surferbayarea
Joined 15 years ago
Joined 15 years ago
How It Works
Planning — Two independent AI architects design competing solutions. Adversarial critics tear each design apart. Refiners address the critiques. A judge synthesizes the best elements into a final plan. The result: plans that have been stress-tested before a single line of code is written.
Execution — A deterministic pipeline runs your plan through configurable steps (code, build, lint, test, review, PR) with evidence-based validation at each stage. State lives on disk, not in LLM memory — every step gets a fresh agent with zero context rot.
Some things to note : this didn't even require a complex multi-agent pipeline. A single shot prompting was able to detect these errors.
For now, we support MySQL, PostgreSQL and SQLite, but are also planning to add support for Mongo. Do you have Mongo/NoSQL databases on your roadmap?
It would be great to connect on a zoom - I'm the co-founder of imagine, my email is [email protected]
(I couldn’t see my earlier post for some reason on Show HN and I thought I accidentally deleted it, so I thought rather than me reposting it, it would be nice to have one of our contributors share his perspective).