It's here! The official @inngest.com Codex plugin! Built with all the love an attention of a builder who appreciates solutions to problems and making agent infra easier than before. Blog coming soon! github.com/inngest/inng...

The recent tech layoffs are about freeing up capital to test AI?! Over the weekend, I was at a kids birthday party, and had a 4 hour convo with another dad. He works at <redacted>, and formerly at <redacted>, and asked me about my opinions on AI, agents I've built, and my predictions for the future

Engineer at a 1,000+ org, 2026 benchmark: "Retries, duplicate events, partial failures, long-running jobs... still hard to build systems easy to debug, resume safely, and trust at scale." Resources don't fix this. Connected stacks do. Link in thread ↓

The 19% of AI teams confident their stack scales 2-3x aren't using different tools. They use tools that are tightly connected. Show me what ran. Why it stopped. If it's safe to resume. All in one place. The work for 2026 is connection. Link in thread ↓

AX is the most important thing your company can be focusing on right now. How does an agent interact with your product. Your infrastructure and APIS are the most important commodities in the AX world.

Say it with me: AGENT EXPERIENCE Michael from @workos.bsky.social took the stage at MCP Night and talked about building systems that agents can use And your agents need durable infrastructure. That's what we're building at @inngest.com!!! #AX #AgentExperience #MCPNight

69% of AI teams in production are not using a third-party agent framework. They're calling LLMs directly or building their own. Top complaints: abstractions make failures harder to trace (26%), poor long-running support (19%), don't compose with orchestration (12%). Link in thread ↓

35% of teams running AI in production are not doing AI evals at all. Of the 65% who do, most built their own pipeline. 47% cite the same gap: eval state and orchestration state can't see each other. That's not an evals problem. It's a context problem. Link in thread ↓

I have a robotic arm with a camera in my office. I left Codex to its own devices. it can control the arm, look around, comment on what's happening, and it's focused on my cat. And my cat keeps looking at the arm. lol The infra was built with @inngest.com and the python sdk.

Sometimes AI vampires need to touch grass. Thank God for mobile hotspots.

"Debugging feels more like forensics than engineering." Engineer quote from our 2026 AI report. Observability = #1 unsolved problem (19% of responses). Orch-native observability: 40% diagnose in minutes. APM-only: 11x more slow-or-blind cases. Link in thread ↓

AI teams spend 2x the time on reliability vs non-AI teams. We split that by orchestration tool. 12-month change in burden: - Inngest: -10pp - Custom: -9pp - Temporal: +22pp - AWS/Vercel/CF: +9pp Tooling is bending that curve. The question is which way. Link in thread ↓

More engineers should mean more confidence. Right? We surveyed 130 engineers for the 2026 AI in Production benchmark. 26% of small teams are very confident at 2-3x scale. 13% of mid teams. 0% of teams with 500+ engineers. The gap isn't tooling. It's context across the stack. Link in thread ↓

Cron is older than I am. Ken Thompson wrote it in 1975. We still hand it our most important jobs. Now AI agents. Server down at 9am? Missed. Halfway failure? Stranded. Inngest gives cron durable execution. Same syntax. Recovers from anything.

5 things a platform owes an AI agent mid-task: 1. State that survives failure 2. Deterministic retry 3. Pause and resume across time 4. Failure as first-class 5. Multi-agent coordination Link in thread ↓

I'm testing an AI clone using HeyGen and ElevenLabs It's not that I want to replace myself, but there is a lot of content that I want to get out, and there isn't enough time to record and edit all the videos. I'm thinking of this as part of a learning program for new users. What do you think?

AGI needs more than scale. Demis Hassabis says we still lack continual learning, memory, and steady reasoning. Agents are the path, and small models plus distillation already let engineers do 1000x the work. If AGI lands near 2030, are you building with it in mind or ignoring it?

Weida Tan, co-founder of Press Club, speaking at AI in Production on May 6. Talk: "From Vibe Coding Demo to AGI-Proof Software." AI made impressive demos easy. Knowing what will last is hard. Weida's covering how to ship prototypes that survive the AGI tide. Inngest HQ SF, 5:30. Link in thread ↓

Google dropped DESIGN.md It gives coding agents a structured design system in one markdown file You define colors, typography, spacing, and components, then lint and export with a CLI If you build with AI agents, your design tokens need a spec like this Sources in 🧵

Matt Biilmann named four pillars of Agent Experience in Jan 2025: Access. Context. Tools. Orchestration. Pillars 1-3 have llms.txt, MCP, agents.json. Pillar 4 has: nothing. That's why I joined Inngest.

the hardest part of building a moat that no one tells you about? it’s the pH balance otherwise you end up with an algae bloom and the water looks all green and gross

Matt Dailey (founder, Ref) is speaking at AI in Production on May 6. Talk: "What won't change?" The angle: this is the best time ever to be a junior engineer, if your team adopts the right practices. Matt's bringing a blueprint. Inngest HQ SF, doors 5:30. Link in thread ↓

It's time to confess your AI Crimes In Production! Anonymously share your worst crimes shipping AI to production and who knows, maybe I'll read it on a live stream. There have already been a few confessions that I can't wait to read to y'all soon. Link in the thread

Go watch an AI agent run a 20-step workflow on your platform. Let step 14 fail. What happens next is your AX, measured honestly. Pillar 4 of Agent Experience is the one nobody's defined.

