· 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
Tagged: agents
11 articles
· 3 min read
You probably don't need multi-agent
The orchestrator, the critic, the researcher and the planner walk into your architecture. One model with good tools was already doing the job. The math and the exceptions.
#agents#architecture#cost
· 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
· 3 min read
MCP in production, now that it grew up
The July 2026 MCP spec brings a stateless core, tasks and real enterprise auth. What changes for those of us who duct-taped servers together last year.
#mcp#agents#tooling
· 4 min read
Design tools for the model you have, not the intern you imagine
Agents do not read your mind, they read your tool descriptions. Most agent failures I debug are tool design failures with extra steps.
#agents#tools#mcp
· 4 min read
Agent memory that isn't a vector database cope
File-based memory, context editing and compaction are now first-class API features. The patterns that survive long sessions, and the one that never did.
#agents#memory#context
· 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
· 4 min read
Sandbox the agent like it's someone else's code, because it is
Your agent executes text written by a probability distribution. Filesystem, network and credential boundaries for code you didn't write and can't fully predict.
#agents#security#sandboxing
· 4 min read
Your context window needs a budget, not a bigger limit
Million-token windows did not fix context rot, they subsidized it. How I split the window into line items and stopped my agents from getting dumber mid-task.
#context#agents#architecture
· 3 min read
Humans in the loop, but at the right loop
The Replit incident was not an argument against agents. It was an argument against agents holding production credentials with a pinky promise as the guardrail.
#agents#safety#architecture