A LatAm EdTech Leader Cut PR Review Time 20% Post-Merger

After growth-by-acquisition scattered engineering practices, the company's dev teams standardized how AI coding agents ship code, cutting PR review time and slashing reverts 65%.

20%

Cut PR review time

Implementation Time

Aanikh Kler

Lazer Technologies | Co-Founder Surf (acquired) | Canada's Young Entrepreneur of the Year 2023

Lazer Technologies

Connect ↓

The Challenge

One of Latin America's largest education technology companies had grown through rapid M&A, leaving engineering practices fragmented across multiple codebases. Some developers used coding tools like Cursor and Claude, but only for basic cases, and there was no standardized way to deploy AI agents across the company's repositories. Leadership, connected to Lazer through the company's private equity partner, wanted to lift engineering throughput and quality without a disruptive reorganization.

What They Built

Lazer embedded a senior forward-deployed engineer directly into the client's team. The first weeks established the foundation: onboarding into the company's systems, a technical audit, KPI definition with leadership, and a weekly delivery cadence. An L&D plan was built to raise the broader team's velocity on agent-assisted work, including hands-on sessions that the client team embraced.

The core technical deliverable is a package for the company's repositories that lets AI agents be deployed in a standardized way across its post-M&A codebase sprawl, turning ad-hoc individual tool usage into an organizational capability. A ticket-to-PR agent is live in the cloud, with one-click ticket delegation from the company's project management system rolling out next. The engagement was extended beyond its original scope on the strength of the results.

Lazer embedded a senior forward-deployed engineer directly inside the client's team rather than delivering from outside. The first weeks focused on foundations: onboarding into the company's systems, running a technical audit of the fragmented post-acquisition codebases, defining KPIs with leadership, and setting a weekly delivery cadence. In parallel, the engineer designed a learning-and-development plan to raise the wider team's velocity on agent-assisted work, running hands-on sessions that developers adopted. The central build was a deployment package that lets AI coding agents run in a standardized way across the company's many repositories, converting scattered individual tool use into a repeatable organizational capability. On top of that package, the team stood up a ticket-to-PR agent hosted in the cloud, and is now rolling out one-click ticket delegation from the company's project management system. Decisions throughout favored measurement and adoption over imposition: KPIs made the change visible, and enablement ensured the gains would hold after the engineer rolled off. The engagement was later extended beyond its original scope.

AI Role

Coding agents are deployed in a standardized way across the company's repositories through a Lazer-built package, with a cloud-hosted agent that picks up tickets and produces pull requests autonomously. The embedded FDE pairs the tooling with team enablement so the velocity gains hold after rolloff.

AI Model

To be confirmed

Infrastructure

Cloud-hosted ticket-to-PR agent • Standardized agent-deployment package across internal repositories

Integration Points

Internal repository ecosystem; CI/CD workflows • Linear ticket delegation (rolling out)

Impact

20% Improvement in PR Review Time

Standardized agent deployment and workflow changes cut the time pull requests spend in review across participating teams.

65% Improvement in PR Revert Rate

Fewer shipped changes get rolled back, indicating the AI-assisted workflow raised quality alongside speed.

Ticket-to-PR Agent Live in Production

An autonomous agent now converts tickets into pull requests in the cloud, with one-click delegation from the project management system rolling out next.

Technology Utilized

Implementation Complexity

Time Savings

Cost Reduction

Best Fit For

Companies that have grown through acquisition and need engineering standardization and AI-agent leverage across fragmented codebases, particularly PE portfolio companies under productivity mandates.

Aanikh Kler

Lazer Technologies | Co-Founder Surf (acquired) | Canada's Young Entrepreneur of the Year 2023

Lazer Technologies

Award-winning entrepreneur and tech leader helping startups and global brands like Netflix and Amazon drive growth by ethically harnessing consumer data and AI-driven innovation.

Get an intro

Industry:

Education & EdTech

Business Function:

Product & Engineering

Company Size:

1,001-5,000

Project Cost:

Cost not disclosed

Ownership:

Private Equity-Backed

Organization Type:

Private Company

AI Pattern:

AI Workforce Enablement

AI-Accelerated Custom Software

Value Type:

Time Savings

Cost Reduction

AI Model:

Frequently Asked Questions

How did a LatAm EdTech company reduce PR review time with AI coding agents?

The company embedded a forward-deployed engineer who built a package to deploy AI coding agents in a standardized way across its fragmented post-acquisition codebases. Combined with workflow changes, this cut the time pull requests spent in review by 20%.

What AI tools and approach were used to standardize the engineering workflow?

Developers used AI coding agents such as Claude Code, Cursor, and Codex within their workflows, unified by a standardized agent-deployment package across repositories. A cloud-hosted ticket-to-PR agent and Linear ticket delegation extended the approach.

What results did the AI coding-agent deployment achieve?

PR review time improved by 20% and the PR revert rate improved by 65%, indicating higher quality alongside speed. A ticket-to-PR agent is now live in production, with one-click ticket delegation rolling out next.

How long did the AI coding-agent rollout take?

The first weeks covered onboarding, a technical audit, KPI definition, and a weekly delivery cadence, after which the deployment package and workflow changes rolled out. The engagement was later extended beyond its original scope; a full timeline was not disclosed.

Who is standardized AI coding-agent deployment best suited for?

It fits companies that have grown through acquisition and need engineering standardization and AI-agent leverage across fragmented codebases, particularly private equity portfolio companies under productivity mandates.