brianletort.ai

AI Transformation Library

See how AI changes the work.

102 real-world cases. What changed, what improved, and where people still decide.

CardsTable

7 cases

1–7

CaseAI valueOpen
An editorial scene for Google contrasts finds migration sites and writes context-specific edits across the monorepo. with discovers likely change locations and prompts a monorepo-trained llm to generate edits. in the llm-assisted 32-bit to 64-bit identifier migration workflow.
Google		74.45% of 595 submitted code changes and 69.46% of 93,574 edits were LLM-generated.
An exhaustive field of regression tests contrasts with a model-selected subset monitored by a software engineer.
Meta (Facebook)		Runs fewer than one-third of dependency-selected tests
An editorial scene for GitHub Copilot research experiment contrasts reads the http-server specification and writes javascript without copilot. with offers inline code completions while the developer implements the same server task. in the ai pair-programmed http server workflow.
GitHub Copilot research experiment		71.17 minutes treatment; 55.8% faster, P=.0017
An editorial scene for Google contrasts submits a change after limited presubmit testing. with submits a change after limited presubmit testing. in the postsubmit speculative cycles with transition prediction workflow.
Google		37 minutes with Speculative Cycles (approximately 65% / 70-minute reduction)
An editorial scene for Meta (Facebook) contrasts reports a bug or crash against a specific line of code. with reports a bug against a specific line and forwards its metadata to getafix. in the getafix automated patch suggestion and validation for null-dereference bugs workflow.
Meta (Facebook)		Getafix attempted patches for about 60% of the ~2,000 null-method-call bugs; about 90% of attempted patches passed automated validation (compilable and Infer no longer emitted the warning); overall, 1,077 bugs (approximately 53%) were successfully auto-patched.
An editorial scene for Anonymous Fortune 500 software company contrasts reads the incoming chat, searches available knowledge, and drafts a response. with observes the live chat and proposes response text based on patterns from prior interactions. in the generative ai agent assistance workflow.
Anonymous Fortune 500 software company		About 14% average increase; 35% for novice/low-skill agents
An editorial scene for Accenture contrasts writes implementation and test code manually. with receives inline code suggestions and accepts, edits, or rejects them. in the github copilot-assisted daily engineering work workflow.
Accenture		Access was associated with 7.51%-8.69% more pull requests per week, depending on specification.
Curated collections →Evidence methodologyPublication history
AI Transformation Library | Brian Letort