Maestro
A self-hostable platform of purpose-built AI agents that compose into scheduled, multi-step workflows for small businesses.
Where it stands
The work that grows a small business — finding the right people, writing to them, handling what comes back — is steady, repetitive and rarely done well, because nobody has time for it. General agent platforms answer this with a blank canvas, which hands the operator a building problem on top of the one they already had. Maestro takes the opposite position: it ships the agents already wired for the job and asks you to configure them.
Small businesses doing their own outbound, starting with three closed-beta design partners selling B2B software. They want to own their contact data and run the thing on their own box rather than rent it.
The hero automation books real meetings for the three design partners, running on their own infrastructure, against their own data, with a human approving every message that leaves.
Harden the platform before the beta widens
Two dozen findings from a full code review. Roughly two thirds are fixed on a branch; the rest are open.
Latest updates
Runs now report they are alive while they work, and anything that stops reporting is closed out rather than sitting as running forever. Schedules claim their slot in a single step, so a restart, a second copy of the service, or a failure part-way through a tick cannot produce the same run twice. Long downtime replays at most one run per schedule instead of a burst.
A systematic read of the runtime, the API, the integrations and the database turned up twenty-four issues, several of them security-relevant. The most serious were fixable straight away and were: credentials can no longer be read out without authorisation, the general-purpose web step can no longer be pointed at internal addresses, and outgoing mail headers are sanitised. Two thirds of the list is now written and verified, and none of it has shipped yet.
How an integration, an agent, an automation and a schedule are authored is now written down in a form both a person and a machine can read, and there is a single definition of what makes an automation valid — checked in one place instead of three. This is the groundwork for describing an automation in plain English and having it drafted for you.