@geraldnguyensg.bsky.socialBenchmarks can narrow a model choice, but they do not tell you whether your agent survives your workflow. As providers turn tracing and post-deployment evaluation into first-class tools, the team that owns the eval suite is becoming the team that... #Ai #AiEngineering #AppliedAi
@tmtabor.ioOur agent pipeline kept producing malformed JSON. Fine-tuning fixed it. Here's what that process actually looked like. #AIEngineering
@academaxjournals.bsky.social📢 Big news for the geoscience community!
EGGE, a new journal on environmental and geotechnical engineering, is now live.
❄️ Covering everything from permafrost thaw to machine learning in geoengineering.
Know more: www.sciencedirect.com/journal/envi...
#AcadeMax #ZJUP #Geoscience #AIEngineering
@upsun.comOptimizing AI coding agents is useless if your team does not share context 🤖. Giving humans and agents the same repo, docs, and vocabulary is where true speed comes from 💡. 👉 upsun.com/blog/context... #AIEngineering #DevOps #SoftwareArchitecture #CodingAgents
@spec-kitty-ai.bsky.socialSpec Kitty fits into the development process your team already uses.
Instead of replacing your favorite AI coding tools, it provides a governed workflow that keeps specifications, decisions, reviews, and project context connected from start to finish.
#DevOps #AIEngineering #TechLeadership
@temprhq.bsky.socialWould you accept fewer errors if p95 latency doubled? Compare p50 and p95 by model after changing a fallback chain. A lower error rate can still hide a painful user experience. #LLMOps #AIEngineering https://temprhq.io/gateway
AWS is streamlining AI agent deployment with tools like SageMaker AI and Bedrock AgentCore. From model serving to autoscaling, structured workflows reduce operational overhead. Coding agents are now essential for managing multi-model agentic applications. #AIEngineering #AWS #AgentDeployment
@yurekilab-en.bsky.socialMy coding agent kept editing generated files. Hand-patched a lockfile. Tweaked an API client built from a schema. Both looked fine in review, both vanished on the next build. Added a do-not-edit list, each pointing at its source. #claudecode #ai #aiengineering #buildinpublic
@temprhq.bsky.socialWhich AI model fits the use case and budget? TemprHQ brings model listings and pricing together so development teams can compare options before implementation. #AIEngineering #LLMOps https://temprhq.io/changelog
@yurekilab-en.bsky.socialMy coding agent told me a helper was unused. I deleted it. Two pages broke. Now every claim about the codebase comes with file:line, or it doesn't count. It recalls code it read 20 minutes ago worse than it sounds like it does. #claudecode #ai #aiengineering #buildinpublic
@temprhq.bsky.socialHow many client integrations should model switching require? Keep one OpenAI-compatible API contract, then change the provider-backed model in Tempr instead of adapting your app to each provider. #AIEngineering #OpenAICompatible https://temprhq.io/providers
@darryl-ruggles.cloud#Jev #TypeSafeAI #StructuredOutputs #AIEngineering #MLOps
I guess it's possible you have not heard about Jev yet but it has taken over the internet in the last week.
@heyymeraki.bsky.socialYou ask an LLM for JSON. Most of the time, you get it. Then one reply starts with "Sure! Here's the record:" and your app breaks.
New in my AI engineering series: why that happens, and how structured outputs gets the shape right.
@temprhq.bsky.socialWhich requirements survive a provider switch? Keep requirements constant across providers: context window, capabilities, reference cost, and key setup. Compare 407 models in TemprHQ. #LLM #AIEngineering https://temprhq.io/models
@frameworktraining.bsky.socialEnterprise Agentic Systems: Foundations - the architecture behind safe, production-ready agents. Deep Dive - the build: Claude Code, Copilot, custom Skills, MCP servers, subagent teams.
As a two-week programme or standalone.
@yurekilab-en.bsky.social"Flaky test" was my agent's favorite excuse. New rule: if a test fails once and passes on rerun, the task isn't done. The agent writes a note on what could have raced. 9 flaky tests last month. 6 were real race conditions. #claudecode #testing #aiengineering #buildinpublic
@blueboxai.bsky.social🧑💻 We’re at @wearedevelopers.bsky.social NA in San Jose this week! Come by booth 337 for a hands-on workshop and swag.
🗺️ Directions here: blog.bluebox.ai/bluebox-at-w...
@levelbrook.bsky.socialStreaming a conversational AI trainer, and teaching it to say I do not know mid-stream. Abstaining after you have already emitted tokens is its own problem. #LLM #AIEngineering
@yurekilab-en.bsky.socialStarted letting my coding agent name the branch before it writes any code. Turns out the branch name is the cheapest plan review there is. "fix-login-redirect" vs "refactor-auth" told me in 2 seconds it had misread the task, before it touched a file. #claudecode #ai #aiengineering #buildinpublic
@nadyavoynich.comEveryone's talking about Jev because it's fast and cheap.
My partner ran it on real Intercom data. Here is his breakdown ↓
(Spoiler: the hype is real)