AI agents for business
Choose the process where business loses money.
We'll build an AI agent for it.
Below are 8 entry points where the effect is usually visible fastest: support, knowledge, documents, sales, backoffice, research, executive work and delivery control. First contour means one process, one metric, real data.
8 directionsEach direction below is described as a business task: what is lost, what the agent does, what the entry costs.
First contour from 250K RUBOne process, one metric, 1–2 integrations. Entry directions start from 250K RUB, procurement agent from 450K RUB.
Enterprise is a separate projectIf you need customer servers, local models, strict rights and SLA, we start with technical scoping.
Not every process is worth automating with an agent.
Honestly speaking, an agent doesn't pay off in every process. So the first thing we do in any conversation is check whether yours is the right case.
An agent works when four conditions all line up.
- 01
the process repeats: daily or weekly: requests, inbound emails, statuses, reports, customer enquiries, documents.
- 02
data is accessible: the process already lives in your systems: CRM, 1C, email, chats, drives, spreadsheets, corporate APIs.
- 03
there is an owner: a person responsible for the process who can review the agent's output.
- 04
«correct» is defined: what counts as «done correctly» is clear: so you can measure whether the agent helps.
If all four are present, the effect can be checked quickly. If data, owner or metric is missing, we help assemble the base first instead of selling development.
When it is better not to start
Just an FAQ without system integrations: a regular scripted bot is enough here, cheaper and faster.
Unique one-off tasks: if the process is new every time, the agent has nothing to learn from.
Solutions without an owner: without a person who can say «this is right, this isn't», the agent becomes a noise generator.
Fully autonomous actions in production: critical steps always require human confirmation. Not a compromise, an engineering principle.
What we do next
If your process fits, we choose a direction below and estimate the first contour. If not, we'll honestly say what is cheaper now: a regulation, CRM setup, regular bot or diagnosis.
A normal outcome of the first call is not always a sale. Sometimes the best outcome is not spending your budget.
Choose the place where money leaks now
Each direction is not an “agent role”, but a clear business loss. Open the one that looks like your situation: inside you'll see entry price, timeline, metric and limits.
Sales Agent
When leads go cold because of slow replies, forgotten follow-up and empty CRM. The agent qualifies inbound, drafts a reply, sets the next step and updates the deal card.
Personal / Executive Assistant
When an executive drowns in meetings, promises, emails and manual assembly of the day. The agent prepares briefs, meeting context and commitment control.
Research / Market Intelligence
When the market changes faster than the team can read sources. The agent watches competitors, news, prices and returns short conclusions for decisions.
Knowledge / RAG Agent
When knowledge sits in documents, but employees still ask colleagues. The agent answers from regulations and contracts with source links and access rights.
Support Agent
When routine tickets grow faster than the support team. The agent answers from the knowledge base, classifies inbound and hands complex cases to an operator with context.
Operations / Backoffice Agent
When requests, documents, acts and approvals get lost between email, chats and spreadsheets. The agent sets status, owner, deadline and next step.
Developer / Delivery Agent
When engineering has become a black box for the owner or CTO. The agent assembles weekly brief, release risks, project memory and decisions from chats.
Supplier / Procurement Agent
When the price of a missed procurement is higher than the agent cost. Monitors platforms, reads the RFP and contract, highlights risks, prepares a bid/no-bid recommendation.
What the entry costs: and what you get.
To avoid turning implementation into an endless estimate, we start with a limited contour. You see the result on your data and only then decide whether to expand the agent.
First working contour: metric check
Around one of your processes. Not a demo prototype: it actually works on your data, produces a result and writes actions to a log.
The first contour includes: one process, one or two key integrations, one main metric, basic logic, testing on your real cases, training one process owner. It doesn't include: the entire CRM, all channels at once, a large knowledge base, autonomous actions without approval.
The first-contour price depends on the direction: simpler entry scenarios start from 250K RUB, complex procurement contours from 450K RUB. That's not marketing: it's the real difference in data volume, integrations and checks.
The first contour's goal is not to sell you a large project at any cost. The goal is to see in 2–3 weeks whether there is an effect on your metric. If not, we'll say so.
Full implementation: agent for the department
Once the first contour proves value, the agent is rolled out across the whole department. It's not «we do the same thing but for more money». It's a qualitatively different project:
- ▪We connect every required data source
- ▪Multiple scenarios for different team roles
- ▪Recurring tasks, reports, reminders
- ▪Roles and access permissions
- ▪Training the whole team to work with the agent
- ▪Process support: when something changes in the business, the agent adapts
Most often the implementation is deployed on our infrastructure: SaaS-style. It's faster, cheaper and easier to maintain. If your security policy requires something different: we have three other formats, see the next chapter.
Enterprise: this is an infrastructure project
A price list doesn't work here. First we do a technical scoping: what infrastructure you have, what data requirements, which models can be used, who's responsible for security, what SLA is needed.
