{"$schema":"https://raw.githubusercontent.com/jsonresume/resume-schema/v1.0.0/schema.json","basics":{"name":"Abhinav Bansal","label":"The Tech Plumber","subline":"Wherever engineering leaks, I go in, then build the team and the tools so it stays fixed. Test automation, then modernization at scale, now AI agents.","email":"abhibansal60@gmail.com","url":"https://abhibansal.dev","summary":"Vice President at Morgan Stanley leading engineering teams through agentic AI adoption and tech modernization, after five years modernizing technology at scale across the firm's business units. Known as the Plumber: wherever something needs fixing, I go in. Strong Python engineer who builds multi-agent systems with LangChain, MCP and the Claude Agent SDK. I love building cookie-cutter tools that let every team start from a working pattern, and presenting them as a developer advocate. Came up through test automation and DevOps, and co-invented a patented test automation engine.","currently":"Leading agentic AI adoption at Morgan Stanley in Glasgow, and shipping tidy, an AI inbox cleaner that can't go rogue.","location":{"city":"Glasgow","region":"Scotland","countryCode":"GB"},"profiles":[{"network":"LinkedIn","username":"erabhinavbansal","url":"https://www.linkedin.com/in/erabhinavbansal/"},{"network":"GitHub","username":"abhibansal60","url":"https://github.com/abhibansal60"}],"nickname":"the Plumber"},"work":[{"name":"Morgan Stanley","position":"Vice President, AI Platform & Tech Modernization","location":"Glasgow, UK","startDate":"2024-12","summary":"Relocated to Glasgow to lead technology modernization under the firm's Refresh Tech strategy.","highlights":["Lead agentic AI adoption and literacy across engineering teams: developer advocacy programmes on agentic frameworks (LangChain, MCP, Claude Agent SDK) and LLM integration patterns","Build specialised agents for development workflows and DevOps operations","Drove Kubernetes and Docker adoption across development teams, with 30% faster deployment cycles","Give architectural guidance on multi-agent orchestration, developer tooling and LLM integration"]},{"name":"Morgan Stanley","position":"Vice President","location":"Bengaluru, India","startDate":"2024-01","endDate":"2024-12","highlights":["Led 5+ engineering teams through tech modernization, with a 40% improvement in deployment frequency","Led the ACT Conference Portal, recognised with the India Technology Showcase Award","Pioneered Kubernetes adoption with documentation and training that sped up adoption across the organization","Set up a formal mentoring programme; 3 mentees are now in advanced technical roles"]},{"name":"Morgan Stanley","position":"Senior Manager, DevOps","location":"Bengaluru, India","startDate":"2021-01","endDate":"2024-01","highlights":["Scaled the Engineer as a Service model: 35% faster modernization rollouts across business units","Reusable architecture patterns that cut time-to-market for new applications by 28%","DevOps and SRE practices with global teams: 45% fewer production incidents","Frameworks and tools used across the firm, improving quality metrics by 20%","Led the firm's Transformation network for DevOps practice adoption"]},{"name":"Morgan Stanley","position":"Manager, Test Automation","location":"Bengaluru, India","startDate":"2020-01","endDate":"2021-01","highlights":["Built an email-embeddable Cucumber reporting tool for QA teams","Built DevOps tooling and a worklog dashboard on the Bitbucket API, adopted by multiple teams"]},{"name":"Morgan Stanley","position":"Senior Associate, Test Automation","location":"Bengaluru, India","startDate":"2018-08","endDate":"2020-01","highlights":["Led a generic, organization-wide test automation framework from concept to code"]},{"name":"Infosys","position":"System Engineer","location":"Bengaluru, India","startDate":"2016-08","endDate":"2018-08","highlights":["Designed a UI automation framework in Java using the Reflection API","Built a report generation module with data cleansing that made the team 11 times more productive","Designed the frontend and REST API of the GST Refund Application","Clients: Telstra and the Government of India"]},{"name":"DollarsGPT.com","position":"Founder","startDate":"2013-05","endDate":"2015-12","summary":"Consumer rewards platform paying users in gift cards and cash for micro-tasks. Bootstrapped while at university.","highlights":["Grew from zero to 20,000 users with 1,500+ monthly actives through performance marketing and partner integrations","Ran the whole product: platform development, partner onboarding, payments and growth"]}],"highlights":[{"name":"Boardroom","summary":"A multi-agent orchestration system: three specialised agents and an orchestrator, built with LangChain and the Claude Agent SDK. It is the internal reference implementation for agentic AI at the firm."},{"name":"BLAZE (US patent, co-inventor)","summary":"BDD Lean Automation Zenith Engine: turns API specifications into executable Java test suites using behaviour-driven development."