Canon — what we agree on
Offload, reduce, retrieve, isolate. Manus-scale tasks need 50+ tool calls; window size alone never saves you.
Skill files evolved offline, gated by tests, merged as pull requests. Open question: our eval dataset.
At-least-once delivery and retries fit the capture-to-synthesis pipeline.
57% of orgs run agents in production (late 2025). Reliability comes from observed iteration, not pre-launch design.
Knowledge outside model weights stays inspectable and editable; progressive disclosure keeps context cheap.
MCP says what an agent can reach; skills say how to use it well. Teams report 40-60% cycle-time cuts.
Independent contexts catch what a saturated context misses. About 3x tokens for 2x fewer escaped bugs.