You will get a cap on what your team spends on AI, per person, before the bill
Project details
Your AI bill grows every month and nobody can tell you who is spending what.
The two usual answers are both bad: thirty separate subscriptions with no visibility, or one shared API key where a single runaway script bills the whole company.
This is the third answer. One vendor contract, one key per person, a ceiling nobody can cross.
FOUR CONTROLS
One key per employee, so every request is attributable to a person and a department. Model access tiered by role, usually the largest saving and it needs no behaviour change from anyone. A rolling budget enforced BEFORE the request goes out. And the running cost on each answer, so people connect their own habits to the bill.
Over budget returns a clean 429 naming the amount, the window and when access returns. Not a truncated answer, not a silent downgrade, not a timeout.
WHAT I WILL NOT DO
I will not quote you a savings percentage before seeing your usage. The break-even between metered access and per-seat pricing swings widely depending purely on how long your conversations run, so anyone quoting a number upfront is guessing.
I also do not resell AI access. Everything routes through YOUR vendor account under YOUR contract.
The two usual answers are both bad: thirty separate subscriptions with no visibility, or one shared API key where a single runaway script bills the whole company.
This is the third answer. One vendor contract, one key per person, a ceiling nobody can cross.
FOUR CONTROLS
One key per employee, so every request is attributable to a person and a department. Model access tiered by role, usually the largest saving and it needs no behaviour change from anyone. A rolling budget enforced BEFORE the request goes out. And the running cost on each answer, so people connect their own habits to the bill.
Over budget returns a clean 429 naming the amount, the window and when access returns. Not a truncated answer, not a silent downgrade, not a timeout.
WHAT I WILL NOT DO
I will not quote you a savings percentage before seeing your usage. The break-even between metered access and per-seat pricing swings widely depending purely on how long your conversations run, so anyone quoting a number upfront is guessing.
I also do not resell AI access. Everything routes through YOUR vendor account under YOUR contract.
AI Algorithms
Large Language ModelAI Applications
AIOpsAI Models
ChatGPT, GPT-4What's included
| Service Tiers |
Starter
$290
|
Standard
$890
|
Advanced
$1,900
|
|---|---|---|---|
| Delivery Time | 1 day | 8 days | 18 days |
Number of Revisions | 0 | 2 | 3 |
AI Model Integration | - | ||
Batch Normalization | - | - | - |
Database Integration | - | - | - |
Detailed Code Comments | |||
Image Upscaling | - | - | - |
MLOps | - | - | - |
Model Deployment | - | - | - |
Model Documentation | - | - | - |
Model Monitoring | - | - | - |
Model Testing & Optimization | - | - | - |
Model Tuning | - | - | - |
Natural Language Processing | - | - | - |
NLP Tokenization | - | - | - |
Pre-Training | - | - | - |
Prompt Engineering | - | - | - |
Setup File | |||
Source Code |
Frequently asked questions
About TJ
AI Infrastructure - Internal Knowledge Bases & LLM Cost Control
Hanoi, Vietnam - 8:07 pm local time
I build the layer that fixes that, and I ship it as software you own and run yourself rather than a subscription you rent.
WHAT I BUILD
Internal knowledge bases with real permissions. Staff read them in a browser; their own AI reads them as native tools over MCP (Claude, Cursor) or an OpenAPI action (ChatGPT). Two permission gates are evaluated server-side, so a leaked token still cannot read past its owner. Handles .docx, .xlsx, .pptx and PDF, and searches accented languages correctly.
LLM cost control gateways. One vendor contract, one API key per person, model access tiered by role, and a rolling budget enforced before the request goes out rather than discovered on the invoice. Plus the admin dashboard finance needs to reconcile against the vendor's own console.
The automation around both: marketplace and ERP integrations, scheduled reporting, document pipelines, and browser automation for platforms with no usable API.
HOW I WORK
Fully asynchronous. Written updates, no standing meetings required. Every change ships with a backup and a before/after comparison, and I report what broke as plainly as what worked.
I will not quote you a savings percentage before seeing your usage, and I do not resell AI access. Everything routes through your own vendor account under your own contract.
Stack: Node.js, Python, SQLite, Linux, Nginx, Cloudflare, Firebase, Vercel.
I would rather show you a working system than describe one. There are live demos in my portfolio. Click into them, they run in your browser.
Steps for completing your project
After purchasing the project, send requirements so TJ can start the project.
Delivery time starts when TJ receives requirements from you.
TJ works on your project following the steps below.
Revisions may occur after the delivery date.
Read the usage first, set policy second
Your usage decides the policy, not the other way round. Which roles get which model, what a sensible per-person ceiling looks like, and how long the rolling window should be. You approve the numbers before anything is enforced.
Deploy, issue keys, then prove the ceiling holds
Gateway goes up on your server, one key per person, dashboard running. Then I spend a test budget to zero in front of you so you can see the 429 arrive with the amount and reset time on it, rather than a timeout.