Transforming enterprise data platforms into trusted retrieval surfaces for AI agents.
Modernizing enterprise data platforms and making their data AI-ready. Governed context, semantic layers, and answers that cite their source.
Ayan Putatunda is a data engineer working on petabyte-scale platforms as retrieval surfaces for AI agents, where every answer traces back to a source. He also builds and ships products, and writes, speaks, and teaches about the practice.
- Data and AI platformsbuilt for production AI
- Petabyte scaleSnowflake, dbt, Airflow
- Keynotes and panelsindustry and university conferences
Building now
- contextctl: auditable, open-source context infrastructure for AI agentspaper under review, AAI-BD @ IEEE BigData 2026, decision Nov 12
- Axiomic AI: three live products on one open-source agent harnesspersonal projects
- Built from Bits learning platformlive
Selected work
Systems that run in production or are on their way there. Each case study explains the problem, the choices, and the numbers.
Skills-driven agentic data engineering
A governed library of AI skills and sub-agents that automates the analytics-engineering lifecycle across multi-repo dbt and ingestion workflows, with humans in the loop.
Autonomous incident response agent
Zero-touch detection, root-cause analysis, and auto-remediation of data pipeline failures using the Claude Agent SDK with Snowflake, dbt, and GitHub MCP servers.
contextctl: auditable context infrastructure for AI agents
A vision paper and open-source prototype arguing that agent context should be governed data infrastructure: open files for truth, Git for time, a hash-named evidence folder, one SQLite sidecar for speed, and a token-budgeted serving protocol. Under review at the AAI-BD 2026 workshop, IEEE BigData 2026; decision expected Nov 12.
Axiomic AI agent harness
The multi-agent repository template every Axiomic AI product is built from: agent prompts, MCP server configs, CI, and deploy wiring. Fork, describe the domain, ship.
Personal projects
Ayan's experimental, non-revenue playground for trying out new technology and deployment: one agent harness, three live personal projects.
Axiomic AI is a personal, non-revenue playground for trying out new technology and deployment, with agents doing most of the building. Every project runs on the same harness: a multi-agent repository template with agent prompts, MCP server configs, CI, and deployment wiring. A new project means fork the harness, describe the domain, ship. Three arms: Labs (product builds), Solutions (reference architectures and playbooks), Academy (tech education).
- PersonasFlowpersonasflow.com
- EstateVisionestatevision.io
- WealthPilotpilotmywealth.com
- Agent harnessopen source
Speaking
Keynotes, conference sessions, and invited panels on agentic data engineering and AI-ready data platforms, at industry summits and universities.
Step Inside the AI-Powered Enterprises
USF Enterprise AI Summit, University of San Francisco
Panel, Oct 30, 2026upcoming
Making a Data Platform AI-Ready
Applied AI Summit
Session, Oct 13–15, 2026delivered
What's New: Zero to a Trusted Semantic Layer in Snowflake
Snowflake World Tour, Chicago
Session and discussion, Oct 5, 2026delivered
Writing
Practical notes on MCP, agents, Claude Code, and the data platforms underneath them.
Teaching
Two YouTube channels and a learning platform.
Hands-on data and AI tutorials: Claude Code, MCP, agents, dbt, Snowflake. Also on Substack and Medium.
Conversations with people who ship data and AI systems for a living.
A structured learning platform for AI engineering fundamentals and applied builds, growing out of the Built from Bits channel. Course tracks on MCP, agents, Claude Code workflows, and AI-ready data platforms are being built now.