# Daily Digest Published articles for Daily Digest. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## How an AI Bot Turned 30 School Emails a Week Into One Daily Digest DevFeed: [How an AI Bot Turned 30 School Emails a Week Into One Daily Digest]() Original publisher: [Read original article]() Author: Geoff Cox Published: 2026-10-28T07:44:13Z Content type: article Language: en Sources: [HackerNoon]() Topics: [Bot](), [AI Context Management](), [Pull Request](), [CI/CD]() Tags: [2](), [2026](), [3](), [about](), [account](), [agent](), [agents](), [ai](), [ai-agent](), [ai-agents](), [ai-companies](), [ai-labs](), [artificial-intelligence](), [automation](), [bot](), [can](), [daily](), [daily-digest](), [email](), [i](), [one](), [parenting](), [productivity](), [quiet](), [rules](), [school](), [software-engineering]() ### AI overview The bot consolidates school email and TalkingPoints messages into daily digests, with must-dos first, event times only when stated, duplicate notices removed, and calendar links for items not already listed. It sent 44 digests over the reported period, replacing 30-plus weekly emails and an app; the author estimates 30-45 minutes saved per week. Its key safeguards are read-only access to personal Gmail and the calendar, no school replies or calendar edits, and explicit warnings when a source cannot be checked. Failures such as silently skipping TalkingPoints and reporting a false sign-out led to checks on every run; a program also validates email formatting before sending. The author records bot rules and setup in a Git repository and describes a template where code evaluates sourced items and each run becomes a reviewed pull request. The school bot still needs manual text-code sign-in when TalkingPoints sessions expire. ### Source excerpt I built an AI bot that turns about 200 school emails into one daily digest: what it can read, what it must never do, and the quiet failures that became rules. ## Axonius launches AI Workforce virtual workers as AI Companion and MCP Server go live DevFeed: [Axonius launches AI Workforce virtual workers as AI Companion and MCP Server go live]() Original publisher: [Read original article]() Author: Duncan Riley Published: 2026-10-19T13:00:11Z Content type: news Language: en Sources: [SiliconANGLE]() Topics: [shadow AI](), [ai security](), [MSP MCP](), [AI Chat](), [Artificial Intelligence]() Tags: [agent](), [agents](), [ai-agents](), [ai-tools](), [asset-cloud](), [asset-intelligence](), [axonius](), [axonius-ai-companion](), [axonius-ai-workforce](), [axonius-mcp-server](), [axonius-verified-assets](), [daily-digest](), [exposure-triage](), [general-availability](), [large-language-model](), [model-context-protocol](), [moshe-ben-simon](), [news](), [omdia](), [post-quantum-cryptography](), [remediation](), [security](), [shadow-ai](), [the-latest](), [theresa-lanowitz](), [virtual-workers]() ### AI overview Axonius has added AI Workforce to its Asset Cloud platform, offering autonomous virtual workers for security remediation. The workers act on asset data, track outcome metrics, and can operate in modes ranging from approval required to guarded automatic action. The launch also includes general availability for AI Companion and an MCP Server, with approvals for sensitive changes and an audit trail for actions. ### Source excerpt Asset intelligence company Axonius Inc. today added Axonius AI Workforce to its Asset Cloud platform to let security teams hand ongoing remediation work to autonomous, artificial intelligence-powered virtual workers. AI Workforce is meant to take over follow-up work that security teams rarely have time for. A lot of that work exists because asset data ends [...] The post Axonius launches AI Workforce virtual workers as AI Companion and MCP Server go live appeared first on SiliconANGLE. ## Engineering stories behind the Medium Daily Digest Algorithm: Part 2 DevFeed: [Engineering stories behind the Medium Daily Digest Algorithm: Part 2]() Original publisher: [Read original article]() Author: Raphael Montaud Published: 2025-08-28T11:31:36Z Content type: article Language: en Sources: [Medium]() Topics: [Algorithms](), [Tech Debt](), [it modernization](), [Database]() Tags: [algorithm](), [bloom-filter](), [bloom-filters](), [daily](), [daily-digest](), [database](), [digest](), [dynamodb](), [engineering](), [medium](), [migration](), [recommendation-system](), [recommendations](), [software-engineering]() ### AI overview Medium replaced its oversized, hard-to-debug Bloom filters for Daily Digest recommendations with queries against user-level database histories, reporting a tenfold cost reduction compared with its existing setup. For muted writers, it fetches each user's muted list, which averages fewer than one database item per feed because most users mute nobody; heavy muters can incur higher latency. For presentation counts, it fetches up to the latest 5,000 records and accepts edge cases beyond that window because the three-presentation threshold is a diversity guideline, not a hard limit. Read filtering is mandatory, so it uses a two-stage approach: query recent reading history early, then check remaining candidates individually. This supports clearing reading history and avoids maintaining derived filter data. The cost comparison is qualified: a newly created, better-separated Bloom filter setup might have been cheaper than Medium's single, ever-growing instance. ### Source excerpt How we made our filtering 10x cheaper by