Enterprise isn't «a more expensive version of the first contour». It's:
- Serverspurchased or provided by you
- Deploymentin your perimeter, on-prem or private cloud
- Local modelsours or yours; we can fine-tune on your data for quality and response speed
- Controlroles, audit logs, monitoring, backups, SLA in the contract
- Integrationsoften several internal systems: ERP, DWH, EDI, billing
Price is calculated after technical scoping. Not because we hide it: but because an enterprise contour at a bank and at an industrial holding are different engineering problems.
Footnote · maintenance
From 40K RUB/month: because the agent lives in production
Fair question: you paid for the first contour, paid for the implementation, the agent works: why pay every month on top? Because the agent isn't a static website. It lives in three constantly changing environments:
- Your business changes: a new customer category, the sales lead changes, a branch opens. Without maintenance the agent will be running on old rules in 3 months and the team starts bypassing it manually.
- The models change: OpenAI ships a new version, the old prompt breaks. Anthropic improves quality, we switch. Every 2–3 months something changes on the model side, and if you don't watch: quality drops silently.
- The infrastructure changes: if the agent runs on our SaaS contour, we update servers, apply security patches, renew certificates, monitor uptime. The customer shouldn't be doing this.
Included in 40K RUB/month
- · SaaS infrastructure (if hosted with us): servers, updates, backups, certificates, uptime
- · DevNeuroX local model within the agreed limit
- · Monitoring, incident analysis, service restarts
- · Adjusting prompts and scenarios for process changes
- · Adaptation to model API changes (new versions, new billing)
Billed separately
- · External model tokens (OpenAI, Claude, Gemini): paid directly to the provider
- · Paid SaaS model subscriptions (GPT-4, Claude Opus, GigaChat Pro)
- · Major changes: new integration, new scenario, new role
- · Enterprise infrastructure (if on-prem): servers and their administration on the customer side
Maintenance covers everything that should just work «by default» so that in 6 months the agent doesn't become a ritual artifact.
Eight agents surrounding one business
Each agent owns one process. The left side covers customers, leads and the market; the right side covers internal operations. All eight can run in parallel, but it is better to start with one.
Your business
CRM · ERP · EDM · your data and processes: agents plug into what already works for you
- One first contour in 2–3 weeks: no commitment to the whole stack
- On our SaaS infrastructure or on your servers
- Local models for sensitive data
- Bilingual: RU/EN from one interface
- From 250K RUB for a first contour, from 40K RUB/month for support
You don't need to deploy them all at once. Take the process where the pain is sharpest: a 2–3 week first contour will show real impact on your data.
Four formats of infrastructure.
When people say «deploy an AI agent» they usually imagine one thing: either «in your cloud» or «on our server». In practice there are four options, and they differ not in «expensive/cheap» but in control level, launch speed and the maturity of the customer's IT team.
On our infrastructure
- For whom
- SMB. Most first contours and first deployments.
- How it works
- Servers, backups, monitoring, certificates, updates: all on our side. External LLM/API costs are paid by the customer directly or capped by limits.
- Pros
- Fast start. Low upfront cost. Simple maintenance.
- Limitations
- Not suitable for strict security requirements: banking, government. Some data may pass through external services (subject to agreement).
Dedicated cloud environment
- For whom
- Mid-market with sensitive data, but without a hard on-prem requirement.
- How it works
- Dedicated cloud environment: isolated access, own storage and logs. Can use paid external models or local/private ones.
- Pros
- Balance of control and speed. Suitable for most production deployments.
- Limitations
- More expensive than format A. Requires cloud environment architecture sign-off.
On your servers
- For whom
- Companies with a mature IT perimeter and their own infrastructure.
- How it works
- The customer provides servers, access and network. We deploy the agent inside. Responsibilities are fixed in advance.
- Pros
- Maximum control over data. Easier to pass internal security requirements.
- Limitations
- Harder to coordinate. Depends on the customer's IT processes. Slower launch.
Fully closed perimeter
- For whom
- Large enterprises, regulated industries, projects with closed data and a ban on public models.
- How it works
- Servers are purchased by the customer. Agent in a closed perimeter. Only local models: ours or fine-tuned. Roles, audit logs, SLA, monitoring, backups.
- Pros
- Full control. Compliance with internal security requirements. Model fine-tuning for the customer is possible.
- Limitations
- More expensive and slower. Requires the customer's IT team. Separate technical design phase.
Cheatsheet · how to pick a format
In reality we discuss the format on the first call: after we understand the process and requirements. Not the other way around.
Four model options: and tokens aren't hidden.
The most frequent question on the first call: «Are you on ChatGPT?». The answer: «it depends». In production deployments a single model is rarely used: more often it's a combination of 2–3 for different tasks.
