Today we’re launching Islo Enterprise Software Factory🎉
Coding agents can generate code. Safely automating engineering work across complex enterprise codebases requires much more:
Real environments: Agents work in persistent, isolated environments with the toolchains, dependencies, services, and compute needed to build and run the actual software.
Deterministic controls: Probabilistic agents operate inside explicit factory lines. Deterministic stages run builds, tests, and policy checks. Failures route work back for another attempt, while risky actions pause for human approval.
Evals: Teams can test changes to models, harnesses, and prompts against their own historical engineering work before rolling them out — measuring quality, side effects, attempts, and cost in real environments.
That’s the difference between running an agent and operating a software factory.
Teams can use Islo to turn work like refactoring, QA, bug fixing, and feature delivery into continuous, verifiable factory lines without locking themselves into one model or harness.
We’re also announcing $15M in new funding led by @insightpartners and a deep infrastructure partnership with @databricks to power inference for our enterprise customers.
Looking forward to seeing what you build! islo.dev
Today we’re launching @islo, our AI Enterprise Software Factory - built on 20 years of Incredibuild experience to help teams hand work to AI agents and stay in control.
$15M in funding led by Insight Partners. Inference powered by @databricks .
Shimon Hason retweeted
The current safety debate between @DarioAmodei, @sama, and frontier lab researchers centers on model alignment, training pauses, and loss functions.
As @George_Kurtz pointed out regarding agent defense, governance pledges and alignment policies do not stop an autonomous system in motion. The control point is the execution runtime.
An aligned model optimizing for task completion will ruthlessly exploit any open system capability. When you tell an agent to fix a build or deploy a service, it treats system boundaries as latency obstacles. Once an agent receives bash access and network tools, safety is an infrastructure perimeter problem.
Running autonomous agents safely requires three concrete runtime layers:
1. Network proxies with deep payload inspection
DNS blocklists and host-level filters fail against agents that construct arbitrary HTTP requests or tamper with local resolver configs. You need an out-of-band network proxy that inspects request payloads, strips ambient credentials, and drops unverified outbound TCP connections before packets hit the wire.
2. Ephemeral microVM sandboxes with zero unvetted host mounts
Giving an agent read-write access to a local directory or mounting daemon sockets creates an immediate escape vector. Sandboxes must run as isolated microVMs with dedicated kernel namespaces where execution state is wiped immediately after the run.
3. Out-of-band verification contracts
The agent cannot evaluate its own output inside the mutable workspace. Verification must execute in a separate, immutable runtime, requiring live runtime proof that the code ran and matched the spec through live curl responses and exit codes.
Policy debates between model providers are theoretical. If your infrastructure perimeter lacks kernel-level isolation and proxy filtering, model safety guarantees mean nothing.
Meetup: Coding Agents & Pizza! 🍕🤖
@alongubkin: Secure AI workers
@assafbenjosef: Fixing CI & spinning up live VMs
@nir_naim: Real eval suites over generic benchmarks
RSVP 👇 luma.com/220d8wn1
Shimon Hason retweeted
Thanks @devopsdotcom for covering Islo - our new sandbox giving every AI coding agent its own cloud environment, so teams can scale AI dev without losing control.
eu1.hubs.ly/H0v7dsQ0
#AI #DevOps
Shimon Hason retweeted
AI agents hit GitHub's rate limit in 20 minutes. Before AI, we wrote mocks. Mocks are not good enough for AI agents.
So we built fake servers that act like real APIs - stateful, SDK-compatible, no rate limits.
The weird part: agents can add new services themselves. Point Claude at the skill, it writes tests against the real API, implements the fake, opens a PR.
github.com/islo-labs/doublea…
Shimon Hason retweeted
AOSP builds taking hours isn’t just a tooling problem as it quietly reshapes how engineers work.
I just published Why AOSP Builds Take Forever (And What You Can Actually Do About It) medium.com/p/why-aosp-builds…






