AI spend is growing. Most leaders still don't know where. We'll be on the ground at @WeAreDevs 2026 (in San Jose, from Sept 23–25). If you want to learn how to control your AI spend, stop by the booth, check out talks from co-founders @jevering and Chris Waterson, OR book time with us here → guild.ai/we-are-developers-2…

That's a wrap for #splunkconf26! Thanks to the @splunk team for partnering with us on the breakout stage—and self-improving agents. If you missed us on the floor, check out our latest demo to find out how we reduced AI agent costs by 87% using our own Agent Optimizer youtube.com/watch?v=Q_UsP5WT… And if you're in San Jose next week, swing by the @WeAreDevs World congress and come grab some piping-hot swag from the Guild swag forge. Until next time!

Self-improving agents aren't just possible. They're repeatable with @Splunk and Guild. Self-improving agents have four hard problems to solve: - Observability - Evaluation - Governance & Risk - Accountability And we solved all four with one closed loop that can be managed with Guild and Splunk: Build → Deploy & Govern → Monitor & Collect → Evaluate & Optimize → Approve & Redeploy And because agents should never stop improving, the loop never closes. Thanks to everyone who came out to our session at #splunkconf26 to see how we're building agents that work smarter every day. And a special shoutout to Guildmaster Spencer Wanlass for bringing the 🔥 of knowledge to the stage.

We had a blast last night chatting all things agent operations at our first ever Guild Table Dinner. Shoutout to all the smart minds who came out to share in the conversation (and the hors d’ouvres). If you’re at #splunkconf26 looking for an amuse bouche from the Guild team, grab some time at the link below and we’ll give you a bite-sized demo of what we’ve been cooking up this summer in the Guild forge. guild.ai/conf-2026

For the last few months, we’ve been relying on our internal Guild Software Factory to plan, implement, review, triage, and maintain our engineering work. Now we're making it available for everyone out of the box. Sign up to try the factory for free and we'll give you 100M tokens to get you shipping. Visit app.guild.ai/factory to learn more.

The agent you already trust deserves a real home—and you shouldn't have to rebuild it to give it one. That's why we're excited to announce that Guild now fully supports agents written for @openclaw and @LangChain . The same typed interface, the same version history, and the same governance. All in one place. At Guild, we believe that every enterprise needs a centralized operations layer to run and govern their agents. And we're committed to making that vision a reality. We started with Goose agents this summer. Now we're three. And we're still just getting started. Your agent worked on a laptop. Now it runs everywhere (with the guardrails on). Learn more 👉 guild.ai/blog/engineering/br…

Rethinking your AI infrastructure? Wondering what Guild.ai is all about? Guild CEO @jevering is going LIVE @ 8:30 PT w/ hosts @RonfortMartin and @MichaelWaitze on @AGTPinsights!

We built a Software Factory for ourselves first. Now we're making it available to everyone. Here's some quick stats after just a few months using our Software Factory internally: 🔥 34% of merged PRs at Guild are now written autonomously by our Software Factory 🔥 56% of all code fixes are created by the Software Factory 🔥 and 91% of merged Factory PRs need no additional engineer commits Want to see it in action? Check out the demo in the link below 👇 youtube.com/watch?v=HW4doj2g…

ICYMI check out @jevering , @ChrisWaterson , and the rest of the Guild team on @insidestartups with @willsclips_ for an inside look at the platform, the office, and the many bespectacled builders crafting the next generation of AI infrastructure. youtube.com/watch?v=IyaPJtR3…

34% of merged PRs at Guild are now written by Software Factory, autonomously. 56% of all code fixes come from it. 91% of merged Factory PRs need no additional engineer commits. Software Factory is changing how we build at Guild. It’s not another coding agent. It’s a system of specialized agents that continuously finds work, plans it, implements it, tests it, reviews it, and hands a finished PR back to an engineer. And it runs all the time. A few more numbers from our own codebase: - 70% of fixes for auto-detected issues come from the Factory - 81% of log-triage fixes are Factory-written - 80% of code changes to the Guild CLI are written by the Factory - 75% of Factory PRs are accepted and merged - 25% of alerts have a fix PR up within 90 minutes - 97% reduction in time-to-fix for some workflows - About $12 in model spend per merged Factory PR The important part is what those numbers add up to. The Factory is taking entire categories of engineering work off the team: production bugs, flaky tests, noisy logs, small fixes, and maintenance work that would otherwise sit in a backlog or interrupt an engineer. Humans still merge every PR. That’s deliberate. Agents do the work. People own the outcome. Coding agents were the first step. The next step is engineering systems that can continuously find, route, execute, review, and maintain work. We built ours for ourselves first. Now Software Factory is available for other teams to run on Guild. Try Software Factory → app.guild.ai/factory

Want to reduce AI costs without making your agents… well…worse? Us too. And that’s exactly why we built Optimizer. Launched today, Optimizer is the easiest way to improve agent costs across the enterprise. Built on the back of Guild’s new Spend Explorer, Optimizer will automatically: 1️⃣ Create an eval from your existing production history 2️⃣ Test variables against your latest quality score 3️⃣ Provide a detailed recommendation to optimize cost and performance With Optimizer's recommendations, teams can instantly— - Discover the cheapest model for any task - Trim tools to reduce unused complexity - Optimize prompt structures for tighter token counts - And replace unnecessary LLM calls in workflows when code can do the job better Each recommendation comes with a report on cost and quality impact. Agree with the recommendation? Deploy any change in a single click. Internal tests have seen some agent costs reduced by as much as 87% with no reduction in quality. Spend Explorer gives you the bill. Optimizer makes it actionable. Interested? Read more: guild.ai/blog/product/optimi…

At Guild, we believe open source isn't just a workflow—it's part of our DNA. We're building the operating system for agentic development, ensuring agents are the next generation of secure, controllable contributors. We're proud to partner with @linuxfoundation —steward of the Linux kernel and home to the @AgenticAIFdn (AAIF), where open standards for agentic AI are taking shape. Their team has been instrumental in pushing us to build more open-source-friendly releases, including support for the goose framework, which now lives under the AAIF. We’re excited to support their team in building, running, and managing their own internal agents on the Guild platform. Read James Everingham’s full take on the future of development here: guild.ai/blog/news/linux-fou…

Big thanks to Will Phillips for coming by the office and featuring Guild on INSIDE Startups. Check out the full episode below.

AI spend is up. But most leaders still can't say where it's going. Join us at #splunkconf26 (Denver, Sept 14–17) where we'll be on-hand talking all things agent governance and cost control for the enterprise. And if self-healing agents are on your bingo card, be sure to catch our session with the Splunk team-- "From Code to Self-Improving Agents: Building Observable Agents at Scale with Guild and Splunk" Tues Sept 15 @ 10:30 am. Wanna connect one-on-one? Grab a meeting here → guild.ai/conf-2026 We'd love to see ya.

It’s 2026. Do you know where your AI budget is? Last week we launched our new AI Spend Explorer — completely for free. Connect your platform provider and in <2 minutes, we’ll show you where every dollar went (across providers, models, users, teams, and agents) with a projection for the rest of the month. Files are read-only. There’s no credit card required. And setup is a single copy-paste. But why build this? And more importantly, why make it free? AI spend is growing fast, but most companies still can’t tell you where that money is going—or more importantly, if they could have paid less. Which agents are creating value? How much do they cost? And how do you make them dramatically more efficient without making them... worse? First, we’ll show you the bill. Then we'll can help you act on it. Visit spend.guild.ai to try it for yourself.