ENTRIES
Fig. 6 · claude-code-second-brain
· 9 MIN
How I set up Claude Code to stop starting from zero
A global memory vault that gives my coding agent context across sessions, machines, and agents, plus the small config tweaks that keep a live session sharp. The architecture, the tooling I looked at, and the honest numbers.
ai engineeringclaude codeagent memory
Fig. 5 · resume-as-mcp-server
· 10 MIN
I had to apply through a company's MCP server, so I made my résumé one
Most hiring MCPs make a candidate's agent apply or a recruiter's agent screen. I published my résumé as a remote MCP server instead, so a company's agent can query my work, assess fit, and reach out. The build, the security model, and the honest adoption caveat.
mcpmodel context protocolagents
Fig. 4 · 6gb-vram-local-agent
· 10 MIN
6GB of VRAM is enough, if you know where the tokens go
A personal AI agent on a 2018 gaming laptop with 6GB of VRAM. The five budget constraints that actually decide a local agent stack, each measured.
local llmollamaagents
Fig. 3 · prompt-cache-timestamp
· 10 MIN
The prompt caching mistake that costs more than no caching at all
A changing timestamp in your prompt prefix gives you a 0% cache hit on OpenAI, so you just save nothing. On Anthropic the same line makes your bill 25% higher than if you had never cached. Measured, with a reproducible benchmark you can play with.
ai engineeringprompt cachingkv cache
Fig. 2 · coercion-layer-when-swapping-models
· 8 MIN
If you keep swapping models in production, you need a coercion layer
I swapped Claude Sonnet for an open model ~50x cheaper. The gaps I hit are why a coercion layer is non-negotiable once you keep changing models in a production agent.
ai engineeringtool callingopen models
Fig. 1 · evidence-over-claims
· 2 MIN
Evidence over claims
What this site is for, and the plan.
metaai engineering