Use Case Intelligence RSS Search use cases Search
IBM Software / SaaS Global

IBM

Application Refactoring

IBM wanted to help developers understand undocumented code, generate documentation faster and reduce the manual effort required to work across large, inherited codebases.

Read the original story Explore all use cases
56% average reduction in time spent on code explanation
59% average reduction in code documentation time
750 JavaScript files
more than 90% time savings on code explanation for one team

Reported impact

Business outcome

IBM teams reduced the time spent understanding and documenting code, improved productivity across project teams and created a repeatable pattern for accelerating software maintenance work.

  • Productivity Improvement
  • Speed to Market

Solution

IBM teams used IBM watsonx Code Assistant during the watsonx Challenge to speed up code explanation, documentation, generation and test creation across large, inherited repositories. One highlighted team had taken over more than 50 undocumented code repositories containing about 750 JavaScript files and used the assistant to summarize large files, explain advanced syntax and generate scripts that identified which files still needed documentation. In the working pattern, developers submit source files or natural-language prompts to the assistant, review the generated outputs and then incorporate accurate summaries or generated code into their maintenance workflow. Because watsonx Code Assistant is embedded directly in development tasks, it reduces the time needed to understand legacy code, document APIs and onboard newer engineers without requiring every contributor to be a deep expert in the codebase.

Data flow

Developers submit source files or natural-language prompts to watsonx Code Assistant, review the generated summaries or code outputs and then use those artifacts to document and update legacy repositories more quickly.

Solution architecture

1 components · 1 layer
  1. Serving
    • IBM watsonx Code Assistant Explains code, generates documentation and creates code artifacts that speed development work on large codebases.

Architecture clues

  • Handled files with more than 1000 lines of code in the showcased team
  • Supports code explanation, documentation, generation and test creation
  • Used across hundreds of project teams in the watsonx Challenge

Evidence from the source

107 teams reported reducing time spent on code explanation by an average of 56%.
By using watsonx Code Assistant, they summarized each file in approximately 12 seconds.
Thousands of IBM employees, spanning hundreds of project teams, experimented with the many watsonx Code Assistant capabilities.
Transparency Evidence & methodology 95/100 reference value · 84% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value95/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact25/25
    3 metrics describe measurable impact.
  • Deployment scale5/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence84%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence15/20
    3 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. IBM

    IBM customer story

    First-party
    https://www.ibm.com/case-studies/ibm-software-team
    Source type
    Vendor-published customer story
    Published
    Oct 17, 2024
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
OpenAI Oct 9, 2026 Asana Software / SaaS North America Asana needed to cut the cost and latency of its StackAI browser agent so it could offer customers more capable models for browser-driven workflows without unsustainable operating expense. $0.47 average estimated model cost with the optimized GPT-6.1 Sol workflow Application RefactoringIT Operations Automation Codex · Command · GPT-6 Astra OpenAI Oct 8, 2026 Braintrust Software / SaaS North America Braintrust wanted to respond to customer feature requests faster and run more engineering experiments, but slower coding tools and backlog-driven workflows made it costly to turn feedback into working prototypes in real… 50% of the Braintrust team moved to Codex in one month Application RefactoringIT Operations Automation Codex · GPT-5.5 OpenAI Oct 8, 2026 Notion Software / SaaS North America When the feature request came in, Notion's mobile app already had a functional version, but the desktop and web client didn't. Even though Ryan wasn't entirely sure how the feature worked on mobile, he was able to give… "Whenever I need to research a task, fix a bug, or make a little tweak, Codex is just there, ready and willing.… Application Refactoring Codex