AI Engineer
Clixsy Oracle Agent
An eval-first agent on top of the MarketBrew knowledge base, with answers cited back to the atoms.
The agent layer built on top of the MarketBrew knowledge base (see the Reference Manual project). An eval-first agentic scaffold on PostgreSQL: contracts and fixtures are defined before generation, and every recommendation is evidence-cited back to the underlying knowledge atoms. The scaffold pattern transfers across client domains.
The problem
Most LLM-backed recommendation tools generate first and validate later. When the generation is wrong, the team is left chasing why. The eval-first pattern flips that order: define the contract, build the fixtures, generate against the contract. Outputs are checkable from the moment they exist.
What we built
A PostgreSQL-backed agent layered on the MarketBrew knowledge atoms, with contracts and fixtures defined before any generation happens. Every recommendation cites the supporting atom, so a reviewer can trace the path from output back to evidence. The eval-first scaffold itself is the deliverable: a working foundation, not yet a fully deployed product.
What was delivered
- PostgreSQL schema for inputs, fixtures, and outputs
- Contract-and-fixture-first architecture
- Evidence-cited recommendation pattern with traceable provenance
- Reusable scaffold for adjacent eval-first agentic work
Outcomes
- Outputs are checkable from the moment they exist
- Recommendations cite their supporting data
- Scaffold pattern transfers to adjacent client domains
- Demonstrates the eval-first discipline Sonoma Solutions applies to AI engagements
Services: PostgreSQL, Anthropic API, Node.js, Eval-first design