},{"name":"Internal events and conference platform","summary":"Built and evolved over 5+ years into the standard for global internal events. Added AI features: proposal submission and review with a recommendation engine for session curation, content filtering, and a Hacker News-style knowledge platform with AI ranking."},{"name":"AI developer tooling","summary":"A VS Code extension for in-place codebase review and modernisation, CLI skills for DevOps automation, and reusable skills infrastructure that cut onboarding and deployment tasks from days to minutes."},{"name":"Pull request chat","summary":"A chat bubble on the pull request page so authors can talk to reviewers in place, saving 375+ person-days of effort a year."}],"projects":[{"name":"tidy","kind":"python package","featured":true,"description":"Cleans up Gmail and YouTube subscriptions with AI without letting AI loose on your account. A small model judges each email; plain, tested code decides what that judgment may do; nothing risky happens until you approve.","highlights":["Sorted a 12,158-email backlog for about $0.43","Never deletes, never touches starred mail, never clicks unsubscribe links"],"keywords":["Python","Agents","Guardrails"],"url":"https://github.com/abhibansal60/tidy","install":"pipx install tidy-ai"},{"name":"ai-workbench","kind":"claude code skill","featured":true,"description":"A Claude Code skill that sets up a matching matrix-green and cyber-purple dev environment on Linux: prompt, terminal, editor, diffs and status line. No sudo; it reads your config before touching it.","keywords":["Claude Code","Skills","Linux"],"url":"https://github.com/abhibansal60/ai-workbench"},{"name":"awesome-copilot-toolkit","kind":"vs code extension","featured":true,"description":"A VS Code extension to browse and install custom instructions, prompts and chat modes from the github/awesome-copilot repository without leaving the editor.","keywords":["TypeScript","VS Code","Copilot"],"url":"https://github.com/abhibansal60/awesome-copilot-toolkit"},{"name":"macify","kind":"shell script","description":"Makes Ubuntu GNOME look like macOS in one command, with a one-command revert.","keywords":["Shell","Linux"],"url":"https://github.com/abhibansal60/macify"}],"awards":[{"title":"India Technology Showcase Award","awarder":"Morgan Stanley","summary":"For the ACT Conference Portal."}],"certificates":[{"name":"HashiCorp Certified: Terraform Associate (003)","issuer":"HashiCorp"},{"name":"Site Reliability Engineering (SRE)"}],"education":[{"institution":"Maharishi Markandeshwar University","studyType":"Bachelor of Technology","area":"Computer Science","startDate":"2012","endDate":"2016"}],"skills":[{"name":"Agentic AI","keywords":["LangChain","MCP","Claude Agent SDK","Anthropic and OpenAI APIs","Pipecat","Deepgram","Twilio"]},{"name":"Platform","keywords":["Docker","Kubernetes","AWS","Terraform","Jenkins","CI/CD"]},{"name":"Languages","keywords":["Python","Java","TypeScript","React","SQL"]},{"name":"Testing","keywords":["BDD","Cucumber","Selenium","TestNG"]},{"name":"Advocacy","keywords":["Developer advocacy","Presenting","Cookie-cutter tooling","Mentoring"]}],"languages":[{"language":"English"},{"language":"Hindi"}],"talks":[{"title":"Getting agents past the change board","summary":"What it takes to move agentic AI from demo to production in a regulated enterprise: guardrails, literacy programmes, and the reference implementations that make teams trust it."},{"title":"Your test suite was the first agent harness","summary":"Ten years of BDD and test automation taught the same lesson agents need now: put deterministic checks around the part you don't trust."},{"title":"Cheap judgments, expensive builders","summary":"Splitting work between a frontier model that writes the code once and a small model that makes thousands of decisions, with real cost numbers from tidy."}],"timeline":[{"year":"2013","stage":"bootstrap","name":"DollarsGPT","log":["Founded a consumer rewards platform while at university","Grew from zero to 20,000 users with 1,500+ monthly actives","Ran development, partners, payments and growth"]},{"year":"2016","stage":"build","name":"Infosys","log":["BDD frameworks with Selenium, Java and Cucumber","Clients: Telstra and the Government of India","A report module that made the team 11 times more productive"]},{"year":"2018","stage":"test","name":"Test automation","log":["An organization-wide test automation framework at Morgan Stanley","Email-embeddable Cucumber reporting for QA teams","Co-invented BLAZE: API specs in, Java test suites out (US patent)"]},{"year":"2020","stage":"modernize","name":"Tech at scale","log":["Five years modernizing technology across Morgan Stanley business units","Engineer as a Service: 35% faster modernization rollouts","Led 5+ teams to a 40% jump in deployment frequency","Cookie-cutter patterns and Kubernetes adoption: 28% faster time-to-market, 45% fewer incidents"]},{"year":"2024","stage":"release","name":"Agentic AI","log":["VP, AI Platform & Tech Modernization","Boardroom: multi-agent orchestration with the Claude Agent SDK","India Technology Showcase Award for the ACT Conference Portal"]}]}