External paid models
Fast start, maximum quality
OpenAI, Anthropic Claude, Google Gemini. A working option when you need launch speed, there's no ban on external LLMs and data is processed under agreed rules.
- Billing
- Customer pays the provider directly
- Control
- Limits, spend monitoring, prompt optimization
- Jurisdiction
- US, EU
Different tasks within one agent may use different models: GPT-4 for complex reasoning, Claude Sonnet for documents, Gemini Flash for fast classification.
Russian corporate
Jurisdiction and a clear perimeter
GigaChat, YandexGPT and similar. Fit when there are jurisdiction requirements and you need a corporate contour with a clear contract.
- Billing
- Russian invoicing, pay-per-token
- Quality
- Comparable on typical tasks, weaker on complex ones
- Jurisdiction
- Russia
Critical for corporate customer accounting and for compliance with Russian data law 152-FZ.
DevNeuroX local models
No dependency on external APIs
Open-source models (Llama, Qwen, Mistral and similar) that we deploy and maintain on our infrastructure.
- Billing
- May be included in the 40K/mo maintenance within a limit
- Control
- Predictable cost: no token billing
- Jurisdiction
- Our infrastructure (RU)
Big practical advantage: counted in requests per month, not tokens per week. If volume grows: exceeds the limit: we revisit maintenance, without surprises.
Local models at the customer
Enterprise and fine-tuning
When format D (Enterprise on-prem) is chosen, the model is deployed on the customer's infrastructure. Requires GPU servers or an agreed private cloud.
- Billing
- Only our work on the agent layer
- Control
- Full independence, the model stays with you
- Jurisdiction
- Customer's perimeter
Customer fine-tuning is possible here: see below.
Enterprise · model fine-tuning for the customer
Fine-tuning on your data: faster response and higher quality in your domain.
In format D fine-tuning is possible: training a model on your historical data. We fine-tune both our local model and open-source models inside your perimeter.
Faster response
the model is adapted to your domain, no need to explain context every time
Higher quality
internal jargon, standard templates, corporate terminology: the model already knows
Fewer «hallucinations»
the model has seen your documents during training, it doesn't make things up
Full independence
the model and the data stay with you
This is a separate engineering stage within an enterprise project: data preparation, training infrastructure, usually 2–4 weeks of work.
Where we stop a project: and why it's important to know upfront.
A good vendor must be able to say “this should not be done”. Below are situations where we won't sell an agent until the proper base exists.
We don't take processes without an owner on the customer side. If there's no person on the team who can say «this is right, this isn't»: the agent will turn into a noise generator. This isn't about customer laziness, it's an engineering necessity: machine learning requires human feedback to improve quality.
We start with a business task, not AI itself: A defined process and a measurable result are required before work starts. A request to deploy AI and see what happens provides no decision criterion. We do not launch the first contour until value is defined.
We quote percentages after measurement: We agree the metrics before development and measure them on the real process. An agent may handle 80% of routine requests in one case and 30% in another. Either result can be successful, depending on the starting point.
A human approves critical actions: A human approves customer emails, payments and deal-stage changes. The agent prepares the action and submits it for review. This is our baseline production safety policy.
We don't process personal data via public LLMs without an agreed contour. Russia's 152-FZ isn't a formality, it's a real risk. If the task requires PII processing: we discuss format C or D with a contour inside Russia and Russian models or a local model.
Enterprise requires a separate project: The contour is designed around the organisation's infrastructure and security requirements. Another company's configuration cannot be copied without adaptation. We therefore begin with technical scoping.
Choose the format without unnecessary risk.
If the process is clear, we start with the first contour. If the task is mature, we estimate implementation. If a closed perimeter is needed, we start with technical scoping.
01 · First contour
Process is clear but it's unclear if AI will help
We start with a first working contour for one agent: pick a scenario, connect the needed data source, agree on a metric and test it on your real cases.
2–3 weeks · from 250K RUB
Review the metric →02 · Implementation
The task is already clear: needs to be done properly from the start
We move to implementation scoping: review process, systems, data, roles. Prepare architecture, working contour and launch plan.
1–2 months · from 500K RUB
Get an implementation estimate →03 · Enterprise
Closed perimeter, multiple systems or local models
This is an enterprise contour. We start with technical scoping of infrastructure and security requirements. Based on the scoping we propose architecture and an implementation roadmap.
No «N thousand» estimate: this isn't calculated that way
Request technical scoping →Not sure which format fits? Describe the process in the form below. We'll reply where there is fast effect, where diagnosis is needed, and where an agent won't pay off now.
Training after launch
Your team should be confident with the new tool
After launch, we teach the process owner and the team to manage scenarios, give useful feedback and catch errors before they become routine.
See training optionsWe'll review the process, metric and first agent
We reply during business hours. On the first review we'll say where an agent can pay off, which metric proves it, and where budget is better not spent.