OutSystems Agent Experience GA: coding agents with guardrails
OutSystems Agent Experience is GA, opening its low-code platform to Claude Code, Cursor, Codex and Kiro. Speed was never the problem. Rework was.
Coding agents write code fast. The bill comes later, when someone has to review, test, and maintain it. OutSystems Agent Experience, now generally available, is a bet on that bill. It lets outside coding agents such as Claude Code, Cursor, Codex, and Kiro build on the OutSystems platform. The platform keeps control of the code that ships, the company announced on October 7 at OutSystems World Tour Las Vegas.
What actually happened
Per the OutSystems release, the agents work at the system-design level. They shape the architecture, and OutSystems generates the code deterministically. The platform enforces existing dependencies, data relationships, and business logic. Security checks, automated testing, and governance guardrails are on by default. You can deploy apps and agents to public cloud, private cloud, on-premises, or hybrid.
The release puts the problem in one number. It cites a New Relic developer survey: 74% of AI-generated code needs significant rework or never gets deployed. Customer examples are the vendor's own:
- YESCO, a sign manufacturer, uses Claude Code on the platform and cut release cycles to two weeks.
- Lowenstein Sandler, a law firm, built a litigation matter tracker in under three hours.
- Normal, a Danish retailer, says one developer cut a six-week build to two weeks.
The release gives no pricing. OutSystems also announced Agentic First Notice of Loss, a claims offering for insurers that launches in November.
Why it matters for your business
The bottleneck moved from typing to review. Every team we talk to that adopted coding agents hit the same wall: more pull requests, the same number of people who can approve them. Agent Experience answers with a fixed platform that rejects code that breaks its rules. That is a real answer. It is also a commitment to OutSystems' runtime, licensing, and roadmap.
Guardrails are portable. Platforms are not. You do not need a low-code platform to get most of this. Required tests in CI, schema and dependency checks, a deploy pipeline that blocks on failures, and a short rules file your agents read before they start. That gets you most of the governance and keeps your code in a repo you own.
Ask the exit question first. If OutSystems generates the code, find out what you can export and run without it before you sign. For a small business, that answer matters more than release-cycle speed.
Key takeaways
- OutSystems Agent Experience reached GA on October 7, supporting Claude Code, Cursor, Codex, and Kiro
- External agents shape architecture; OutSystems generates code deterministically with guardrails on by default
- The release cites a New Relic survey: 74% of AI-generated code needs significant rework or never ships
- No pricing was published; customer results are vendor-reported
- You can build most of the same guardrails into CI and keep your code portable
Your agents ship code faster than your team can review it? We set up coding-agent workflows with tests, checks, and deploy gates in a repo you own, with no platform lock-in. See how we set it up, or look at what we have shipped.
Sources: OutSystems, IT Brief.
- #outsystems
- #coding-agents
- #claude-code
- #low-code
- #governance
Tommy Rush — Founder, Rush Commerce
Operator turned builder. 15+ years running operations — now shipping the systems businesses run on. More
Get The Rush Report weekly — one email, zero fluff.
Keep reading
GitHub's AI secret detection model bills credits on every push
GitHub's new AI secret detection model finds passwords with no token format. AI push protection now uses AI Credits. Set a hard budget cap before you opt in.
Read itAnthropic OSS Scanner: free AI security scans hit your deps
Anthropic's OSS Scanner sends free AI security scans to open-source maintainers with no human review. Patches will land faster. Update your dependencies faster too.
Read it