{ "@context": "https://schema.org", "@type": "Person", "name": "Semmal Palanisamy", "jobTitle": "Technical Product Manager, AI", "email": "semmal5002@gmail.com", "url": "https://semmal.one/", "sameAs": [ "https://www.linkedin.com/in/semmal-p", "https://github.com/semmal-dev" ], "address": { "@type": "PostalAddress", "addressLocality": "Bengaluru", "addressCountry": "IN" }, "description": "I can build what I spec: prototypes, architecture reviews and eval harnesses, so decisions move at the speed of evidence.", "openTo": [ "Senior AI PM & Technical PM roles", "Bengaluru, or fully remote" ], "bestFitFor": [ "0→1 AI / LLM products", "AI quality, evals & trust", "Platform & integration bets", "Growth & monetization features" ], "experienceYears": { "building": 7, "seniorEngineerOrTechnicalPM": 5 }, "caseStudies": [ { "code": "PRD-001", "title": "GenAI analytics for a 3,400-location supply chain", "status": "Shipped", "organization": "CanPrev (health & wellness supply chain, acquired by Apotex, Feb 2025) · via Trigent", "period": "Sep 2025 — present", "role": "Technical PM + architect. Owned the shipment platform as engineer and product owner.", "problem": "Ops and finance ran on spreadsheet reporting that took days.", "whatWasDone": "Shipped a GenAI analytics layer that turns shipment, inventory and fulfillment data into natural-language insights, with a quality bar and validation checks.", "outcomes": [ { "value": "Days → hours", "label": "operations reporting time" }, { "value": "Trusted", "label": "summaries used without manual re-verification" } ], "url": "https://semmal.one/#case-canprev", "markdown": "https://semmal.one/work/prd-001.md" }, { "code": "PRD-002", "title": "Compliance Copilot: grounded AI with a human in the loop", "status": "Shipped", "organization": "Public School Works (K-12 EdTech compliance) · via Trigent", "period": "Oct 2024 — Sep 2025", "role": "Architected the agent and its workflows; set PRD standards for the engineering team.", "problem": "US K-12 institutions reviewed regulatory documents by hand, and every decision had to stay traceable and auditable.", "whatWasDone": "Architected a RAG agent that extracts and classifies regulatory clauses, handles routine cases autonomously and escalates the risky ones to people.", "outcomes": [ { "value": "↓", "label": "manual compliance-document review time" }, { "value": "+50%", "label": "engineering throughput (AI-assisted docs, standardized PRDs)" }, { "value": "−30%", "label": "technical debt, with NPS up (“Stability First” roadmap)" } ], "url": "https://semmal.one/#case-copilot", "markdown": "https://semmal.one/work/prd-002.md" }, { "code": "PRD-003", "title": "Native Zoom integration: +22% MRR in two quarters", "status": "Shipped", "organization": "Omnify (B2B SaaS for service businesses)", "period": "2021 — 2024", "role": "Owned 0→1 product and engineering end to end.", "problem": "Post-pandemic, customers needed to run services online, and the platform couldn’t host them natively.", "whatWasDone": "Owned a native Zoom integration from zero to one, product and engineering.", "outcomes": [ { "value": "+22%", "label": "MRR within two quarters" } ], "url": "https://semmal.one/#case-zoom", "markdown": "https://semmal.one/work/prd-003.md" }, { "code": "PRD-004", "title": "Omnify Payments & Credits: a new revenue stream", "status": "Shipped", "organization": "Omnify", "period": "2021 — 2024", "role": "Architected payments and the refund system; owned the product decisions.", "problem": "Merchants processed payments externally, so Omnify earned nothing on transactions, and refunds cost merchants cash.", "whatWasDone": "Architected native checkout on Stripe Connect and a wallet-based refund system with fraud-pattern detection.", "outcomes": [ { "value": "New", "label": "high-margin transaction-fee revenue stream" }, { "value": "+18%", "label": "ARPU / upsell conversion" } ], "url": "https://semmal.one/#case-payments", "markdown": "https://semmal.one/work/prd-004.md" }, { "code": "PRD-005", "title": "Enterprise SSO & RBAC: +30% enterprise adoption", "status": "Shipped", "organization": "Omnify", "period": "2021 — 2024", "role": "Engineered the architecture; owned the enterprise requirements.", "problem": "Enterprise buyers in the US and APAC needed SSO and granular permissions before they could adopt.", "whatWasDone": "Built multi-tenant SSO with granular role-based access control.", "outcomes": [ { "value": "+30%", "label": "enterprise-segment adoption (US & APAC)" } ], "url": "https://semmal.one/#case-sso", "markdown": "https://semmal.one/work/prd-005.md" }, { "code": "PRD-006", "title": "Activation: −40% onboarding drop-off", "status": "Shipped", "organization": "Omnify", "period": "2021 — 2024", "role": "Owned the analysis and the onboarding redesign.", "problem": "New users dropped off during first-time onboarding, and client onboarding was slow.", "whatWasDone": "Used Mixpanel cohort analysis to find the friction, redesigned onboarding, unified support tooling and automated first-response triage.", "outcomes": [ { "value": "−40%", "label": "activation drop-off" }, { "value": "↑", "label": "Day-1 retention" }, { "value": "−60%", "label": "client onboarding time" } ], "url": "https://semmal.one/#case-activation", "markdown": "https://semmal.one/work/prd-006.md" }, { "code": "PRD-007", "title": "15+ products, end to end", "status": "Shipped", "organization": "Independent (retail & service businesses)", "period": "May 2019 — Jan 2021", "role": "Sole engineer and product decision-maker.", "problem": "Small retail and service businesses needed digital products without a product team.", "whatWasDone": "Ran discovery, architecture, build and launch for 15+ products; built an inventory-synchronization engine with rules-based demand logic.", "outcomes": [ { "value": "15+", "label": "products shipped end to end" }, { "value": "−40%", "label": "manual operational overhead (retail clients)" } ], "url": "https://semmal.one/#case-freelance", "markdown": "https://semmal.one/work/prd-007.md" }, { "code": "SPEC-01", "title": "Spec: eval-first launch plan for an AI support-triage agent", "status": "Spec work (not shipped, no results claimed)", "organization": "Spec work, not shipped. Extends the first-response triage I automated at Omnify.", "period": "Spec · 2026", "role": "Written as the PM owning the agent’s launch.", "problem": "Rule-based triage misroutes long-tail tickets; an LLM agent could do better, but only if quality is measurable before launch.", "whatWasDone": "A launch plan where the eval set, rubric and gates are defined before the prompt is written.", "outcomes": [ { "value": "Spec", "label": "no shipped metrics: this is a plan, not a result" } ], "url": "https://semmal.one/#case-spec-evals", "markdown": "https://semmal.one/work/spec-01.md" } ], "competencies": [ { "id": "ship", "label": "Shipped LLM / GenAI products", "evidence": [ { "text": "GenAI analytics layer in production for a 3,400-location supply chain", "caseStudy": "PRD-001" }, { "text": "RAG compliance agent for US K-12 institutions", "caseStudy": "PRD-002" } ] }, { "id": "evals", "label": "Evals & AI output quality", "evidence": [ { "text": "Defined the accuracy, freshness and traceability bar for AI outputs, plus validation checks", "caseStudy": "PRD-001" }, { "text": "Grounded retrieval kept compliance answers traceable and auditable", "caseStudy": "PRD-002" }, { "text": "Spec: eval-first launch plan for an AI triage agent", "caseStudy": "SPEC-01" } ] }, { "id": "rag", "label": "RAG, agents & tool use", "evidence": [ { "text": "Architected a RAG agent with agentic, function-calling workflows", "caseStudy": "PRD-002" }, { "text": "API-driven LLM parsing pipeline for clause extraction and classification", "caseStudy": "PRD-002" } ] }, { "id": "trust", "label": "Trust, safety & human-in-the-loop", "evidence": [ { "text": "Escalated ambiguous and high-risk cases to human reviewers", "caseStudy": "PRD-002" }, { "text": "Validation checks so stakeholders trust AI summaries without re-checking numbers", "caseStudy": "PRD-001" } ] }, { "id": "discovery", "label": "Discovery & problem framing", "evidence": [ { "text": "Translated ops and finance leadership needs into scoped deliverables and success metrics", "caseStudy": "PRD-001" }, { "text": "Cohort analysis to locate onboarding friction", "caseStudy": "PRD-006" } ] }, { "id": "strategy", "label": "Roadmap, prioritization & PRDs", "evidence": [ { "text": "RICE prioritization with direct stakeholder input", "caseStudy": "PRD-001" }, { "text": "Data-backed PRDs with strict edge cases: +50% engineering throughput", "caseStudy": "PRD-002" }, { "text": "\"Stability First\" roadmap: −30% technical debt, higher NPS", "caseStudy": "PRD-002" } ] }, { "id": "metrics", "label": "Metrics, analytics & experimentation", "evidence": [ { "text": "−40% activation drop-off and better Day-1 retention via Mixpanel cohorts", "caseStudy": "PRD-006" }, { "text": "A/B testing and SQL in day-to-day decisions", "caseStudy": "PRD-006" } ] }, { "id": "business", "label": "Business impact & monetization", "evidence": [ { "text": "+22% MRR within two quarters from a 0→1 Zoom integration", "caseStudy": "PRD-003" }, { "text": "New transaction-fee revenue stream and +18% ARPU/upsell", "caseStudy": "PRD-004" }, { "text": "+30% enterprise adoption across US & APAC", "caseStudy": "PRD-005" } ] }, { "id": "platform", "label": "Platform & technical depth", "evidence": [ { "text": "FastAPI microservices integrated with a Laravel core via REST", "caseStudy": "PRD-001" }, { "text": "Stripe Connect payments infrastructure and wallet refunds", "caseStudy": "PRD-004" }, { "text": "Multi-tenant SSO with granular RBAC", "caseStudy": "PRD-005" } ] }, { "id": "leadership", "label": "Cross-functional leadership", "evidence": [ { "text": "Worked directly with client ops and finance leadership", "caseStudy": "PRD-001" }, { "text": "Aligned engineering, compliance reviewers and the client", "caseStudy": "PRD-002" } ] }, { "id": "zero", "label": "0→1 ownership in ambiguity", "evidence": [ { "text": "Owned the native Zoom integration from zero to one", "caseStudy": "PRD-003" }, { "text": "15+ products end to end as sole engineer and product lead", "caseStudy": "PRD-007" } ] } ], "judgment": [ { "decision": "Rules, not a model", "context": "Inventory for small retailers", "why": "Rules-based demand logic instead of a forecasting model. Owners needed something reliable and explainable they could run themselves.", "caseStudy": "PRD-007" }, { "decision": "Checks around the model", "context": "Supply-chain reporting", "why": "The AI drafts the insights; validation checks guard accuracy, freshness and traceability, so stakeholders use the summaries without re-checking the numbers.", "caseStudy": "PRD-001" }, { "decision": "A human, not autonomy", "context": "Compliance reviews for schools", "why": "The agent handles routine clauses; ambiguous and high-risk ones go to a reviewer. Automate the volume, not the liability.", "caseStudy": "PRD-002" } ], "challengesHeCanHelpWith": [ "Launch our first GenAI feature", "Our AI output isn’t trusted yet", "Scale a platform or integrations", "Grow revenue or activation", "Bring order to a chaotic roadmap", "Someone who can prototype, not just spec" ] }