AI Engineering in Practice10 min read
uv for production AI: beyond requirements.txt
Why uv replaces pip, pip-tools, and poetry for production agentic AI services. The speed, the lockfile, and the 5-minute migration.
Loading...
Loading...
Build Your First Software Factory Execution Harness live Thursday, Oct 1, 12:00 PM ET
Oct 1, Reserve a seatHands-on projects and practical tutorials for building real-world AI applications. Step-by-step guides from concept to production deployment.
40 posts in total
AI Engineering in Practice10 min read
Why uv replaces pip, pip-tools, and poetry for production agentic AI services. The speed, the lockfile, and the 5-minute migration.
AI Engineering in Practice10 min read
How to wire Langfuse into an agentic AI service for full observability. The trace hierarchy, the decorator pattern, and what to log per span.
AI Engineering in Practice11 min read
How to cut Docker build time for agentic AI images from 8 minutes to 40 seconds. The layer order rule, the cache mount, and the trap beginners hit.
AI Engineering in Practice11 min read
How to use JWTs for agentic API auth. The claims that matter, the refresh rotation pattern, and the middleware that keeps long-running agents logged in.
AI Engineering in Practice11 min read
How to rate limit a FastAPI agent service. Token buckets per user, burst control, and the Redis pattern that survives multi-worker deployments.
AI Engineering in Practice10 min read
Why exposing DB models as API responses leaks sensitive fields. The Pydantic separation pattern, the 3 schema layers, and the safe FastAPI response.
AI Engineering in Practice11 min read
How to model users and conversation sessions for multi-tenant AI agents. The schema, the tenant guard, and the pattern that scales to thousands.
AI Engineering in Practice10 min read
Why your agentic AI service hits 'broken pipe' errors at 100 users and how SQLAlchemy connection pools fix it. The sizing rule and the lifespan pattern.
AI Engineering in Practice10 min read
How SQLModel gives agentic AI systems type-safe structured storage. The end of JSON blob columns, the Pydantic bridge, and the 50-line pattern.
AI Engineering in Practice11 min read
Why every agentic AI container should run as a non-root user. The Dockerfile pattern, the permission gotchas, and the attack it actually prevents.
AI Engineering in Practice12 min read
Why production LangGraph agents need a postgres checkpointer and thread model. How persistence survives restarts, and the trap that loses every chat.
AI Engineering in Practice11 min read
Why agentic AI systems need .env.development and .env, not one shared file. The config pattern that prevents leaked keys and broken deploys.