Aviation · aircraft components trading and MRO
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.
- Status
- Pilot
- Timeline
- two phases: the AI loop, then the deal-tracking system
- Stack
- n8n
- IMAP
- Telegram Bot API
- Google Sheets API
- React/TypeScript
- Supabase (PostgreSQL, RLS)
The task
Aircraft component procurement ran on email and spreadsheets: RFQs were parsed by hand, quotes compared manually, and five departments worked in parallel with no stage control or access rules. Delays are expensive here. An AOG request means a grounded aircraft, and every shipment needs FAA 8130-3, EASA Form 1 or COC paperwork checked and alternate P/Ns considered.
What we built
- We put an AI agent on the working mailbox. It reads incoming mail over IMAP and extracts component requests: P/Ns, alternates and analogs across Rotables, Expendables and LLP.
- The agent collects supplier quotes, compares price, lead time and terms, verifies trace documents and notifies the team in Telegram. This loop ran on a live procurement process.
- Industry rules are built in: AOG priority, exchange programs, Incoterms and logistics. Without them, comparing aviation quotes makes no sense.
- We designed a deal-tracking system for procurement. Each deal passes mandatory stages (manager, procurement, logistics, customs, finance), with stage order and role access enforced at the database level.
- We built and deployed a working interface prototype: 11 screens, 6 roles, an order audit log, a full-text parts catalog and management analytics.
Outcome
- 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
- 6 × 6
- roles and deal stages in the deal-tracking system. Stage order and access are set in the database schema; counted from the prototype code
- 11
- screens in the working prototype, from the order card with action history to management analytics; counted from the code
Services
More cases
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
IT consulting · Lead qualification
In-house productA 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.
- 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
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.