AI implementation: RAG, assistants, ERP

LLM gateway, budgets and eval

Teams blow the LLM bill and still cannot say whether last week's prompt change helped.

Discuss this directionContact form

Tell me the goal, stack constraints, and timeline — I reply on Telegram.

Teams blow the LLM bill and still cannot say whether last week's prompt change helped. This track is a gateway: one place to route models, cap tokens and money, log prompts (redacted), and run an evaluation harness. It is not data security (roles, on-prem, encryption)—that page stays the policy contour. It is not RAG. It is the control plane under assistants, RAG, and agents.

I implement a small service your apps call instead of scattering vendor SDKs: API keys in one vault, per-team quotas, fallbacks (provider down, rate limit), and traces you can join to a ticket ID. Quality work uses a frozen eval set—golden questions, expected citations, tool outcomes—not a founder clicking the chat once. Write-ups: LLM gateway and FinOps and AI evaluation harness. Broader quality notes: LLM quality testing 2026.

First slice: wrap one production path (internal FAQ or support draft) with budgets and a weekly eval job. Multi-region, multi-vendor beauty contests wait until you have numbers. On-prem models plug into the same interface when policy requires it.

Stack: TypeScript/Node.js gateway, Postgres for usage, optional Redis for rate limits. Python eval jobs if the rest of the ML contour is Python. Related portfolio: cursor-telegram-integration, thinklens-bot—both need cost and failure modes once they leave the demo.

Out of scope: buying GPU clusters “for independence,” or promising a 40% cost cut without a baseline week of logs.

Timeline: a usable gateway + first eval suite is often 3–7 weeks.

What you get

  • Single LLM entrypoint, keys, quotas, fallbacks
  • Redacted prompt/response logs with retention you approve
  • Eval set, scheduled run, and a short report format your lead can read
  • Runbook for rotating keys and raising a team cap

FAQ

Tap a question to expand the answer.

Will this lock us to one model vendor?

No. The point is to swap or route without rewriting every bot. The first vendor is whoever you already pay; we do not invent a second bill for sport.

Do you log full customer prompts?

Only with a written retention and redaction policy. Default is IDs, hashes, and truncated samples—not a searchable dump of PII.

Is eval the same as RAG tests?

RAG eval is retrieval + answer. Gateway eval is cost, latency, and regression across all LLM calls. They share fixtures when the product is a grounded assistant.

Discuss this directionContact form

Tell me the goal, stack constraints, and timeline — I reply on Telegram.

View full service page