~/blog · filtered by category

runtime.

12 entries filed under this signal. ← back to all entries

[blog/category/runtime] · reverse chronological $ ls -la --filter=runtime

2026-07-20 runtime The run died at 2am: recovery as a first-class workflow The agent hit a rate limit, or lost the thread, or the context filled and it quietly forgot episode one. You wake up to a half-finished branch. Right now recovery is heroism. It should be a workflow. #recovery#checkpoints#agents#reliability#runtime 7 min ./read → 2026-07-20 runtime Running eight sessions: worktrees, parallelism and the cost of being the scheduler Parallel agents give you throughput and hand you a second job you didn't apply for. Here's how the worktree setup works, and what being the scheduler actually costs. #parallel-sessions#worktrees#agents#runtime#paelladoc 8 min ./read → 2026-07-20 runtime Orchestrating multiple coding agents without them poisoning each other More agents is more throughput and more ways to collide. The three things that keep parallel agents from contaminating each other: isolation, contracts, and reconciliation. #multi-agent#orchestration#agents#runtime#paelladoc 8 min ./read → 2026-07-20 runtime Memory for coding agents: what should persist outside the chat Not everything an agent learns deserves to be remembered, and the chat is the worst place to keep the parts that do. A practical taxonomy of what to persist, and in what form. #agent-memory#agents#ai-coding#runtime#paelladoc 7 min ./read → 2026-07-20 runtime Your rules file is lying to your agents: keeping instructions alive The rule that pointed at a script you deleted. The convention nobody follows anymore. Your agents read all of it as gospel, and a stale instruction never throws an error. It just quietly steers the work wrong. #claude-md#agents-md#stale-rules#agents#runtime 7 min ./read → 2026-07-20 runtime Harness engineering: the discipline forming around agent operations The model writes the code. Everything around the model, the loop that feeds it context, runs its tools, checks its output and recovers its failures, is a system someone has to build. That system has started to get a name. #harness-engineering#agents#tooling#reliability#runtime 7 min ./read → 2026-07-20 runtime Compaction eats your decisions: managing the context window on long work The window fills, the session compacts, and the constraint you set three hours ago is gone. The agent keeps going, confident, having quietly forgotten the thing that made the work correct. On long jobs, the context window is a budget. #context-window#compaction#agents#context-engineering#runtime 7 min ./read → 2026-07-20 runtime Context loss between sessions: the productivity killer nobody budgets for The tokens are cheap. Re-explaining the same decision to a cold agent for the fourth time is not. Here's what actually disappears when a session ends, and what to do about it. #context-loss#agents#ai-coding#runtime#paelladoc 8 min ./read → 2026-07-20 runtime Building software with AI agents: the operating guide The code is written. The job that stayed is running the loop around it: define, specify, execute, verify, learn. This is the map of that work, one stop per part. #building-with-agents#ai-coding#agents#paelladoc#runtime#spec-driven-development 14 min ./read → 2026-07-20 runtime Agents will drift: engineering for divergence instead of praying against it Drift isn't a bug you can prompt away. It's what agents do. The useful move is to design a system that expects divergence and catches it, instead of hoping this run behaves. #agents-will-drift#divergence#agents#runtime#paelladoc 8 min ./read → 2026-07-20 runtime AGENTS.md, CLAUDE.md, cursor rules: where your decisions should actually live Every tool wants its own rules file. Most of the comparisons only argue about code style. The harder question is where the product decisions go, because that is what actually rots when you get it wrong. #agents-md#claude-md#cursor-rules#agents#runtime 7 min ./read → 2026-07-20 runtime Handoffs: passing work between agents without losing the plot One agent scopes it, another builds it, a third reviews it, and somewhere in the relay the reason it was being built that way falls on the floor. The handoff is where agent work quietly loses the plot. #handoffs#agents#context#orchestration#runtime 7 min ./read →

— end of log · 12 entries in runtime —