Scenario and limits of authority
We define what the agent does on its own, what it proposes to a person and what it never does. Its permissions are set in the architecture, not as a request in the prompt.
AI agents · Assistants · Task automation
In AI agent development the main question is authority: what the agent is allowed to do, how its work is checked and what happens when it makes a mistake. An agent differs from a chatbot in that it acts: it chooses the steps, calls your systems and carries the task through to a result.
For teams that need to take repetitive work off people when that work still requires understanding the content: parsing requests and documents, first-line support, preparing reports, routine in CRM and internal services.
We define what the agent does on its own, what it proposes to a person and what it never does. Its permissions are set in the architecture, not as a request in the prompt.
We connect the agent to your databases, APIs and services and handle failures and timeouts in advance. Sooner or later a tool will return an error, and at that moment the agent must behave predictably.
Documents, internal procedures and data become the agent’s memory through semantic search and knowledge graphs. The agent then works from your rules and does not have to guess.
Test task sets and metrics are in place before the rollout to production. Without them, “it got better” stays a feeling, and every prompt change becomes a lottery.
Every agent action is logged: what it did, on what grounds and what it cost. The log serves both incident investigation and control of spend on model calls.
The agent works where people already work: a messenger, a web interface, an embedded widget, an internal system. A separate service that people have to make a point of visiting loses its users.
We pick a scenario that repeats often and has a verifiable result. Rare and one-off tasks do not go to an agent.
We build the agent together with a set of test tasks: quality is measured from day one, before the first user complaints.
We launch on a real flow of work, and a person confirms every action the agent takes. We look at where the agent makes mistakes and on what.
We give the agent more independence where quality is confirmed and keep human confirmation where a mistake is expensive.
We monitor quality and cost, review new cases and rerun regression checks when the model changes.
We do our engineering work together with AI agents from several vendors, under one set of rules. People start the sessions and accept the results, so we know well where an agent goes wrong and how to catch it.
Versions, test task sets, metrics, regression checks when the model or the prompt changes. We maintain an agent the way we maintain any program that has to run in production.
If your data cannot leave the perimeter, we deploy the agent on local open-weight models inside your infrastructure.
Aviation · aircraft components trading and MRO
PilotAn AI agent reads incoming RFQs, compares supplier quotes and checks trace documents. A separate deal-tracking system moves each deal through mandatory stages.
Distribution · Partner networks
In productionPartners 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.
AI infrastructure · multi-agent systems
In-house productThe 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.
IT consulting · Lead qualification
In-house productWe replaced the contact form with an AI consultant: it interviews the visitor, returns a pilot plan with KPIs and risks, and sales gets a lead with budget and timeline.
A chatbot answers with text, following a preset script or using a model. An agent performs a task: it plans the steps, calls external systems, checks the result and sees the job through. For an agent, conversation is only the interface; the work itself happens in your systems.
Most of the cost goes into integrations, preparing the knowledge and checking quality; the agent itself costs less. A simple agent with one data source and one integration point costs noticeably less than an agent with access to several systems that has to run on-premise. We give a price range after reviewing the scenario.
Whatever the architecture provides for. Actions with costly consequences need a person to confirm them; the rest are logged and reversible. We design the system on the assumption that a mistake will happen, because it will.
Yes, if your environment requires it. Local models are weaker at complex reasoning, so we match the scenario to what the model can do and discuss this up front.
With a set of test tasks whose correct answer is known, plus metrics on the real flow: the share of tasks completed without intervention, the share corrected by a person, the cost of one task. The same metrics show when the agent can be given more independence.
Usually not. One agent with good tools is cheaper and more predictable. Several agents make sense when you need different roles with different permissions, or when one participant checks another’s work. The page on multi-agent systems covers this in detail.
Multi-agent architectures · LLM · Autonomy
AI implementation · Process automation · Integration
R&D · Research · Development
The AVA calculator works out the economics of your process from your own figures, with no form and no price from us. If automation does not pay off, it says so.
Estimate the paybackDescribe the problem in your own words. If it can’t be solved or won’t pay off, we’ll say so before any work starts.