BayesInsights: Modelling Software Delivery and Developer Experience with Bayesian Networks at Bloomberg
arXiv:2603.29929v1 Announce Type: new Abstract: As software in industry grows in size and complexity, so does the volume of engineering data that companies generate and use. Ideally, this data could be used for many purposes, including informing decisions on engineering priorities. However, without a structured representation of the links between different aspects of software development, companies can struggle to identify the root causes of deficiencies or anticipate the effects of changes. In this paper, we report on our experience at Bloomberg in developing a novel tool, dubbed BayesInsights, which provides an interactive interface for visualising causal dependencies across various aspects of the software engineering (SE) process using Bayesian Networks (BNs). We describe our journey fr
View PDF HTML (experimental)
Abstract:As software in industry grows in size and complexity, so does the volume of engineering data that companies generate and use. Ideally, this data could be used for many purposes, including informing decisions on engineering priorities. However, without a structured representation of the links between different aspects of software development, companies can struggle to identify the root causes of deficiencies or anticipate the effects of changes. In this paper, we report on our experience at Bloomberg in developing a novel tool, dubbed BayesInsights, which provides an interactive interface for visualising causal dependencies across various aspects of the software engineering (SE) process using Bayesian Networks (BNs). We describe our journey from defining network structures using a combination of established literature, expert insight, and structure learning algorithms, to integrating BayesInsights into existing data analytics solutions, and conclude with a mixed-methods evaluation of performance benchmarking and survey responses from 24 senior practitioners at Bloomberg. Our results revealed 95.8% of participants found the tool useful for identifying software delivery challenges at the team and organisational levels, cementing its value as a proof of concept for modelling software delivery and developer experience. BayesInsights is currently in preview, with access granted to seven engineering teams and a wider deployment roadmap in place for the future.
Comments: 6 pages, 1 figure, Camera Ready Accepted at FSE-Industry 2026
Subjects:
Software Engineering (cs.SE)
Cite as: arXiv:2603.29929 [cs.SE]
(or arXiv:2603.29929v1 [cs.SE] for this version)
https://doi.org/10.48550/arXiv.2603.29929
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: David Williams [view email] [v1] Tue, 31 Mar 2026 16:02:49 UTC (103 KB)
Sign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
modelbenchmarkannounce
‘That’s a great point!’: Overly agreeable AI models shown to harm people’s judgment - Palo Alto Online
<a href="https://news.google.com/rss/articles/CBMiywFBVV95cUxOa1ZrSUQyY0JEbXEtUDFveWVUMV9SOWxZd05LM1AtOEFkc3d0QlN1X0RuSzd1RGNSM3BCN0pITlpCRUl5UmhWaWpGTXE0Q0ZWcFZqRTA2X1dEcERldk1wZnVWR2hXdGtKUDV0cmxQTVVBNVFDc1FLNXpWM3BYeEI3UE5QQWtvVmhtSmFsV0pqdF9feVhzVHRTbGtuTGNqNjJubGFNWjJ4d2lpUVFtOFA2cm1zYklkQW9vZkRDS2p3blhkaHpZWHItYlIwQQ?oc=5" target="_blank">‘That’s a great point!’: Overly agreeable AI models shown to harm people’s judgment</a> <font color="#6f6f6f">Palo Alto Online</font>
Your agent's guardrails are suggestions, not enforcement
<p>Yesterday, Anthropic's Claude Code source code leaked. The entire safety system for dangerous cybersecurity work turned out to be a single text file with one instruction: <em>"Be careful not to introduce security vulnerabilities."</em></p> <p>That is the safety layer at one of the most powerful AI companies in the world. Just a prompt asking the model nicely to behave.</p> <p>This is not a shot at Anthropic. It is a symptom of something the whole industry is dealing with right now. We have confused guidance with enforcement, and as agents move into production, that distinction is starting to matter a lot.</p> <h2> Why prompt guardrails feel like they work </h2> <p>When you are building an agent in development, prompt-based guardrails seem totally reasonable. You write something like "ne
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Analyst News
Alibaba recruits Google DeepMind contributor to join Qwen AI team, sources say - scmp.com
<a href="https://news.google.com/rss/articles/CBMiwwFBVV95cUxNUzZNY3JSZndfR1NEWC1RUmlrNkNaSms4Z0pGdjFJZk56cjVHbmV2VkZHU3NsNTgzOGtYUWNJcU1Wa3BDSXY2ZmtXS1k3UnE1VU40cmhmRFpGWXAyaHZtbTlLblBrdEhIdmR1ekxwbGVSVU9wUE9PNG1xNVZVZ2Nicmo3bVo3TzJVT3BLSUxnSkU3a25uVU9wR3lSbTJ2YkVNa2JBRnEwbDk0eGYxOUpxRlI3eWdGdWtvY19VSW5hclgzalU?oc=5" target="_blank">Alibaba recruits Google DeepMind contributor to join Qwen AI team, sources say</a> <font color="#6f6f6f">scmp.com</font>
Group Pushing Age Verification Requirements for AI Turns Out to Be Sneakily Backed by OpenAI - Gizmodo
<a href="https://news.google.com/rss/articles/CBMiwAFBVV95cUxNZy0tdHVKZTBYZWUzWWRRRHc1ODVpX0Y3Wm9sQWxUTHoxdWtTZ3pwTWJpLW15cUZBS0h3OW1KdzRsQllfQTRWTk5yWTNHM1RlRTg2SURGRDE0bWF0NEpBcDNTT25yV2NkVEt4dGQyS05kSW9OSUFMUlByODh4VFpta0FHVzZBaGlkSC1XMW93MDhlclVLcXIxci0wQVNuRjRsZjN2cXNHX2NramxJQkZ4RXBfY0VmYV9xS25BQ0FVX0E?oc=5" target="_blank">Group Pushing Age Verification Requirements for AI Turns Out to Be Sneakily Backed by OpenAI</a> <font color="#6f6f6f">Gizmodo</font>
Scientists Create Plant That Produces Ayahuasca, Shrooms, and Toad Psychedelics All At Once
The proof-of-concept system produces psilocybin, DMT, and other compounds in leaves of the tobacco plant, potentially easing pressure on wild species and preserving Indigenous traditions.
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!