# Contact

> Start a conversation with Sailesh Dahal, AI Integration Consultant.

- Canonical: https://saileshdahal.com.np/contact
- Email: hi@saileshdahal.com.np
- LinkedIn: https://linkedin.com/in/saileshbro
- X: https://twitter.com/sail_sail30
- GitHub: https://github.com/saileshbro

---

## What to include

- What you are trying to do, in a sentence or two.
- What exists today: a product, a pile of documents, a workflow, or nothing yet.
- What "working" would look like, and roughly when you need it.

## What I can help you build

> Example briefs, not a record of past delivery. The shipped, checkable work is at https://saileshdahal.com.np/index.md.

- **AI where it already fits** (Start here): Summarise, classify, extract, draft. Wire a model into the workflow your team already runs (a support macro, a triage queue, a report that writes its own first draft) with a prompt you can read and a test that tells you when it drifts.
- **Ask your documents** (Start here): Retrieval over your own corpus: contracts, policies, tickets, wiki, PDFs. Chunking and embeddings tuned to your documents, hybrid search with a reranker, and every answer citing the passage it came from so a reader can disagree with it.
- **RAG that survives contact with real data** (Production): The version that holds up past the demo: incremental ingestion, freshness and permissions carried through the index, query rewriting, retrieval evals with real recall numbers, and a fallback that says "I do not know" instead of inventing a clause.
- **Agents with hands** (Production): Agents that act on your systems through typed tools and MCP servers (book, refund, update, escalate) with scoped permissions, idempotent actions, a full audit trail, and a kill switch. Human approval on anything expensive or irreversible.
- **Evals, guardrails and the release gate** (Production): A graded dataset built from your real traffic, an eval suite in CI that blocks a prompt or model change from shipping when quality drops, plus injection and PII checks, refusal behaviour, and per-request cost and latency budgets you can watch.
- **Your own inference stack** (Deep end): When the API bill or the data boundary stops making sense: open-weight models served on your own GPUs, quantisation and batching sized to your traffic, LoRA fine-tunes on your data, and a routing layer that sends the easy 80% to the small model. The fine-tuning and quantisation half of this is thesis work I can show; no specific serving stack is named here because that choice depends on your hardware.
- **Multimodal and voice** (Deep end): Vision, audio and documents in the same pipeline: read the invoice, watch the video, hear the call. Streaming speech in and out for a phone or in-app agent, with latency budgets that keep a conversation feeling like a conversation.
- **AI inside a mobile app** (Deep end): The part most teams underestimate: streaming into a React Native or Flutter UI, on-device and hybrid inference, offline behaviour, token cost per session, and a review-safe story for what the model can and cannot do on a user’s phone.

## How I work with teams

- **AI opportunity audit**: Two weeks inside your product and your team’s workflows. You get a ranked list of where AI actually pays, with the cost, the failure modes and the eval you would need for each, plus an honest list of where it does not.
- **Build the first integration**: One workflow, taken all the way to production: retrieval, prompts, tool calls, an eval suite that gates deploys, cost and latency budgets, and a human-in-the-loop path for the cases the model should not decide alone.
- **Agents and internal workflows**: Agents that touch your real systems through typed tools and MCP servers, with permissions, audit trails and a kill switch. Built so the interesting part is your data, not the plumbing.
- **Make your product legible to AI**: Structured data, markdown twins, llms.txt and in-page agent tools, so assistants describe your product correctly instead of guessing. This site is the reference implementation.