> Markdown version of [/videos/1042-postgres-in-the-age-of-ai-and-devin?t=148](https://www.wearedevelopers.com/videos/1042-postgres-in-the-age-of-ai-and-devin?t=148). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Postgres in the Age of AI (and Devin)

Autonomous agents like Devin are taking over tedious database migrations. Learn to adapt your Postgres infrastructure for multi-agent systems and embrace the new AI-driven development lifecycle.

- **Speakers:** [Nikita Shamgunov](https://www.wearedevelopers.com/@nikita-shamgunov)
- **Event:** World Congress 2024
- **Published:** August 20, 2024
- **Duration:** 20:50
- **URL:** https://www.wearedevelopers.com/videos/1042-postgres-in-the-age-of-ai-and-devin

## Summary

The rapid evolution of AI software engineers like Devin is transforming how developers approach complex tasks such as database migrations. By guiding an autonomous agent through a hands-on migration from MongoDB to a relational Postgres schema, developers can observe the AI autonomously read API documentation, debug installation errors, and submit comprehensive pull requests. This dynamic shifts historically tedious technical operations into automated workflows, requiring human intervention primarily for strategic prompting and minor unblocking.

As autonomous tools assume more direct coding responsibilities, traditional developer experience requirements are morphing into an "AI experience" (AX). Infrastructure must adapt to accommodate multi-agent systems by offering serverless scalability, sub-second provisioning, and isolated testing environments. Platforms that decouple storage from compute allow AI bots to rapidly test schema changes, execute commands in parallel, and experiment within isolated database branches without risking production state or incurring idle resource costs.

Ultimately, the baseline definition of a technologist is expanding from a solo human developer to a "human leveraged by AI." With AI handling the repetitive heavy lifting of schema normalization and driver configuration, engineering teams can reallocate focus toward broader product logic. Ensuring underlying stateful data layers are instantly provisionable, stateless, and infinitely scalable is now a fundamental prerequisite for supporting an AI-driven development lifecycle.

**Keywords:** serverless postgres, mongodb to postgres migration, devin AI software engineer, database branching, stateful infrastructure previews, AI experience, multi-agent coding systems, schema normalization workflows, isolated preview environments, cloud native database storage, automated pull request generation, stateless database compute, AI-driven application development

## Chapters

1. **Rapidly provisioning serverless Postgres instances with Neon** (00:03) — Spinning up a serverless Postgres database instantly accelerates rapid application development.
1. **Migrating existing applications from MongoDB to Postgres** (02:28) — Assessing the complexity of transitioning an existing MongoDB application to a relational Postgres schema.
1. **Automating database migration tasks using Devin AI** (04:30) — How an AI software engineer automatically generates pull requests to move a collection to normalized relational tables.
1. **Prompting AI agents for successful application infrastructure changes** (08:42) — Refining prompts effectively guides AI tools in discovering APIs and generating correct migration logic.
1. **Analyzing autonomous AI planning and error recovery workflows** (10:49) — Following a multi-agent system as it encounters provisioning errors, debugs logs, and autonomously completes database tasks.
1. **Aligning serverless infrastructure properties with AI agent requirements** (13:43) — Why autoscaling compute and database branching are crucial when AI agents autonomously manage stateful deployments.
1. **Leveraging AI agents as iterative software engineering tools** (16:31) — Overcoming the learning curve of autonomous agents allows teams to offload routine infrastructure maintenance.
1. **Shifting emphasis from developer experience to AI experience** (18:01) — Adapting infrastructure to provide rapid provisioning and isolated test environments ensures bots operate efficiently and safely.
1. **Making Postgres databases stateless using cloud-native storage systems** (19:10) — Decoupling storage from database compute enables rapid horizontal scaling and instant preview instances.

## Related Moments

- [Shifting developer workloads and realistic AI productivity gains](https://www.wearedevelopers.com/videos/1830-wearedevelopers-live-speculaitions) (from "WeAreDevelopers LIVE - SpeculAItions")
- [Transitioning software engineering teams to AI-native development workflows](https://www.wearedevelopers.com/videos/100087-ai-ready-what-enterprise-transformation-actually-takes) (from "AI-Ready? What Enterprise Transformation Actually Takes")
- [The transforming role of developers in the AI era](https://www.wearedevelopers.com/videos/100337-user-1st-technology-2nd-stop-building-ai-nobody-uses-start-delivering-real-business-outcomes) (from "User 1st! Technology 2nd! Stop building AI nobody uses - start delivering real business outcomes")
- [Developer role changes in the AI era](https://www.wearedevelopers.com/videos/100281-why-your-codebase-lies-to-ai) (from "Why your codebase lies to AI?")
- [Using artificial intelligence to reimagine developer experience](https://www.wearedevelopers.com/videos/1546-ai-pair-programming-with-github-copilot-at-sap-looking-back-looking-forward) (from "AI Pair Programming with GitHub Copilot at SAP: Looking Back, Looking Forward!")
- [Leveraging artificial intelligence to accelerate system migration](https://www.wearedevelopers.com/videos/1444-crew-management-system-for-airlines-plan-duties-for-pilots-flight-attendants-worldwide) (from "Crew Management System for Airlines: Plan duties for pilots & flight attendants worldwide")

## Related Articles

- [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development)
- [Navigating the AI Shift](https://www.wearedevelopers.com/magazine/629-navigating-the-ai-shift)
- [Exploring AI: Opportunities and Risks for Developers](https://www.wearedevelopers.com/magazine/522-exploring-ai-opportunities-and-risks-for-developers)
- [Stephan Gillich - Bringing AI Everywhere](https://www.wearedevelopers.com/magazine/489-stephan-gillich-bringing-ai-everywhere)

## Related Jobs

- [Principal Software Engineer, Enterprise AI Platform](https://www.wearedevelopers.com/jobs/ext/1467292-principal-software-engineer-enterprise-ai-platform) at **GitHub**
- [Staff Software Engineer, Copilot Experiences](https://www.wearedevelopers.com/jobs/ext/164361-staff-software-engineer-copilot-experiences) at **GitHub**
- [AI Software Engineer (Germany)](https://www.wearedevelopers.com/jobs/48317-ai-software-engineer-germany) at **Sunhat**
- [Senior AI Agent Software Engineer (Go, Python) (m/f/x)](https://www.wearedevelopers.com/jobs/48277-senior-ai-agent-software-engineer-go-python-m-f-x) at **Dynatrace**
- [Principal Engineer - AI Search & Vector Infrastructure](https://www.wearedevelopers.com/jobs/ext/353953-principal-engineer-ai-search-vector-infrastructure) at **Redis**
- [AI Full Stack Engineer](https://www.wearedevelopers.com/jobs/ext/1354435-ai-full-stack-engineer) at **Almedia**