Multi-agent systems, and what they cost
By the end of today you can say what splitting work across several agents actually buys, name the four costs it adds, and recognise the cases where one well-scoped agent is plainly better.
YesterdayOn Day 65 you learned microservices solve an organisational problem at a technical price. Multi-agent is the same argument, and most of the same costs.
TomorrowTomorrow, MCP, and how tools become a standard instead of a bespoke integration.
Why this matters
Multi-agent is the most over-applied pattern in the field. It is genuinely useful for a narrow set of shapes and expensive everywhere else, and the reasoning is almost identical to microservices.
- Multi-agent systems
- Briefing a sub-agent
- Coordination cost
- Context isolation
Learn it
70 minCopy this into Claude or ChatGPT. It quizzes you before it explains anything, which is deliberate. The resources under it are how you check what it told you.
Today's Master Prompt
Free · sign inA prompt written for this day alone: your level, the exact scope, what to leave out, and an instruction to quiz you before it explains anything. Paste it into Claude or ChatGPT and it teaches you today's material.
Check it against something that is not a model
An assistant can be fluent and wrong, and on a topic you met today you will not catch it. These cover the same ground and were made by people who do this for a living, so they are what you hold the explanation up against. They are other people's work and we only link to them, so judge them for yourself.
3 hand-picked resources
Free · sign inVideos, official docs and articles covering the same ground, each opened and annotated by hand. They are what you check the assistant against on a day you cannot yet catch it being wrong.
Build it
50 minTake a task that fans out over several independent items. Build it two ways: one agent handling everything in sequence, and a coordinator delegating to parallel sub-agents. Measure total tokens, wall-clock time and correctness for both. Then deliberately under-brief one sub-agent and record what it does.
Recall it
25 minAnswer out loud, reveal, then mark honestly whether you had it. That score is the only thing on this page you do not get to choose.
5 recall questions
Free · sign inQuestions you answer from memory, then grade yourself against the real answer. The score is carried into the mastery rating below it, so an honest miss cannot quietly become a tick.
Rate it
Completion and mastery are tracked separately. Be honest, because an inflated rating only means the concept resurfaces sooner.
Mastery tracking
Free · sign inRate yourself against five named criteria per concept. Completion and mastery are tracked separately, and anything you rate shakily comes back automatically on a spaced schedule.
Recap
- 01Context isolation is the real benefit, and the least mentioned
- 02Every delegation re-establishes context from nothing, twice over
- 03This is microservices, with the same costs and the same overuse
- 04A sub-agent knows only what its brief tells it
Your progress
Free · sign inMark days complete, pick up where you left off across devices, and watch completion and mastery diverge. Free, and the account exists only so ninety days of work cannot vanish with a cleared browser.