Symphony is an agentic operating system: AI agents that take a task in plain language, work across your applications — even ones with no API — and bring back finished work. They act with the access of the person who asked and stop for approval wherever you say, inside your own infrastructure if you need it. Its first edition, Orquestra, puts specialised agents to work on procurement, connected to procure.az through its MCP server.
Finishing one task means carrying information between documents, conversations, databases and applications — by hand, every time.
A chatbot can tell you what to do. Someone still has to open the systems and do it.
An assistant with its own wide-open credentials can reach what the person asking never could. Security teams are right to say no to that.
Teams buy their own tools and models, and nobody can say who uses what, what it costs or where company data goes.
Describe the task in plain language. Symphony plans the steps, coordinates the agents and returns a finished result, such as a document built from your own template, not just an answer.
An agent acts with the access of the person who gave it the task and cannot widen it. Sensitive steps wait for a person’s approval, and every action is written to the log.
Agents use the integrations you approve to read records, prepare documents and update systems — including older applications that have no API.
Agents search policies, contracts and records only as the person asking is allowed to see them, so answers come from your documents and respect your access rules.
One gateway to the models you choose: the right model for each task, quotas, and spend tracked by department — with models on your own servers where policy requires it.
Deploy in your own infrastructure, a private cloud or fully offline, with the same capabilities in every setup, so your data and logs stay with you.
The procurement edition: specialised agents for RFIs, RFX processes and procurement analytics, working with procure.az data and actions through its MCP server, with human review at defined decision points.
| Assist | Approve | Execute | |
|---|---|---|---|
| What the agent does | Retrieves information and prepares a recommendation | Prepares an action for a person to review | Completes authorised tasks within the limits you set |
| Who decides | A person, using the agent’s recommendation | A person approves before anything runs | The agent, inside its limits — exceptions go to a person |
| Good for | New workflows and sensitive information | Actions with financial or legal effect | Routine tasks whose results are already proven |
With Orquestra, prepare RFIs, structure supplier questions, review submissions and analyse procurement data on procure.az, with a person at every decision point.
Check account details, resolve routine requests and hand complex cases to a person with the full context attached.
Prepare briefs, proposals and status reports from your own records, check invoice information and route requests, with approval before anything is sent.
See which agents run, with whose access, on which models and at what cost. Set the rules once, then read the audit trail instead of taking it on trust.
A chatbot talks. Symphony agents also act: they plan the steps, use your tools and track a task through to completion.
Inherited permissions, approval steps, a full audit log and deployment inside your perimeter answer the questions security teams ask before a pilot can start.
Review every action in the activity log, track spend per department and evaluate each workflow on completion, accuracy and how often people stepped in.
Orquestra works with procure.az data and actions through its MCP server, so procurement agents start on the platform your teams already use.
From the Greek symphōnía, “sounding together”. In a symphony every instrument plays its own part, and the result is one piece of music. Symphony does the same with agents: each has its own role and tools, and together they finish one piece of work. Its procurement edition takes the name of the players themselves — Orquestra.
Symphony agents act with the access of the person who asked, and nothing more. Sensitive actions can wait for a person’s approval, every action is logged, and you decide — workflow by workflow — how much autonomy the agents get. Deployed in your own infrastructure, your data and logs stay inside it.
Allmaz is the AI product studio of Smart Solutions, which built and operates Azerbaijan's unified public procurement portal — established by presidential decree and delivered as one of the country's first public-private partnerships in digital government.
Bring us one workflow worth improving. We will run a pilot on that single process with success criteria agreed up front — what must be completed, how accurately, how often people step in — and you decide on scaling only after you have seen the results.