How Jev Cut Our Classification Cost by 20×
We moved bounded classification decisions in Ari from general-purpose LLM calls to TypeSafe's Jev, at roughly one-twentieth the cost and 10–15× the speed.
Oats Blog6 min read
engineering
1,108 stories
Claude Agent SDK: How to Build Production AI Agents
Learn how to take the Claude Agent SDK from prototype to production with sandboxing, durable sessions, permissions, observability, approvals, and recovery.
Rerun Blog15 min read
Choose a coding model using the work your team actually does
Compare coding models on representative tasks, review effort, retries and cost before choosing a default.
Hoplite Blog3 min read
Improving site performance by shipping more CSS
How we fully migrated github.com away from CSS-in-JS. The post Improving site performance by shipping more CSS appeared first on The GitHub Blog.
GitHub Blog AI8 min read
MacBook overheating while coding agents run? Check what they started
Identify the processes behind sustained heat, reduce unnecessary local work, or move the agents to cloud sandboxes so the laptop stops running builds.
Hoplite Blog3 min read
Coding agents keep running your Mac out of memory. What to check first
Use memory pressure and process ownership to diagnose RAM exhaustion, reduce concurrency, or move the agents' browsers and test workers into cloud sandboxes.
Hoplite Blog3 min read
Why your MacBook gets slow when you run several coding agents
Find whether parallel agents are limited by local compute, memory, services, or a remote model, or skip the tuning and give each agent its own cloud sandbox.
Hoplite Blog3 min read
We swapped our LLMs for Jev. It's 39% cheaper.
Our on-call agent makes thousands of small decisions a day. We moved them from LLMs to Jev, a model that doesn't write text, and cut the cost by 39%.
Polylane Blog7 min read
Running an Open-Source Project in Autonomous Mode
oats is public, so anyone can file an issue, and most of maintaining it is toil. GitHub Actions workflows run Claude Code on a self-hosted runner. Three save the most time: auto-classification of every issue; autofix for bugs, critical review findings, and tasks, which it declines without…
Oats Blog7 min read
How I built agent-based security reviews on Databricks
We already had automation in parts of our security review process. It was useful,...
Databricks Blog10 min read
Rendering huge pull requests in the GitHub Copilot app
How we rebuilt the diff surface in the GitHub Copilot app to open a million-line pull request with hundreds of inline review comments. The post Rendering huge pull requests in the GitHub Copilot app appeared first on The GitHub Blog.
GitHub AI Engineering Blog14 min read
Using Hoplite to build Hoplite
What our published use of Hoplite says about delegation and a workflow for making agent work reviewable.
Hoplite Blog3 min read
What Is AI-Native? Architecture, Products, and Real-World Examples
A practical definition of AI-native, the architecture behind it, real examples, and a 10-point test for separating genuine AI-native products from AI add-ons.
Rerun Blog12 min read
MCP vs A2A: Key Differences, Architecture, and When to Use Each
Compare MCP vs A2A across architecture, discovery, task state, security, and use cases, then learn when to use MCP, A2A, both, or neither.
Rerun Blog11 min read
Announcing out-of-memory reporting in iOS
In bitdrift for iOS, OOM terminations now appear in the Session Timeline and Issues page with stack trace and full session context leading up to the crash.
bitdrift Blog7 min read
How Scam AI and TinyFish vet candidates and claims
How the Scam AI and TinyFish integration checks hiring candidates and insurance claims: public pages bound to the case, files checked, gaps written down.
Scam AI Blog10 min read
How We Each Review Tens of PRs a Day
At Ariso, we each review tens of pull requests a day. A GitHub Action prepares the handoff: when a draft becomes ready for review, Claude Code assesses risks, blockers, regressions, deleted behavior, and specific human checks.
Oats Blog11 min read
Custom fields that work everywhere without per-field code
How Relaticle makes custom fields available across forms, APIs, chat, and MCP, with shared normalization, clear empty-value semantics, and explicit limits.
Relaticle Blog8 min read
Showing 954 of 1,108 stories
Load more storiesAiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts