AI Development

Building with LLMs: agents, RAG, evals, and shipping to prod. 20 posts.

AI Development

Surviving LLM API Failures: Timeouts, Fallbacks, Queues

LLM APIs fail for hours each quarter. Timeout budgets, retry rules that honour Retry-After, provider fallbacks, and queues that keep your app standing.

AI Development

A Realistic AI Pair-Programming Workflow

A realistic AI pair-programming workflow — decompose to verifiable tasks, verify like a reviewer, and the three signals to take the keyboard back.

AI Development

Open-Weight Models in 2026: What's Actually Usable

Which open-weight models are production-usable in 2026, task by task, plus licence gotchas and the maths for when they beat APIs on cost and privacy.

AI Development

Choosing a Vector Database: pgvector Until It Hurts

Start with pgvector and move only when one of four numbers turns red. The decision ladder to Qdrant, plus the benchmarks that matter and those that lie.

AI Development

Shipping AI Features Behind Flags

Ship AI features behind four controls — kill switches with defined fallbacks, shadow mode, cost circuit breakers, and pinned versions you can roll back.

AI Development

Synthetic Data That Doesn't Collapse Your Model

How to generate synthetic training data without model collapse — diversity seeding, MinHash dedup, judge calibration, and the real-data anchor ratio.

AI Development

Prompt Injection: Threat Model and Practical Mitigations

Prompt injection can't be prompted away. The threat model, the defences that fail under red-teaming, and the capability confinement that limits damage.

AI Development

Multimodal Pipelines: OCR, Vision, and Audio in One Stack

How to build one pipeline for OCR, vision, and audio — routing per modality, engine choice with real costs, and fusing outputs into one JSON shape.

AI Development

AI Code Review: Where It Helps, Where It Lies

Which bug classes AI code review catches, which it misses, and the false-positive budget that decides whether your team keeps reading its comments.

AI Development

Building an MCP Server: Field Notes

Field notes from building MCP servers — tool design agents can use, output token discipline, stdio vs HTTP transports, auth, and multi-client testing.

AI Development

Local-First AI Apps: Patterns and Pitfalls

Where local-first AI works in 2026 — model sizes per task, runtime capability probes, sync rules for derived data, and when to escalate to the cloud.

AI Development

Tracing and Observability for LLM Apps

Logs can't debug a six-step agent. Traces with spans for prompts and tools, cost per request, sampling strategies, and self-hosting Langfuse.

AI Development

Context Window Management: Budgeting, Caching, Compaction

Big context windows moved the problem from fit to cost. Set token budgets per feature, lay prompts out cache-first, and prune before you summarise.

AI Development

Embeddings Search: From Cosine Demo to Production

From cosine demo to production search: structure-aware chunking, hybrid BM25 plus vectors, cross-encoder reranking, and the eval set that proves it.

AI Development

Structured Output From LLMs: Schemas, Grammars, Retries

Reliable JSON from LLMs is a solved problem: native structured outputs, grammar-constrained decoding for local models, and validation-retry loops.

AI Development

Agent Architectures in 2026: Loops, Graphs, and Handoffs

Single loop, subagents, handoffs, or graphs — how to pick an agent architecture in 2026, and when multi-agent complexity actually pays for itself.

AI Development

Evals Before Vibes: Testing LLM Apps Properly

Skip the dashboards. Build a 50-example golden set, write code assertions first, calibrate an LLM judge against human labels, and gate CI on it.

AI Development

Prompt Engineering Is Just Engineering

Prompts are config that ships to production. Version them in git, test them in CI, review the diffs, and stop the recurring "model got worse" mysteries.

AI Development

Tool Calling Patterns That Don't Fall Apart in Production

Tool calling patterns that survive production: flat schemas, idempotency keys, parallel call handling, and error results the model can repair.

AI Development

RAG vs Fine-Tuning: When Each Actually Wins

RAG injects knowledge, fine-tuning changes behaviour. A decision framework based on data volatility, latency, and cost, plus hybrid patterns that work.