Writing
Notes from a season of AI meetups in Warsaw: the demos got dramatically better while the number of agents actually running unattended in a business barely moved. The gap is not model quality — it is everything around the model.
Most multi-agent systems fail because the control flow itself is generated by a language model. Invert it: a deterministic orchestrator that only routes, retries and times out, with all judgement pushed to the leaves where it can be observed and replaced.
A stateless agent re-clones the repo, re-installs the dependencies and re-derives the same conclusions on every run. Giving it a durable workspace — a desk that survives the session — removes more failure modes than a bigger context window ever will.
An agent that uses your GitHub, inbox and cloud console does not need to know a single credential. Put a broker between the agent and the account: the agent states intent, the broker holds the secret, and the key never enters the model's context.