A developer used the coding agent Shelley, running on a freshly spun-up VM, to build a fire watch aggregator website in just under an hour that combines PurpleAir sensor data, Bay Area Air Quality Dis…
A developer replaced a CI-based cron job that posted Slack nag messages about out-of-sync LLM gateway model lists with a bot running on an exe.dev VM that outputs a diff of the proposed change plus a …
A developer at the company exe built a tool called exe-finops that combines ClickHouse with AI agents to generate financial reports and investigate billing issues, reducing the need for manual data re…
An unnamed developer's LLM evaluation benchmark was blocked by Anthropic's Claude model Fable, which refused a request it misclassified as violative cyber content, despite the task being unrelated to …
Joel Spolsky's 2000 Joel Test for software teams has been updated by an unnamed author at exe.dev into the Shelley Test, adding nine agent-era questions such as agentic code review, LLM-supervised con…
A developer who spent six months writing code exclusively with AI agents reports that the models improved dramatically in early 2025, with GPT-5.3 and Opus 4.6 handling larger changes with less steeri…
A blog post from exe.dev argues that the most valuable design insights come from surprises discovered after building, and suggests that teams using coding agents should ask the agent for the design af…
Exe has added support for Workload Identity Federation (WIF), allowing agents and workloads running on exe to access cloud resources without long-lived credentials. The integration, announced in a blo…
Bending Spoons acquired Airtable for $1.28 billion, marking a turning point for no-code platforms as LLM loops with tool use make traditional no-code tools less relevant. The author, a former Airtable…
Exe has developed a set of informal etiquette rules for bots, including that bots do not post to human spaces, humans write their own words, and bot output is clearly marked. The rules also require bo…
Exe.dev's coding agent Shelley can be customized by asking it to change itself, with customizations rebased onto each new version. The company advocates editing code directly as a third way to customi…
Antithesis software engineer Carl Sverre uses exe, a VM platform, as a sandbox for agentic AI software tests, citing its per-user pricing model ($25/user/month for up to 50 VMs), root access, and non-…
Anthropic's Claude is not a compiler but is better than one, argues software engineer Dan Breunig, because it can work vertically across the software stack from strategy to machine code, unlike tradit…
Josharian built a mobile-friendly concert calendar for San Anselmo's summer music series using the exe.dev iOS app, demonstrating how developers can create software entirely from a phone. The project …
Exe.dev announced that users can now connect their ChatGPT subscription to the platform, enabling the use of OpenAI models with the coding agent Shelley. The integration is configured via the LLM inte…
Exe.dev deploys software updates multiple times daily without interrupting active network connections by handling connections in a separate, rarely-updated process called exepipe. The exepipe process …
Exe.dev launched an iOS app built using a coding agent named Shelley on a Mac Mini, with an over-the-air update system and incremental SQLite synchronization. The development process involved SSH forw…
Exe.dev launched an iOS app featuring native notifications, share sheet integration, voice mode, SSH support, and centralized VM management. The app addresses limitations of mobile browsers for agenti…