> Markdown version of [/videos/100261-building-an-agentic-software-factory-how-we-rebuilt-product-development-at-pipedrive](https://www.wearedevelopers.com/videos/100261-building-an-agentic-software-factory-how-we-rebuilt-product-development-at-pipedrive). 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).

---

# Building an agentic software factory: How we rebuilt product development at Pipedrive

Former CTO Agur Jõgi claims human attention, not coding, is engineering's ultimate bottleneck. See how Pipedrive automated friction with AI agents to transform developers into autonomous system managers.

- **Speakers:** [Agur Jõgi](https://www.wearedevelopers.com/@agur-jogi)
- **Event:** World Congress 2026 Europe
- **Published:** July 10, 2026
- **Duration:** 29:21
- **URL:** https://www.wearedevelopers.com/videos/100261-building-an-agentic-software-factory-how-we-rebuilt-product-development-at-pipedrive

## Summary

As Pipedrive scaled from a startup CRM into a global platform, its engineering challenges shifted fundamentally. Former CTO Agur Jõgi highlights that the ultimate bottleneck in modern software companies is no longer writing code or baseline capacity, but rather human attention. With business leaders demanding hyper-customer-centric developers and the rapid explosion of new frameworks, developer cognitive load has skyrocketed. Simply using artificial intelligence to write code faster or rapidly clear backlog tickets is an illusion of productivity if those tasks lack meaningful business impact. Instead, organizations must elevate from an engineering-output mindset toward engineering-led growth, prioritizing high-value, strategic focus over blindly accelerating manual execution.

To build an "agentic software factory," Pipedrive leaned into the compounding effect of the Kaizen philosophy by automating widespread friction points rather than only chasing massive, ambiguous overhauls. They developed specific internal agents to tackle operational drag. "Scooby," an observability agent, rapidly performs the "five whys" on system incidents to isolate root causes with zero recurring cost. Another agent, "Atlas," navigates the architectural sprawl of 750 microservices and 2,200 repositories. Recognizing that traditional documentation becomes outdated almost instantly, Atlas translates the actual codebase—which acts as the single true source of information—into readable product documentation that non-engineers can verify and understand.

Transforming product development requires a profound cultural adoption, moving from treating new technologies as extended search engines to entirely redefining the future of engineering roles. Pipedrive centralized this shift through a specialized engineering excellence team that curated an internal marketplace of capabilities, strictly guarded by a watchdog agent to prevent duplicate plugin creation. By integrating dynamic compliance and infosec agents directly into standard workflows like Slack, developers are guided to meet global regulations seamlessly. Ultimately, as repetitive coding is abstracted away, the developer's core job transforms from manual task execution to autonomous system management, steering technology to drive exponential business growth.

**Keywords:** agentic software factory, engineering-led growth, developer cognitive load, software engineering kaizen, incident observability automation, root cause analysis workflows, microservice dependency mapping, automated code documentation, internal tooling marketplace, dynamic compliance agents, infosec requirement embedding, product development transformation, autonomous engineering operations, legacy architecture navigation

## Chapters

1. **Shifting focus from code output to human attention** (01:44) — Human attention and cognitive capacity have replaced raw code as the most expensive resource in software engineering.
1. **The illusion of time-saving metrics in AI** (04:20) — Measuring AI engineering value requires assessing actual delivered product impact rather than merely validating time saved on repetitive tasks.
1. **Applying compound interest and the Kaizen principle** (06:49) — Focusing on small, frequently executed automated tasks generates a cumulative compound effect across the entire engineering organization.
1. **Developing the Scooby agent for automated incident analysis** (08:36) — An automated incident management agent leverages the five whys framework to rapidly identify root causes in legacy architectures.
1. **Resolving minor backlog tasks without direct engineering involvement** (10:53) — Enabling product and design leaders to solve non-functional backlog constraints reduces operational friction and frees engineering capacity.
1. **Utilizing the Atlas agent for dynamic microservice documentation** (12:23) — An autonomous agent automatically reads code dependencies across hundreds of microservices to generate accurate product documentation.
1. **Defining the future of job roles alongside AI** (15:37) — Maximizing the strategic value of AI requires redefining the intrinsic purpose of roles rather than cloning current human workflows.
1. **Managing cognitive load in a multi-agent engineering environment** (18:54) — Coordinating multiple independent agents simultaneously increases cognitive load and demands strict engineering focus on highly impactful strategic tasks.
1. **Answering questions on compliance, architecture, and cultural adoption** (23:30) — Audience questions address how AI agents validate architecture constraints, adhere to compliance rules, and overcome initial developer resistance.

## Related Moments

- [The evolving role of software engineers alongside agents](https://www.wearedevelopers.com/videos/100132-the-agent-interface-layer-protocols-tools-and-trust-boundaries) (from "The Agent Interface Layer: Protocols, Tools and Trust Boundaries")
- [Exploring AI agent usage within the software engineering industry](https://www.wearedevelopers.com/videos/1814-wearedevelopers-live-markdown-liquid-and-checkouts) (from "WeAreDevelopers LIVE - Markdown, Liquid and Checkouts")
- [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")
- [Navigating developer bottlenecks and human accountability](https://www.wearedevelopers.com/videos/100265-fireside-chat-in-conversation-with-werner-vogels-cto-of-amazon-com) (from "Fireside Chat - In conversation with Werner Vogels, CTO of Amazon.com")

## Related Articles

- [What is Agentic Programming and Why Should Developers Care?](https://www.wearedevelopers.com/magazine/625-what-is-agentic-programming-and-why-should-developers-care)
- [Never delegate the understanding](https://www.wearedevelopers.com/magazine/749-never-delegate-the-understanding)
- [Transforming Software Development: The Role of AI and Developer Tools](https://www.wearedevelopers.com/magazine/527-transforming-software-development-the-role-of-ai-and-developer-tools)
- [Navigating the AI Shift](https://www.wearedevelopers.com/magazine/629-navigating-the-ai-shift)

## Related Jobs

- [Principal Product Manager, Agent Platform](https://www.wearedevelopers.com/jobs/ext/277541-principal-product-manager-agent-platform) at **GitHub**
- [Tribe Lead - ( Software) Engineering Centre of Excllence](https://www.wearedevelopers.com/jobs/ext/1475530-tribe-lead-software-engineering-centre-of-excllence) at **SD Worx**
- [Staff Software Engineer, Copilot Experiences](https://www.wearedevelopers.com/jobs/ext/164361-staff-software-engineer-copilot-experiences) at **GitHub**
- [Principal Software Engineer, Enterprise AI Platform](https://www.wearedevelopers.com/jobs/ext/1467292-principal-software-engineer-enterprise-ai-platform) at **GitHub**
- [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**
- [Lead Software Engineer (f/m/d)](https://www.wearedevelopers.com/jobs/48296-lead-software-engineer-f-m-d) at **Personio SE & Co. KG**