§ 05 · Ask Kevin · AI assistant
Ask Kevin
AI answers based on my published work · You can check the sources
Ask KevinAI assistantThis session isn't saved · 7 case files
Ask Kevin · AI
Ask about Kevin's projects, how he works, or where an engagement starts. The answers use his published work and link to the source.
Recorded example · 2026-10-07One question · 3 sources, word for word · No hosted model
Specimen · Recorded run · 2026-10-07 · Corpus ca23fc2e · No generative model · Matching source passages, word for word
“We run Salesforce, three legacy databases, and our salespeople qualify RFQs by hand. What could Kevin build for us?”
EvidencedSimilarity 0.659 · Floor 0.55
No generative model · Matching source passages, word for word
- Kevin Fincel · What I buildSimilarity 0.659
I build AI agents, retrieval systems that find relevant information, and integrations with ERP, CRM, analytics and legacy software. I also build MCP servers, the connections that let AI use those tools. The work includes testing answers, access controls and human approval for sensitive changes.
- Kevin Fincel · Case 06 · AI-assisted ad changes with approval before every change · ProblemSimilarity 0.627
The team manages about 18 industrial-sector ad accounts. Agents can help with audits and campaign builds, but API changes affect live client spend. I needed a review process that made each change traceable and required a person to approve it before execution.
- Kevin Fincel · ThesisSimilarity 0.621
I want to work inside the problem. Before I build anything, I need to understand how the work gets done. I spend time with the people doing it, trace the information they rely on, and find where the process gets stuck. Then I work out what is worth building. As a Forward Deployed AI Engineer, I work inside your business to understand the workflow, build AI into your existing systems, and help your team use it. I handle the data connections and access rules, and stay involved through deployment and adoption. I build AI agents, retrieval systems that find relevant information, and integrations with ERP, CRM, analytics and legacy software. I also build MCP servers, the connections that let AI use those tools. The work includes testing answers, access controls and human approval for sensitive changes. We decide what the software can change on its own and what needs your team's approval. Then we test it. AI will get things wrong, and catching those mistakes is part of the work. I've been responsible for getting business systems into daily use for more than eighteen years. The tools have changed. I'm still accountable for whether the thing works.
This example was recorded at build time using the same model as the browser. It uses source passages word for word; no hosted model wrote the answer.
You can question any sentence and send it to Kevin for a reply.