Assistants that do the work
They review the contract, chase the answer, book the meeting, flag the risk. Not chatbots that only answer: systems that carry a workflow from request to result, using your tools and your data, and knowing when to hand back to a person.
37
agents in production across four systems
7
frameworks we ship on, chosen per problem
0
irreversible actions taken without a person
Thirty-seven agents, five systems
Four of these are our own products, which is why we can open them up rather than describe them. The fifth is a delivered client system, and the client is named because they cleared it.
23
Paralegent AI
Our contract-review product: twelve scoring agents, one per legal category, smart-routing to eleven specialist analysts. Circuit breakers, two-tier retry, tracing on every request, and model-agnostic by design.
7
A family-office platform
A supervisor-router dispatching to financial, legal, knowledge, document, calendar and email specialists, with 62 tool functions and 105 endpoints behind them.
4
VectorHire
Resume, professional-network, code-host and live voice-interview agents screening a candidate at the same time rather than in sequence.
3
An AgentCore reference build
Advisor, budget planner and compliance guardrails on AWS Bedrock AgentCore — guardrails written in code that block non-compliant requests as they happen, with persistent memory.
1
Dyco Parts, delivered
A multi-agent decision assistant over an Odoo ERP — natural language to SQL, to API, document retrieval and OCR — delivered inside Slack, where the executives already were.
Six patterns we have proven in production
Anyone can wire a model to a tool. What decides whether it survives contact with real traffic is where the guarantees live.
Supervisor and router orchestration
One agent that decides, specialists that do. The alternative — every agent seeing every request — is simpler to build and far more expensive to run.
Typed tool contracts
A tool is a schema, not a prompt. If the model cannot produce a valid call, the call does not happen.
Guardrails in code, not prompts
A prompt asking a model to behave is a request. A policy engine that refuses the action is a guarantee. Dispensable actions go through the second one.
Human-in-the-loop at the boundary
The system proposes and a person disposes, wherever the action is irreversible. That boundary is designed in, not bolted on after a bad week.
A judge before delivery
Output scored against a rubric before it ships — in one build, every lesson is scored before a teacher ever sees it.
Deterministic overrides
Where arithmetic beats judgement, arithmetic wins. A real design rule from one of our systems: an ordinal is arithmetic, a name is judgement.
Route first, then reason
Smart routing cut LLM calls by 75% against the brute-force version of the same system.
Running every specialist against every input is simpler to build and far more expensive to run, and the difference only shows up once real volume arrives. That is the kind of decision this work is actually made of — not the model you pick, but what you decide to stop calling.
Chosen per problem, including none
We build custom orchestration where a framework would fight the problem — our contract-review pipeline has no framework dependency at all, and that was the right call for it.
Agent orchestration in production
The infrastructure layer: memory, authorisation, scaling, observability — everything between a demo and a system.
See the system →Deploying on AWS Bedrock AgentCore
Typed action groups, guardrails tuned per group, memory with a schema, and three environments as code — inside your own account.
See the deployment →Bring the workflow you would trust an agent with
This is our AI engineering practice
It is real work and it is where our four products came from. But what Cognilium leads with is narrower: optimization apps that run in tandem with Microsoft Dynamics 365, computing the decisions the ERP records but does not derive — the optimal price, the optimal pick path, the optimal stock level. See the optimization apps · How we build inside the ERP.