#llm
11 posts. Other tags: #evals · #agents · #nodejs · #typescript · #tutorial · #fintech · #healthcare
A dev team of agents, each in its own git worktree
How I turned Claude Code into a small team: a project manager, backend, frontend, database and QA agents working in parallel without stepping on each other.
Designing an MCP server an LLM can use safely
Lessons from exposing market data, account data and a trade journal to Claude through MCP: grouping tools, failing clearly, and never letting the model place an order.
Five levers for LLM cost that matter more than a clever prompt
Model per task, fewer tokens, caching, batching and measuring every request: the cost controls I rely on when LLMs run inside a real product.
LLMs in production: the hard part is the contract around the model
What I learned putting OpenAI, Anthropic and Gemini behind an accounting product: schemas, deterministic checks, confidence thresholds and a human review queue.
Rules first, LLM second: categorizing Colombian bank transactions
In Nora, my personal-finance app, the LLM is the last resort, not the first step. Here's the pipeline and why every AI answer becomes a rule.
Three ways LLMs fail in production, and what to do about each
API errors, broken output and answers that look right but aren't. Each one needs a different defense.
Building an LLM feature, part 1: plan before you prompt
A hands-on series on planning, designing and shipping an LLM feature, using the transaction categorizer in my finance app Nora. Part 1: the problem, the success criteria, and deciding where the model belongs.
Building an LLM feature, part 2: design the system around the model
Architecture, data model and the contract with the model for Nora's transaction categorizer: async processing, confidence scores, idempotency and rules that learn.
Building an LLM feature, part 3: build the rules, the model call and the service
The code behind Nora's categorizer: a rules-first decision function, a batched LLM call with a schema-enforced enum, and a background service that saves answers and learns rules.
Building an LLM feature, part 4: test and evaluate it
Unit tests for the deterministic parts, a golden set for the model, and an eval script that reports accuracy, coverage and confident mistakes and can fail CI.
Building an LLM feature, part 5: ship it and keep it healthy
Running Nora's categorizer in production: graceful degradation, timeouts and retries, cost tracking, logs you can query, privacy, and the loop that makes the model less necessary over time.