· 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
Agents
6 articles
· 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
· 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
· 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