AI Integration Consultant
Most AI projects die between the demo and the deploy. I work on the part after the demo: the retrieval that has to be right, the evals that gate the release, the guardrails and the audit trail, the cost per request.
The offer
Four shapes. Most engagements start with the first.
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 a list of where it does not.
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 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.
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.
Want the concrete version? RAG, agents, evals, self-hosted inference. Example briefs, cheapest to deepest
Open any of these and check it. Nothing here is a screenshot of a prototype.
Shipped, live and open to inspection. Entries marked LaunchBox were built at the studio where I am lead engineer; the rest I built outside it.
Marketing compliance for finance and iGaming. Ingest the policy documents, extract enforceable rules from them, then review copy, images, video and audio against those rules, with every verdict linked back to the clause it came from, with a full audit trail.
Nepal's home-services marketplace with 50+ services across Kathmandu, Lalitpur, Bhaktapur and Pokhara. Customer app, provider app and the booking platform behind them.
What I build
Where AI projects actually fail, and what shipped against each.
Contract record since February 2021: 32 contracts at 100% job success, one of them running 4,494 of the 4,963 hours. Open the profile and check it ↗
Issue 5. Qwen published two open-weight checkpoints (27B under Apache 2.0, 2.4T under a custom licence), OpenAI wrote up the controls behind its Astra pause, and GLM-5.3 got a primary source but its weights are still out. The hard number: OpenAI puts monitoring overhead at roughly 20 percent of the inference compute it watches.
AI Week issue 4: model choice now includes price, deployment, local runtimes and compute ownership alongside benchmarks.
AI Week issue 3: labs disclosed models reaching real companies, while new controls respond to rising cyber capability. What the incident numbers mean for builders.
AI agent security lessons from 2026 incidents: why eval harnesses failed, how real systems were reached, and what boards should change about AI controls.
AI Week issue 2: agent evaluations reached the real internet and one published malware to PyPI. The lesson is about threat-modeling AI eval harnesses.
1,771 merged pull requests across 78 repositories total, the six above are the only ones whose changes were substantive enough to list.
I help teams put AI into production.
