AI-Assisted Software Development at Scale

Personally built the infrastructure and scaled AI coding tools to 800 engineers in 6 months

Overview

I led the AI-assisted development program that brought Amazon Q Developer and Kiro to 800 engineers in six months. I personally built Terraform/AWS infrastructure and paired technical implementation with rollout planning and company-wide enablement. The work grew from infrastructure and access workflows into team-specific context, practical workshops, and parallel AI-assisted development workflows within the Agentic AI group.

Results

  • AI-assisted development rollout reached 800 engineers in six months
  • Agentic AI group reached the department’s #1 AI-assisted development adoption position
  • My own team tripled its delivered feature scope over one year, measured in developer-weeks of work and total team output
  • “Context is King” workshops developed with partners across three groups
  • Appian Impact Award in December 2025 for cross-organizational AI adoption
  • Program became a model for how Appian rolls out new developer tooling

My Contribution

My work combined hands-on infrastructure, collaborative deployment controls, and practical enablement:

  • AWS Infrastructure (Terraform): Personally built Terraform/AWS infrastructure for the AI-assisted development program. Co-developed controls separating shared development state from an isolated production state backend.
  • CI/CD Deployment Controls: Co-developed configuration for local development workflows with shared S3/DynamoDB state and merge-triggered GitLab CI/CD using an isolated production backend.
  • Cost Management: Investigated subscription and user-deactivation workflows and documented the manual process. This work clarified how access and license management should support the rollout.
  • Adoption Tracking: Investigated how to connect activity telemetry with user and team information. Documented a proposed AWS data-enrichment pipeline to make adoption patterns easier to understand; this proposal was separate from the infrastructure I personally implemented.
  • Group Configuration: Worked through group-based access and subscription-management requirements for Amazon Q, connecting rollout needs with identity and team-level controls.
  • Company-Wide Enablement: Delivered 3 Appian Talks driving adoption:
    • "Releasing Amazon Q" — Initial rollout announcement and onboarding
    • "Make Boring Less Boring with Q" — Practical use cases and productivity tips
    • "Context is King: Build Your Own Custom Assistant for Your Team" — Advanced usage, custom assistants, team-specific configurations
  • “Context is King” Workshop: Designed a hands-on workshop and partnered across three groups to teach team-specific context for AI coding assistants, including codebases, architecture documentation, and testing patterns. The sessions connected practical exercises with teams’ own engineering work and encouraged shared learning across groups.

Parallel AI-assisted development workflows in the Agentic AI group

I introduced parallel AI-assisted development workflows within the group, coaching teams on the effective use of agentic development tools to accelerate delivery. The practice connects parallel workstreams with shared API boundaries, contract-first and mock-first development, and daily hands-on use of AI tools.

Over one year, my own team tripled its delivered feature scope — measured in developer-weeks of work taken and in the team's total output. That is a team-scoped result for the group I lead, not a department-wide figure, and it describes growth in the scope of work delivered rather than individual engineers executing three times faster.

During 2026, I combined that coaching with delivery-confidence assessments, capacity-gap analysis, and investment in team cohesion and knowledge sharing. The company-wide rollout put AI tools in engineers’ hands; the group’s workflows bring those tools into everyday planning, implementation, and collaboration.

See how the approach connects to Agent Studio delivery →

A longer history of engineering enablement

The three Appian Talks extended an earlier commitment to teaching: AWS hands-on labs and internal machine-learning sessions for cloud engineers, a week-long Cloud internship training program, and the three-week Site Reliability Academy. Each paired shared technical foundations with practical work in the team’s domain.

Impact Award

Engineering Department Head presenting the Impact Award for driving cross-organizational AI adoption.

© 2025 Sahil Gupta. All Rights Reserved.