AI infrastructure · multi-agent systems

Agent teams assembled from configuration, with paired critic agents

The core of a multi-agent platform in 2.5 weeks: 29 declarative agents in three teams, agent-critic pairs, shared memory on four databases, five autonomy levels.

Status: In-house product
Timeline: 2.5 weeks (core)
Stack: Python
LangGraph + LangChain
FastMCP
Redis / Qdrant / Neo4j / PostgreSQL
OpenAI + Anthropic
Docker + Traefik

Describe your problem Estimate the payback All cases

The task

Ad-hoc LLM chains do not grow into a product platform: no task routing, no review of agent output, nothing accumulated between runs, and autonomy is all-or-nothing. We needed one core for several products: engineering, research and cognitive agent teams on a shared platform with quality control and managed autonomy.

What we built

A declarative platform: agents, teams and pipelines are defined in YAML, and the execution graph is built at runtime. A new agent team is added by configuration, not by rewriting orchestration code.
Agent output is reviewed by 10 agent-critic pairs, from tech lead to security red team. Critics score outputs across several dimensions and send them back for rework; unresolved disputes go to the orchestrator.
An agent registry matches tasks to executors by capability, role and tags; only knowledge that passes validation is committed to shared memory.
Four memory circuits: episodic (Redis), semantic search (Qdrant), knowledge graph (Neo4j), tasks and audit log (PostgreSQL).
Five autonomy levels that adjust to metrics and escalate to a person; a meta-agent tracks team metrics and suggests changes to team make-up. Managed via MCP tools and a monitoring dashboard. The platform runs in our lab and is not built into client systems.

Outcome

25,000+: lines of Python in the platform core across 134 modules, counted from the repository
29: declarative agents in three ready-made teams (engineering, cognitive, research); counted from YAML specs
2.5 weeks: from first commit to a working core with memory, agent-critic pairs and a dashboard, per repository history

A similar problem? Let’s look at it

Services

Multi-agent systems: when one agent is no longer enough

Multi-agent architectures · LLM · Autonomy

AI agent development: the agent acts, people set the limits

AI agents · Assistants · Task automation

More cases

Aviation · aircraft components trading and MRO

Pilot

Aircraft parts procurement: from email to a managed pipeline

An AI agent reads incoming RFQs, compares supplier quotes and checks trace documents. A separate deal-tracking system moves each deal through mandatory stages.

Full loop: the AI loop ran end to end on a live procurement process, from an incoming RFQ to a team notification. This was a pilot and the figures are our own so far: the client has not confirmed them yet
3: types of trace documents checked by the agent: FAA 8130-3, EASA Form 1 and COC. Like the figure above, it still awaits the client’s confirmation

Distribution · Partner networks

In production

A sales and support platform for a distributed partner network

Partners ask who on their team is inactive and what blocks the next level, and get numbers for their own part of the network only. Access is enforced at the SQL level.

Their own slice: a partner gets figures for their own team only: a filter on the current user is added to every SQL query
6 layers: of data protection between the language model and the database, from blocked personal-data columns in SQL to rate limits; counted in the code

AI infrastructure · multi-agent systems R&D

Research project

A multi-agent environment where the rules are code

In four days we built and open-sourced (MIT) an agent environment where code enforces the rules: cryptography, a PBFT-style agreement protocol, reproducible experiments.

same hash: a repeated run and a replay of the log give a byte-identical final event hash; anyone can check it on the MIT-licensed code
187 of 187: engine tests passing; master branch, commit 625b81d, as of 05.10.2026

Estimate the payback of a similar process

AVA lets you work out the economics of your process on your own figures, with no form and no price from us. It shows what the manual work costs, what cash effect automation would give and what budget would pay back. If the effect does not even cover running costs, it says so.

Estimate the payback

Discuss a similar problem

Describe the process and the data you have. Before any work starts we will tell you what can be measured in money, what cannot, and whether it is worth doing.

New write-ups on Telegram