Emma Starks Webb

human inference engine. Comms @augmentcode | Former @circleci @coursera @launchsquad

[Augment Code @augmentcode]

"Excited, anxious, invigorated."

That's how one engineering leader described going AI-native. We asked 218 others how they feel.

The results? Remarkably consistent:
"Insecurity, mistrust, hope."
"Optimistic, excited, threatened."

It's the same people, holding many feelings at once.

That's the baseline running through our new report, The State of AI-Native Engineering in 2026, co-authored with @VinayPerneti and @EmmaStarks.

[Emma Starks Webb @EmmaStarks]

@sathaxe not just for dads 😆

[Augment Code @augmentcode]

Adobe Principal Engineer Lars @trieloff shares his top 3 tips for getting real results from AI coding agents.

Use your actual codebase, pick the right model for the task, and know when to step in yourself

[Emma Starks Webb @EmmaStarks]

@RayFernando1337 Forked it and rebuilt for tvOS in Intent, made a version with terrible jokes for my kids 😎

[Emma Starks Webb @EmmaStarks]

@augmentcode

[Emma Starks Webb @EmmaStarks]

This is exactly why we're building Intent.
https://t.co/lq5nERz4jq

[Andrej Karpathy @karpathy]

Expectation: the age of the IDE is over
Reality: we’re going to need a bigger IDE
(imo).

It just looks very different because humans now move upwards and program at a higher level - the basic unit of interest is not one file but one agent. It’s still programming.

[Amelia Wattenberger 🪷 @Wattenberger]

https://t.co/KISd1HZWnB

[Augment Code @augmentcode]

https://t.co/CuTwpvZL9V

[Emma Starks Webb @EmmaStarks]

@augmentcode There's a new 𝗌̶𝗁̶𝖾̶𝗋̶𝗂̶𝖿̶𝖿̶ default model in town.

[Augment Code @augmentcode]

GPT-5.4 is now the default model in Augment, and it’s free for a limited time.

[Emma Starks Webb @EmmaStarks]

@augmentcode @guygr still waiting on those TPS reports

[swyx @swyx]

this might be the single best timed called shot in the history of AIE. I now think about this talk almost ~daily and have direct line of sight to the nonstop onslaught of new post-IDE form factors for agentic engineering.

@RealGeneKim and @Steve_Yegge really nailed this one, no notes. and they called out one of the predominant shifts in 2026 coding, in Nov 2025. i'm still shocked how -I- myself have changed opinion this dramatically in the last 3 months, because unlike appearances I'm actually not an early adopter of things personally (although I serve early adopters for a living). So by the time -I, a perennially left-of-mid-bell-curve person- have come around to the idea, then you really, really know its here.

well: it's here. @Wattenberger just showed me what she and the Augment team have been cooking and yeah, this is the "ADE" or whatever three letter acronym you wanna call it. Cursor 2.0 was a toe dip. Claude folded it into their chat app. Codex formalized the Conductor patterns. Amazon Kiro went hard on Spec Driven Dev. but Intent... this feels like every good idea i've heard in code agent management rolled into one app that, very generously, does not lock you into only using Augment's inhouse coding agent.

I'm in awe at all these smart people I get to talk to because yeah the future of how software is made is happening right in front of my eyes and people will ask us what it was like during this golden age for the rest of our lives.

[Augment Code @augmentcode]

@gdb feels like such a wasted opportunity every moment your greg brockman agent isn't running

[Augment Code @augmentcode]

Intent is our vision for what comes after the IDE.

AI has changed how we build software. But, it’s also made our workflows messier.

One agent is great. Two work. Past that, things fall apart fast. Prompts go stale, context lives everywhere, and you end up spending more time on the tedious work of orchestrating agents.

The bottleneck isn’t writing code anymore. It’s keeping the agents aligned.

That’s why we built Intent.

[Augment Code @augmentcode]

Today we’re launching Context Engine MCP. After 1,000s of beta testers and overwhelming feedback, it’s now available to anyone.

[Emma Starks Webb @EmmaStarks]

We’ve all worked with people who leave extremely pedantic, “well actually…” comments on every doc you write.

And then you have the folks who only chime in when things really matter - their voice matters. That’s how we built
Augment Code Review.

[Augment Code @augmentcode]

Introducing Augment Code Review, powered by GPT 5.2. It's the #1-ranked AI code reviewer across precision, recall, and overall quality.

Free for the first week for every paying customer, and free for open source projects.

[Igor Ostrovsky @igoro]

Users love our Context Engine. Last week, we made it available to all agents as an MCP server.

Today, we're sharing our 🚀Context Engine SDK🚀. What we do with context, you can do too.

You can build agents and tools that retrieve from codebases, docs, configs (and more)!

📚 Quickstart: https://t.co/75VLgSMoHt
💡 Examples: https://t.co/QmwDOtvISe

More to come in the next couple of weeks!

Here's what you can build with it 🧵

[Emma Starks Webb @EmmaStarks]

New model dropping
Lightweight, powerful, cheaper
Try it share feedback

[Augment Code @augmentcode]

Claude Haiku 4.5 is now live in Augment Code.

In our internal evals, we found it delivered ~90% of Sonnet 4.5’s performance at 34% faster response speed.

We're giving up to 20 free user messages over the next two weeks to everyone subscribed to a monthly paid plan once the pricing migration is complete — no action required. Rolling out today.

[Emma Starks Webb @EmmaStarks]

people say AI code gen creates huge bottlenecks in code review.
when we solve AI code review @augmentcode , what will the next bottleneck be?

[Cameron Custer @cam_custer]

When I read the review while I was writing the postmortem I saw that the only comment the agent left was about fixing the nil pointer check! If only an agent had reviewed this code we could have prevented that outage.

[Augment Code @augmentcode]

Claude Sonnet 4.5 is now the default model for Augment Code.

We’re rolling it out to all customers over the next 24 hours, where it will be available alongside Sonnet 4 (for a limited time) and GPT-5 in the model picker.

Here’s how Sonnet 4.5 compares to Sonnet 4: