tool to generate it — and deliberately banned the model from writing any of the SQL. Where a language model earns its place in a code generator, and where determinism matters more.
Building an AI Financial Analyst with Oracle Select AI Agent — Part 4
When the Tooling Tells You It Worked
A PL/SQL object with a compile error still gets created — it just gets created INVALID, and most drivers report that as success. Why that surfaces three layers away as a missing-grant error, and the fixed order I now use to trace an agent failure back to its cause.
Building an AI Financial Analyst with Oracle Select AI Agent — Part 3
Custom Tools, and Getting the Password Out of the Code
Registering your own PL/SQL functions as agent tools, and running pandas and numpy inside the database through OML4Py. Plus the authentication problem: a stored credential cannot be read back, but the OCI Vault can be — which removes the hardcoded password entirely.
Building an AI Financial Analyst with Oracle Select AI Agent — Part 2
The Foundation: NL2SQL and RAG
Building the foundation: table comments that make natural-language SQL work, the profiles, and the vector index. Includes the IAM policy that catches everyone — the database needs its own, and being a tenancy admin does not cover it — and the grant problem that everyone blames on roles when the real culprit is something else.
Building an AI Financial Analyst with Oracle Select AI Agent — Part 1
What It Is, Why I Went This Route, and How the Pieces Fit
Part 1 of a five-part series on building an AI financial analyst inside Oracle Autonomous Database. What Select AI Agent is, why an in-database agent beat the managed service for this use case, and how the four core objects — tool, task, agent, team — stack together.
How and why BA Soapbox moved off Wix to a self-hosted Grav instance on Oracle Cloud's Always Free tier, provisioned with Terraform — the stack, the manual steps Terraform did not cover, and the networking, storage and billing surprises underneath it that ate a weekend.
After a three-year hiatus spent relocating back to New York and shifting into a Data Engineer role focused on AI/ML delivery on Oracle Cloud, the blog is back — with a Select AI Agent series already in the works.
A Red Hot session on integration options between Oracle Cloud applications (Fusion, EPM) and the modern data platform on OCI, covering the Lakehouse architecture, extraction methods, and recommended patterns.
