· 1 min read
Your agent is only as good as your repo
Teams keep grading the model on codebases that would fail any new human too. The preparation argument, with the checklist I actually run.
#agents#tooling#developer-experience
Tooling
8 articles
· 1 min read
temperature is a TypeError now, and the API sends a 400 for it anyway
Anthropic's Python SDK v1.0 shipped August 20 and deleted temperature, top_p and top_k from Messages calls. On Opus 4.7 and later the API already rejected them. Migration notes.
#sdk#anthropic#migrations
· 5 min read
agents can't read your website, and the fix is one Accept header
Plain fetches get div soup and cookie walls. Stripe, Cloudflare, Vercel and the Claude docs now answer Accept: text/markdown, and copying them takes an afternoon.
#agents#tooling
· 2 min read
MCP went stateless and my infrastructure diagram got boring
The 2026-07-28 spec release candidate kills sticky sessions, adds real auth, and makes remote MCP servers deployable like any other web service. Finally.
#mcp#agents#infrastructure
· 1 min read
OpenAI is un-shipping fine-tuning, check your calendar
The fine-tuning API winds down in three gates through January 2027, and one of them already closed this month. The dates, the loophole, the exits.
#fine-tuning#openai#deprecations
· 3 min read
Track LLM spend like cloud spend or repeat cloud history
OpenTelemetry's GenAI conventions finally standardize token and cost telemetry. Instrument now or meet your bill the way we all met AWS bills, screaming.
#observability#cost#tooling
· 2 min read
What AI code review catches, misses, and hallucinates
Six months of running model review on every PR. The findings, the false alarms, and why it reviews the diff but never the decision.
#code-review#tooling#agents
· 2 min read
Streaming is a UX decision you keep making by accident
Token streaming makes chat feel alive and dashboards feel broken. Where streaming earns its complexity and where buffering is the adult choice.
#streaming#ux#api