Deep dive · · 6 min read
Adding a second agent does not add intelligence, it adds a contract
Six posts on multi-agent systems, and the failures were never inside an agent. They were between two of them.
Topic
Multi-agent
20 entries.
In the glossary: Orchestration (supervisor, pipeline, peer), what each means and how to say it in a review
Part of AI & Models: all AI & Models entries · the AI & Models lens on the map
Entries
Deep dive · · 6 min read
Six ways to wire agents together, and the same three things break every time
The topology gets all the design attention. Ownership, termination and traceability are what decide whether it survives contact with production.
Deep dive · · 6 min read
Most agent controls do not actually control anything
Six days of notes on supervising autonomous systems, and the same failure shape kept turning up: the control exists, it is documented, and nothing in the running system is bound by it.
Explainer · · 2 min read
A wrong answer tells you nothing about which agent was wrong
Multi-agent systems need trace timelines, trajectory evals and designed recovery, because the final output hides everything that produced it.
Explainer · · 2 min read
An agent that stops when it feels finished has no stop condition
Permissions belong to roles, budgets belong to runs, and termination has to be something a machine can check.
Explainer · · 2 min read
Every multi-agent pattern is an answer to one question: who controls the run
Supervisor, orchestrator-worker, planner-executor, pipeline and judge differ mainly in where control lives and when it returns.
Explainer · · 2 min read
Write role contracts, not agent personalities
"You are a meticulous senior researcher" is a costume. Inputs, outputs, permissions and done criteria are a contract.
Comparison · · 2 min read
Most teams reaching for multiple agents do not need them
Separation of work has to buy quality, control or throughput. Usually it buys a harder debugging problem.
Explainer · · 1 min read
Why multi-agent systems need decision rules
Why agents need arbitration rules before disagreement reaches the final answer.
Explainer · · 2 min read
Why agents need a shared language
Why agents need shared message contracts before they can collaborate reliably.
Explainer · · 2 min read
Why role design matters more than agent count
Why agent roles need clear purpose, authority, tools, memory, and evaluation.
Explainer · · 1 min read
When decentralized agent behavior makes sense
Why decentralized agent behavior needs convergence rules before it earns production trust.
Explainer · · 2 min read
Why AI debate needs a reliable judge
Why AI debate is only useful when the judge has reliable criteria.
Explainer · · 1 min read
Why shared state needs structure and attribution
Why shared state needs structure, attribution, and versioning to stay debuggable.
Explainer · · 1 min read
Why peer agents need protocols, not vibes
Why peer agents need communication rules, round limits, and a final decision owner.
Explainer · · 2 min read
Why dynamic dispatch needs ownership rules
Why dynamic dispatch needs visible routing decisions and clear final ownership.
Explainer · · 1 min read
Why pipelines make AI handoffs inspectable
Why predictable AI workflows often benefit from pipeline structure before agent autonomy.
Explainer · · 1 min read
Why supervisor agents help and where they bottleneck
Why supervisor agents help only when routing, review, and authority are clear.
Explainer · · 1 min read
When hierarchy helps multi-agent work scale
Why hierarchy helps when work has real layers of authority and responsibility.
Explainer · · 1 min read
Why one giant agent is rarely the cleanest design
Why multi-agent systems should reduce complexity through specialization, not add agents for novelty.