deployment
Model routing between fast and smart engines
Model routing directs requests between fast and capable LLMs based on complexity, balancing accuracy against latency and cost at scale.
2026-03-2812 min read
Goatfied blog
Benchmarks, deployment notes, and hard-won patterns
Developer-to-developer writing. No fluff. Just what worked, what failed, and what shipped.
Filter by category
Filter by tag
All#security#refactoring#open-source#models#deployment#benchmarks#agent-loop#self-hosted#gpu#infra#devex#debugging#apps#agents#planning#tools#benchmark#cursor#copilot#code-review#triage#automation#pull-requests#architecture#reliability#case-study#strategy#trust#onboarding#telemetry#ux#inline-diff#ghost-text#lsp#completion#context#sandboxing#secrets#prompting#testing#docs
security
PR triage automation with risk scoring
PR triage automation uses risk scoring to prioritize code reviews based on change impact, contributor history, and affected systems rather than simple rule-based labels.
2026-03-1811 min read
open-source
Prompt patterns for reliable test generation
Learn prompt patterns that treat test generation as a contract-driven workflow instead of one-shot compilation to produce tests that catch real regressions.
2026-03-0813 min read
security
Pull request summaries that engineers actually read
Pull request summaries improve code review quality by stating what changed, why it changed, and what risks need scrutiny without assuming shared context.
2026-02-2810 min read
prompting
Repository indexing that keeps context fresh
Production repository indexing must track code changes in real-time to prevent AI agents from referencing deleted functions, outdated APIs, and stale dependency graphs.
2026-02-1812 min read
ux
Sandboxing untrusted tools in dev workflows
Learn how to isolate untrusted code execution in development workflows using containers, VMs, and permission boundaries without breaking developer productivity.
2026-02-1012 min read
agent-loop
Secret detection before agent execution: a production playbook
A production guide to integrating secret detection into LLM agent workflows before code execution, covering detection placement, performance tradeoffs, and agent-specific leak patterns.
2026-01-319 min read
architecture
Telemetry ethics for open-source assistants: a production guide
Learn how to build telemetry systems for AI coding assistants that improve models without leaking source code or secrets beyond user infrastructure.
2026-01-2112 min read
prompting
Tool call retries with deterministic guards
Tool call retries waste tokens on errors that won't resolve through repetition; deterministic guards validate inputs before execution to prevent futile retry cycles.
2026-01-1110 min read