How Endava builds an agentic organization with Codex
Endava leverages Codex to empower its organization, enabling junior engineers to produce high-quality work and senior engineers to scale their expertise. This approach significantly reduces development time and enhances collaboration across all stages of client engagement. Additionally, the adoption of Codex facilitates knowledge transfer and elevates the overall quality of software delivery.
Endava, a global software contracting firm, has embraced Codex to transform its operational model into what it calls an "agentic organization." This new structure allows the company to codify senior engineering expertise into AI agents that work alongside human teams throughout the entire client engagement lifecycle, from initial intake to final delivery. This paradigm shift has led to substantial improvements in the quality and efficiency of software development. Consequently, Endava has seen an exponential increase in output quality.
One of the key benefits of this agentic approach is the enhanced collaboration between senior and junior engineers. Codex acts as a guide, making senior architects' complex knowledge accessible to less experienced team members. This enables junior developers to tackle tasks typically reserved for senior engineers, producing high-level outputs with the AI's guidance on best practices and architectural decisions. This process effectively codifies senior experience, making it a real-time learning tool.
The integration of Codex has also streamlined the entire delivery process. Stages that traditionally took days or weeks for analysis, design, and build are now consolidated into a unified process. For instance, Endava used Codex to dramatically reduce the time needed to review thousands of legal contracts, transforming weeks of work into a usable specification generated from a two-hour meeting transcript. This demonstrates the tool's capability to accelerate complex tasks and improve efficiency.
Moreover, the agentic model facilitates unprecedented knowledge transfer. Senior judgment, usually acquired through years of mentoring and code review, becomes instantly available to teams through Codex. This allows a single senior perspective to guide multiple teams simultaneously, fostering a continuous learning environment and elevating the collective skill set of the organization. The same time-saving and illustrative capabilities are now being leveraged in client sessions, accelerating ideation and client understanding.
Related articles
Build real agentic apps using CUGA: two dozen working examples on a lightweight harness
CUGA, IBM's open-source Agent Harness, simplifies building agentic applications by handling infrastructure, allowing developers to focus on tools and prompts. It offers pre-assembled components for planning, execution, and state management, significantly reducing development time. CUGA has topped agent benchmarks like AppWorld and WebArena.
OpenAI launches new initiative to help find and patch open source bugs
OpenAI has launched "Patch the Planet," a new initiative in partnership with cybersecurity firm Trail of Bits, to enhance the security of open-source projects. This program aims to assist maintainers in identifying and patching bugs, utilizing OpenAI's AI-powered security tools while reducing the burden on project teams.
PP-OCRv6 on Hugging Face: 50-Language OCR from 1.5M to 34.5M Parameters
Baidu has released PP-OCRv6, an advanced optical character recognition (OCR) model supporting 50 languages. Available on Hugging Face, this version significantly improves accuracy and efficiency across various parameter sizes, from 1.5 million to 34.5 million, marking a substantial leap in multilingual OCR technology.
