IT consulting · Lead qualification
A pilot plan for the visitor, a qualified lead for sales
We 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.
- Status
- In-house product
- Timeline
- 16 days to production, refinements through December 2025
- Stack
- React
- TypeScript
- Node.js
- PostgreSQL
- OpenAI GPT-4
- Docker + Traefik
The task
We needed to turn our own website visitors into qualified leads and show value before the first call. A contact form captures an email at best; an analyst’s consultation costs hours and does not scale. So we built a self-service tool for ourselves: a few minutes in, the visitor has a pilot plan and sales has a lead with context and the full conversation.
What we built
- Three steps instead of a form: contact details, business context, a chat with the agent. The contact is saved before the dialogue starts, so the lead survives even if the visitor drops out.
- The agent runs under a business-analyst role prompt and sees the profile, context and full conversation. The model key stays on the server and never reaches the browser.
- The output is a strictly typed report: quick wins, pilot plan, KPIs, risks, next steps, summary. An incomplete model response never breaks the UI; missing blocks are simply omitted.
- The report exports to PDF, Excel and JSON; the session survives a page reload. The lead, with context and funnel status, lands in a built-in mini-CRM with an admin panel.
- Production setup: HTTPS on its own domain, one-script deploy with preflight and smoke checks, database and config backups with 30-day rotation. A 2 CPU / 2 GB server is enough.
Outcome
- 1 day
- to build a working MVP: frontend, backend and deploy configs
- 16 days
- from first commit to production with HTTPS and an issued certificate on its own domain
- 6 blocks
- in the visitor’s report: quick wins, pilot plan, KPIs, risks, next steps, summary
- 3 formats
- for the report export: PDF, Excel and JSON, so the visitor takes the plan away
Services
AI agent development: the agent acts, people set the limits
AI agents · Assistants · Task automation
AI implementation for business: the process first, then the model
AI implementation · Process automation · Integration
Software product development: from prototype to live operation
Product development · SaaS and platforms · Backend, web, mobile
Infrastructure and DevOps that make production predictable
DevOps · Kubernetes · CI/CD · Observability
More cases
Aviation · aircraft components trading and MRO
PilotAircraft 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 productionA 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
Marketplace e-commerce · Sales analytics
In productionProfit per SKU across three marketplaces, checked against manual figures
Five seller accounts on WB, Ozon and Yandex Market merged into one SKU-level P&L. Variance from the client’s manual figures on a control SKU for one month: 0.00%.
- 0.00%
- variance vs the client’s manual benchmark across units, revenue, COGS, profit and margin for a control SKU over a month; the threshold was 1%
- 1.18M rows
- of sales across 5 accounts and 12 months processed; 10.7% were ordered and settled in different months
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 paybackDiscuss 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.