Eleven years in product, the last three building agentic AI platforms that enterprises and their partners actually ship on: composable agent workflows at Aisera, and an MCP-based marketplace with 50+ agents and 20+ connectors serving 1M+ users at RingCentral.
Follow one request end to end. The console on the right replays a real workflow pattern; each step of the story lights up the part of the trace it describes.
No form, no ticket category, no "please select from the following." The agent takes the request as it is spoken and works out what is really being asked.
Which systems hold the answer, in what order to ask them, and what a good outcome looks like. The plan is visible, so a human can see the reasoning before anything happens.
Identity, endpoint, security, CRM, support, HRIS. Each call is scoped to what the requesting person is allowed to see, and each result is kept with its source.
This gate is the product. Routine, low-risk actions run. Privileged ones route to the right approver. Nothing ambiguous happens silently.
An account is unlocked, a brief is delivered, a laptop is ordered. The person is told what happened and why, and the trail is there for anyone who needs it later.
Most "AI assistants" stop at a chat window. The hard product work starts when the model has to read from ten systems, decide what to do, and be trusted to do it. That is the layer I own.
Composable, self-serve agentic platforms: at Aisera, System Integrators deployed custom multi-agent workflows without our engineers in the room; at RingCentral, a 144-tool marketplace is becoming a headless, API-first ecosystem for ISVs and consultants.
Agents are only as useful as what they can reach. I have shipped 20+ enterprise MCP connectors, the first six in a single quarter, and set the reference architecture third-party developers now onboard against, plus a management platform that meters and bills for what partners consume.
The work that gets an agent past the CISO and the CFO. An AI security agent that statically scans partner code and gates onboarding; telemetry that diagnoses agent behavior for partners; and a three-phase ROI system so GTM teams and resellers can report productivity in numbers.
Five products across two companies, one thread: give agents real access to enterprise systems, let partners build on them, and engineer the trust needed to let them act. Open any project for the full case study.
Working positions, earned from shipping. I am writing each of these up in more depth.
Thumbs-up rates and resolution counts drift away from real user value within weeks of launch, and the dashboards keep smiling. Agent products need a standing practice for detecting that decay, and a culture willing to reset the numbers when it happens.
An agent that does everything autonomously is a liability; one that asks permission for everything is a chatbot with extra steps. The design work is deciding, per action and per role, what runs, what asks, and what escalates.
Models are already capable enough for most enterprise workflows. What blocks deployment is who the agent is when it touches a system of record. Non-human identity, scoped service principals, and audit trails are where agent programs are won or stalled.
Eleven years across two continents: engineer, then product manager, then three years building agentic AI platforms that partners and enterprises ship on.
Own the strategic roadmap for AI Garage, moving a 144-tool AI marketplace to a headless, API-first ecosystem for 1M+ end users and 50+ ISV and consultant partners. Shipped 20+ enterprise MCP connectors, the first six in one quarter as the reference architecture for third-party developers, grew the catalog to 50+ agents, an AI security agent that gates partner onboarding (deployment friction down 35%), a three-phase ROI measurement system for GTM teams and resellers, an ecosystem-wide telemetry engine, and an MCP management platform with usage-based billing.
Owned execution of agentic AI platforms, delivering composable self-serve solutions that let System Integrators deploy custom workflows, driving $150M+ in mutual business value. Built analytics and feedback loops that cut abandonment 27% and let partners raise task success independently. Orchestrated multi-agent workflows and authored blueprints that reduced partner implementation time 42% and accelerated deal closure 26%.
Drove development and go-to-market of a digital learning platform MVP with analytics-driven cohort personalization.
Led a 29-person cross-functional team and ran 100+ customer interviews, lifting adoption and engagement 10%. Earlier, as an engineer, built AI-driven geo-fencing and automated content management modules for ManageEngine MDM, used by 500K+ enterprise users.
Students' Leader, Peer Career Consultant, and Teaching Assistant for Product Definition and Validation.
I am most useful on problems where the model is the easy part and the platform, partners, permissions, and proof of value around it are the hard part.