Today weโre launching Islo Enterprise Software Factory๐
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 โ measuring quality, side effects, attempts, and cost in real environments.
Thatโs 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.
Weโre 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! https://t.co/ovwb02TsNo
Meet the speakers.
Training AI models to out-execute attackers - Lior Moshe, CTO @ Arithmetic.
Autonomous Engineering | Nov 4 | Tel Aviv
https://t.co/XnJQtDNOdT
Meet the speakers: David Mark
You have agents. Do you have a factory?
David Mark, VP Platform Eng @ Incredibuild, on the infra that makes agents ship.
Autonomous Engineering, Nov 4, Tel Aviv
https://t.co/xyHOTDKoZL
Meet the speakers!
How do you get to #1 on the Enterprise RAG Benchmark?
You eval the harness, not just the model.
Regev Ben Simon, CTO @ https://t.co/cKPzPm9CnR, breaks it down at our upcoming Autonomous Engineering meetup.
Nov 4, Tel Aviv
https://t.co/EbwBcCN7Vj
Meet our first speaker for the upcoming meetup!
Your agents shipped 200 PRs this week. How many work?
@islolabs founder @AdamGolds on evals for software factories.
Autonomous Engineering meetup, Nov 4, Tel Aviv
https://t.co/H6FNA8D6ez
On stage:
@AdamGolds Gold - https://t.co/StIkTT1bGi
Regev Ben Simon - https://t.co/YGNUkk1HOX
David Mark - @incredibuild
Doors 17:00, AWS Experience Floor 28. ID needed.
Agents write the code. Now the bottleneck is evals.
Autonomous Engineering meetup: Evals & Software Factories
Nov 4, Tel Aviv. Talks in Hebrew.
Register: https://t.co/oYkhHLgMp5
Last call: building infra for agents, tonight in SF ๐ฃ๐บ
6:00 PM - Adam Gold on evals for software factories, and how to actually make them work.
With @UnikraftCloud, Primitive, Abundant AI.
Doors 5:30.
https://t.co/JA7eslpXva
Tomorrow. San Francisco.
AI Infra Nights x Autonomous Engineering - @islolabs, Alien, Databricks.
A few spots left. Save yours โ https://t.co/aObKcyAwTm
09/24. SF - AI Infra Nights x Autonomous Engineering:
- Adam Gold (Islo) - trusting agents that push their own PRs
- Dhruv Gupta (Databricks) - Omnigent: many agent harnesses, one interface
- Alon Gubkin (Alien) - a cryptographic kill switch for SaaS data
https://t.co/N7Yh0eYg3e
"How we stopped working for our agents."
@AdamGolds on agents that verify their own fixes in a live env before you ever see the PR.
AI Infra Nights x Autonomous Engineering, SF, Sep 24 โ https://t.co/W7N5RkLdos
The infra under production AI, in one room in San Francisco.
AI Infra Nights and Autonomous Engineering are teaming up - Islo, Alien, Databricks on what breaks at scale and how they fixed it.
Thu Sep 24, limited spots. Request to join โ https://t.co/f2FIDdfTLa
Come meet @AdamGolds at SwampUp!
Let's talk about how our users are building their software factories.
Discounted tickets here: https://t.co/nNgTyGWTFh
Software now writes software - at agentic speed.
We're at @jfrog#swampUP 2026 in NYC, Sept 1-3. Come talk agentic software supply chain, self-healing SSCs + governing autonomous #AI agents.
25% off with incredibuild_vip: https://t.co/IO5daDkFqK
#swampUP#DevSecOps
uber built a context graph, self-healing CI, managed maintenance loops, and persistent cloud environments before they let agents write 70% of their PRs
you're not uber. don't build it yourself.