Assistant Inside Your Product
An in-app assistant that knows your catalogue, your pricing rules and who the user is — so it answers about their order, not about the world in general.
We put AI inside the products you already run — your app, your website, your admin panel, your support inbox. Not a chatbot bolted onto a homepage. Features that read your own data, answer accurately enough to be trusted, and cost what you budgeted.
We do not sell you a platform to migrate onto. We add capabilities to the app, website or management software your team uses today — through the same APIs any other feature would use.
An in-app assistant that knows your catalogue, your pricing rules and who the user is — so it answers about their order, not about the world in general.
Retrieval over your contracts, manuals, price lists and past tickets, with a citation on every answer so staff can check the source instead of trusting a paragraph.
Incoming messages classified, routed and answered — either drafted for an agent to approve or sent automatically for the question types you decide to trust.
Invoices, contracts, delivery notes, ID documents and handwritten forms turned into structured fields and pushed straight into your ERP, CRM or accounting system.
Product descriptions, listings, SEO copy and Vietnamese–English translation generated in your tone of voice, with a review step before anything is published.
Search that understands what the customer meant rather than which keywords they typed, plus recommendations built from behaviour instead of a static rule table.
Call transcripts and summaries, voice notes turned into records, product photos tagged automatically, and visual checks that flag defects before shipping.
Multi-step tasks that actually call your systems: check stock, create the booking, issue the refund, update the record — each step logged and reversible.
The gain is rarely the novelty. It is the work sitting in a queue because a person has to read something, decide something routine, or retype what a document already says. That is a narrow target on purpose — and it is where the return is easy to measure.
We will say so during discovery, before you spend the budget. AI is a poor fit when:
In those cases we build the conventional feature instead — and you keep the budget for the use case that does pay.
We are not tied to one vendor. The model is chosen per task — a small fast one for classification, a stronger one for reasoning — and swapped when a better option appears, without rebuilding your feature.
AI projects succeed where the work is frequent, written down and tolerant of a review step. These six areas meet all three conditions.
Product questions answered on the spot, descriptions generated for thousands of items, and search that finds what the customer meant.
Tickets classified and routed, replies drafted from your help centre, and a summary of the whole thread waiting for whoever picks it up.
Invoices and delivery notes read into your accounting system, contracts checked against a clause list, exceptions escalated to a human.
Policies, procedures and onboarding material answerable in one place — so the same question stops arriving in someone's inbox every week.
Campaign copy, social variants, SEO briefs and Vietnamese–English translation produced in your tone and reviewed before publishing.
Voice notes turned into job records, photos checked for defects, and daily reports written from the data your team already captures.
The stage most AI projects skip is evaluation. We put a number on how often the feature is right before it reaches a customer — and you decide whether that number is good enough to launch.
We look for work that is frequent, written down and tolerant of review, then estimate the hours or the revenue at stake. Weak use cases get dropped here, not after the build.
What the feature is allowed to read, where that data lives, how it gets there, and which records must never leave your systems — agreed in writing with your side.
A working prototype plus a test set of real questions with known answers. You get a scored accuracy figure instead of a demo that happened to go well.
The feature built into your app, website or admin panel, with the human-in-the-loop step wherever an error would reach a customer or a ledger.
Spending caps, rate limits, caching, fallbacks when a provider is down, refusal rules for out-of-scope questions, and a deliberate attempt to break it before launch.
Live behind a staged rollout, with dashboards for quality, latency and spend. Prompts and model choice get retuned as usage teaches us what real users ask.
Prove one use case cheaply, ship the whole feature, or keep a team improving it every month. Pricing is quoted after discovery, so you never pay for scope we have not yet understood.
For teams who want evidence before they commit a budget to AI at all.
From prototype to a feature your customers or staff use every day.
For companies rolling AI across several departments rather than one feature.
The hard part of an AI feature is rarely the model call. It is the data, the integration, the permissions and the failure cases — which is ordinary software engineering, and it is what CTG has been doing for years.
No migration, no second system for your staff to learn. The feature appears inside the app, website or admin panel they already open every morning.
Every project ships with a test set and a score. When we change a prompt or a model, we re-run it — so improvements are proven and regressions are caught before your users find them.
Provider accounts and API keys in your company's name, business terms that exclude training on your data, and a written record of exactly what each feature is allowed to read.
Cheaper models for the easy nine tenths, caching for repeated questions, and hard spending caps — so the monthly bill is a number you approved, not a surprise.
Whichever fits the task, and often more than one in the same product. Classification and extraction run well on small, cheap, fast models; reasoning over a long contract needs a stronger one. We build the integration so the model is a configuration choice rather than something welded into your code, which matters because a better or cheaper option appears every few months. If you already have a provider contract, we work within it.
Not under the business terms we set up. The major providers exclude API data from training by default on their business plans, and we configure retention settings and sign the data-processing terms as part of the build. Where the data cannot leave Vietnam or your own network at all, we use a self-hosted open model instead and tell you honestly what capability you trade away for that.
We measure it rather than guess. Stage three produces a test set of real questions with known answers and a score you can see. Then we design around the remaining error: a human approves before anything reaches a customer or a ledger, the answer carries a citation the reader can check, and the feature refuses instead of inventing when it does not know. Any project where a wrong answer cannot be caught is one we would rather not build.
Two parts: the build, and the usage. Usage is billed per request by the provider and depends on volume, how much text each request carries and which model handles it — so we project it during the sprint using your real numbers, then reduce it with caching and by routing easy requests to cheaper models. Hard spending caps are part of stage five, so the bill cannot run away while you sleep.
Yes, with open models such as Llama or Qwen on your hardware or a private cloud. It is the right answer when data genuinely cannot leave your network. Be aware of the trade: you take on GPU cost and operations, and open models still trail the leading commercial ones on hard reasoning — though for extraction, classification and translation the gap is often small enough not to matter.
Almost never. In most projects the AI feature is a service your existing app calls, plus a screen or a panel in the interface you already have. If your current system has no API at all we build a thin one around it — which is usually worth having anyway, and is far cheaper than a rewrite.
Describe the work you would hand to AI and the system it lives in today. Within two working days you will get a written first opinion — whether it is a good fit, roughly what it would cost to run, and what we would build first. No obligation, no sales call required.