removing our Bloom Filters Bloom Filters are great tools to make fast and cheap filtering. They also come with plenty of problems and can easily get expensive and cumbersome. We switched to user-based direct database queries, which made our filtering cheaper and easy to maintain. Here's the full breakdown of that migration. Intro: This is a 4-part series breaking down improvements to the algorithm behind the Medium's Daily Digest over the past year. When we started this work, the Digest was suboptimal -- and since it's a huge distribution surface, reaching millions of readers every day, we started working on incremental improvements.By the end of these projects, the digest was 10% more likely to convert users to paying members, less expensive to run, more flexible and easier to maintain and it's now providing higher quality recommendations for all our users, including our "power readers".This is told through the lens of our engineering team tackling a series of challenges one by one. Medium has a small team but we operate on a big scale. We're working our way through some technical debt and at the same time, striving to provide the best experience for our readers. This is the source of many interesting challenges.I hope this series helps you understand how the recommendations algorithm work and can help others who are facing similar technical challenges. This is probably the most technical story in the series, but I will keep it as simple as possible and hopefully this is interesting for non-technical readers too. Some Concepts Here's a little cheat sheet with some concepts you may need to follow along with this story You may need this to understand the rest of this postBloom Filters at Medium A lot of the filters I mention in this series are backed by Bloom Filters (I've described some of those filtering rules in Part 1 if you haven't read it already). We use Bloom filters to remove stories we think won't interest readers fro ## Engineering stories behind the Medium Daily Digest Algorithm: Part 4 DevFeed: [Engineering stories behind the Medium Daily Digest Algorithm: Part 4]() Original publisher: [Read original article]() Author: Raphael Montaud Published: 2025-08-25T18:31:30Z Content type: article Language: en Sources: [Medium]() Topics: [recommendation systems](), [Algorithms](), [Test-driven development]() Tags: [algorithm](), [daily-digest](), [database](), [digests](), [engineering](), [experience](), [improvements](), [machine-learning](), [medium](), [members](), [programming](), [reading](), [recommendation-system](), [recommendations](), [software-engineering](), [stories](), [team](), [technical](), [technical-debt](), [tickets](), [user](), [users]() ### AI overview Medium found that some heavy digest users repeatedly received the same stories, sometimes up to eight times, even though repetition was minimal for most users. Because Apple Mail Privacy Protection makes opens unreliable, the team tracked digest emails with at least one story click as definitely opened. It then filtered stories sent in more than one such digest. Tests suggested a threshold of one would remove nearly five stories per digest for complaining users while affecting free users by less than one story on average. An A/B test showed a statistically significant increase in reading time, especially among members, and no subsequent diversification complaints. The team notes the hard filter may be improved as a soft filter and could account for story position in the email. ### Source excerpt Cross-Digest diversification In this part 4, we'll see how we went from investigating a few complaints from digest power users to improving our digest recommendations across the board. Intro: This is a 4-part series breaking down improvements to the algorithm behind the Medium's Daily Digest over the past year. When we started this work, the Digest was suboptimal -- and since it's a huge distribution surface, reaching millions of readers every day, we started working on incremental improvements.By the end of these projects, the digest was 10% more likely to convert users to paying members, less expensive to run, more flexible and easier to maintain and it's now providing higher quality recommendations for all our users, including our "power readers".This is told through the lens of our engineering team tackling a series of challenges one by one. Medium has a small team but we operate on a big scale. We're working our way through some technical debt and at the same time, striving to provide the best experience for our readers. This is the source of many interesting challenges.I hope this series helps you understand how the recommendations algorithm work and can help others who are facing similar technical challenges.Some Concepts Here's a little cheat sheet with some concepts you may need to follow along this story You may need this to understand the rest of this postUser Complaints After we shipped all the changes mentioned in the previous installments of this series, we started seeing some support tickets coming in related to the digest: User complaints that started off our investigation I think we should appreciate the level of thoughtfulness our users put in those support tickets. We review those carefully and we take pride in reading and answering every support tickets. Those were forwarded to the recommendation team and we immediately thought that maybe we oversteered to much when we removed some of the filtering rules for the digest. User digests were too repet