streamline ENGINEERING
100x faster with Agentic AI
Build specialized SRE, Platform And DevOps Assistants leveraging our massive library of pre-built automation. They respond to alerts and chats, draft tickets and more.
Thousands of Agentic AI tools for your environment this afternoon
Sync your K8s / cloud accounts to auto-configure thousands of AI tools relevant for your stack. Start with our read-only defaults and get your first Engineering Assistant running in < 1 hour.
Streamline the 70% of engineering time spent outside of code
24/7 developer self service
This team is reducing developer escalations by 62%, giving dev teams their own specialized Engineering Assistants to troubleshoot CI/CD and infrastructure issues in shared environments.
Bring on-call back in-house
This team is reducing MTTR and saving cost, replacing an under-performing outsourced on-call service. They are giving Engineering Assistants to their expert SREs that respond to alerts by drafting tickets.
Traditional automation vs RunWhen
RunWhen’s AI Engineering Assistants find automation and create variable workflows. Adding AI-native automation to your stack is 100x faster than traditional automation initiatives.
WitBh traditional tools, automating repetitive ops work typically takes more time than it saves. This automation is then fragile and flooded with dependencies that break the entire workflow.
With Runwhen we transform your workflow
How RunWhen works
How it works
Each atomic task is a code snippet. We create an embedding to each task and store a pointer to it in a vector database, when an alert or request comes, we compare its embedding with the vector database, suggest the best match based on that and continue this iterative loop until the incident is resolved. There’s no LLM so its fully secured. To connect to the designated systems using a local runner.
How to set it up
Install the RunWhen Local agent in your cluster to scan Kubernetes, AWS, GCP and Azure accounts.
By default it will sync the RunWhen read-only libraries. You can add more public or private libraries over time.
A scan of a typical small/medium size cluster will import several thousand tasks in a few minutes.
How it works for alerts
Install the RunWhen Local agent in your cluster to scan Kubernetes, AWS, GCP and Azure accounts.
By default it will sync the RunWhen read-only libraries. You can add more public or private libraries over time.
A scan of a typical small/medium size cluster will import several thousand tasks in a few minutes.
Average setup time: 20 minutes.
How it works for chat
Spend more time on improving platform capabilities and less time doing basic dev/test troubleshooting. With 24/7, instant availability of AI troubleshooting assistants, platform owners will see a dramatic increase in ‘customer satisfaction’ from their app developers and start to free up engineering bandwidth for platform roadmap or strategic projects.
Automation can cut observability costs
Some of our most popular automation libraries copy logs directly from pods and VMs into Jira/Github tickets. Connecting this to VSCode, alerts and CI/CD webhooks removes the need to ingest and store 90%+ of non-prod logs.
Where to next?
The default Assistants that come out of the box are designed for Platform/SRE teams to give to developers for Kubernetes troubleshooting. However, it doesn't stop there...
Connect To Slack
Connect AI Assistants to Slack so anyone on the team can ask an Engineering Assistant for root cause or remediation help 24/7.
Connect To Alerts
Connect Digital Assistants to alerts so they can run autonomous troubleshooting sessions and report back with a root cause, severity, suggested next steps and a full diagnostic report with output from all automation they ran.
Add No-Code Steps
Add No-Code "Generics," simple application troubleshooting steps like checking a REST API, a SQL query or pre-canned log search. These require only a few lines of configuration to be Engineering Assistant-ready
Connect To CI/CD Pipelines
.png)
Connect to CI/CD pipelines and use Engineering Assistants to run thousands of troubleshooting tasks. They report back on issues found and severity, creating metrics for operational readiness.
Distribute The VSCode Plugin
When you are ready to give your developers the gift of self-serve troubleshooting, consider distributing our VSCode plugin.
Chaos Engineering?
.png)
Connect to your chaos engineering stack or use our lightweight fault-injection scripts to see how Digital Assistants respond to incidents in staging before going to production
Manage to SLOs
.png)
RunWhen's defaults include automation to generate fine-grained SLIs, SLOs and Monthly Error Budgets based on community benchmarks that are useful in dev, staging and production.
A (paid) community?
Expert authors in our community receive royalties and bounties when RunWhen customers use their automation. The community's efforts span infrastructure, cloud services and platform components alongside popular OSS components, programming languages and frameworks.
.svg)
Running a lean team means you need the best engineers you can find...
Do you really want your top engineers spending time on work that someone in industry already automated?
