Company
Blog
Engineering deep-dives, product updates, and AI economics insights from the Azoth team.
Introducing the IO Inventory Connector
Azoth now supports asynchronous vision extraction and catalog matching for IO data pipelines. Every ingest trace can be automatically enriched with image descriptions and SKU-level matching — without blocking the fast path.
GitHub Marketplace integration is live
Install the Azoth GitHub App from the Marketplace. Regression suites now run automatically on every pull request and post results as GitHub Check Runs — pass/fail, latency delta, cost delta, all in your PR review.
How we separated the ingest control plane from the data plane
Our original ingest route did too much: auth, budget check, PII scrub, database insert — all blocking the response. We split it into a control plane that stays on the request's path and an async worker behind it. Here's how.
The hidden cost of over-engineered prompts
Filler phrases, redundant context, deprecated instructions: what a prompt carries that the model does not need, and how to measure, on your own prompts, what cutting it changes.
Multi-provider routing: when to use DeepSeek vs GPT-4o
Our model matrix now spans the major AI providers, from frontier models to small open ones. Not every task needs the most capable model. We break down which routing strategies save the most money for common workloads.
Stay up to date — subscribe by email