99% of people have no idea what is happening with AI Using GPT or Claude is level one, and you still do the work Level two is agents that plan, execute, and deliver full projects with one goal Level three is one AI running teams of sub agents across your business and life Which level are you on?

I don't think @brittanyellich.com and I had fun taping the latest @overcommitted.dev podcast episode...nope...no fun at all. Thanks for having me as a guest on the show! Can't wait to share the episode and maybe open source the AI agents we discussed at the end.

Weekend listening: went on the Chain of Thought podcast and talked about building my AI chief of staff MARVIN from scratch. Good one for a walk or some yard work. open.spotify.com/episode/70sb...

Went on @ConorBronsdon's Chain of Thought podcast and shared my whole framework for building an AI chief of staff. Treat it like a junior hire. Onboard it. Give it context. Let it grow. 40 days later, mid-level. www.youtube.com/watch?v=gFT-...

The new Postman unified workbench finally looks like an IDE. Native git, Agent Mode, API Catalog, and a workspace that actually feels like home for developers. I'm genuinely excited for March 1st. This is Postman becoming what I've always wanted it to be.

The scariest question you can ask an enterprise team: "How many APIs do you actually have running in production?" API Catalog in the new Postman gives you that answer. Finally. Launches March 1st.

if you use Cursor (or any AI editor), stop repeating yourself every session. Cursor Rules + Postman MCP = an AI assistant that actually remembers your API patterns. wrote up how to set it up. starter kit included: github.com/Postman-Devr...

Just dropped: how to connect Cursor to your Postman workspace via MCP. Set up the MCP server, search APIs from the editor, generate client code, and keep docs in sync as you build. youtu.be/cKUXopUlGPg

Agent Mode in @getpostman finally lets you pick your model. Opus 4.5, GPT 5.2, whatever works for you. Sounds small. It's not. About damn time. (support for Opus 4.6 and GPT 5.3 coming soon too) The new Postman drops March 1st.

MCP Apps recently launched. AI tools can now return interactive UIs instead of just text. Postman already supports them. New post breaks down what this means for API developers. 🔗https://buff.ly/cru6lbq

Been testing Postman's native Git workflows for months. .postman directory in my repo. Collections in feature branches. Environments that merge with my code. It's about damn time. 🔥 The new Postman drops March 1st.

I spent the weekend building an agent skill for Postman. Seriously, Anthropic's skills are wicked awesome.

You're vibe coding wrong (And it's not your fault) Last week I was talking with a colleague about all the side projects I've got going on, and he said offhandedly "After hearing how you code now, I think I'm vibe coding wrong." It's all on my Substack! open.substack.com/pub/sterling...

I've always wanted to be an action figure! I love this prompt from Gemini that took a photo of me and turned me into an action figure.

Thank you to everyone who attended my session at API World last week on Building Agenting Workflows with MCP. After my session, I had quite a few attendees ask me for the slides. Over the weekend I updated my website (www.sterlingchin.com#talks) with many of my recent talks!

AI passes the Turing test, but it's not conscious. I've been mulling this over for a few months, but then @mustafasuleymanai.bsky.social's essay where he coined the phrase "Seemingly Conscious AI" took it over the top The reality is that we're not ready for SCAI open.substack.com/pub/sterling...

What are the odds, just enjoying a glass of wine and some apps at the Boroughs Market in London, and someone walks up and asks about my shirt. Yes, MCP is everywhere now! By the way, you can find the shirt here: www.etsy.com/listing/4313...

I have watched this clip a hundred times and I still giggle EVERY. SINGLE. TIME @willjohnson.bsky.social and @focusotter.bsky.social brought a special kind of energy to Web Dev Challenge I don't think we will (should?) see on the show again 😆 full episode: codetv.link/wdc/s2e1

I feel like I live in a bubble in a bubble. I spent some time over the weekend with some long time friends who are also developers. We started talking shop, as one does when you're in a group of developers.

WEB DEV CHALLENGE IS BACK 🔥 this was a HUGE effort by so many people and I can’t wait for y’all to see what we have in store this season - team challenges - upgraded studio - bigger builds - even more web dev fun watch the full first episode now: codetv.link/wdc/s2e1

Had a blast this week on the Web Dev Challenge with partner @dorkrawk.bsky.social ! Thanks @jason.energy @codetv.dev @getpostman.bsky.social for the experience and all my new friends @focusotter.bsky.social @willjohnson.bsky.social @sterlingchin.bsky.social @abbeyperini.dev @dangitalex.wtf

This week I'm heading to Berkeley to participate in a video shoot for @getpostman.bsky.social, and be on the Stack Overflow podcast. There is so much to do, and so little time to do it all.

Tech leadership is about surrounding yourself with the right people. People who don't always agree with you. People who will challenge your assumptions. People who will provide feedback. But it has to be built around trust. Trusting those around you.