Relvy (YC F24) – On-call runbooks, automated
Hey HN! We are Bharath, and Simranjit from Relvy AI (https://www.relvy.ai). Relvy automates on-call runbooks for software engineering teams. It is an AI agent equipped with tools that can analyze telemetry data and code at scale, helping teams debug and resolve production issues in minutes. Here’s a video: [[[https://www.youtube.com/watch?v=BXr4_XlWXc0]]]A lot of teams are using AI in some form to reduce their on-call burden. You may be pasting logs into Cursor, or using Claude Code with Datadog’s MCP server to help debug. What we’ve seen is that autonomous root cause analysis is a hard problem for AI. This shows up in benchmarks - Claude Opus 4.6 is currently at 36% accuracy on the OpenRCA dataset, in contrast to coding tasks.There are three main reasons for this: (1) Telemetry data volume can drown the model in noise; (2) Data interpretation / reasoning is enterprise context dependent; (3) On-call is a time-constrained, high-stakes problem, with little room for AI to explore during investigation time. Errors that send the user down the wrong path are not easily forgiven.At Relvy, we are tackling these problems by building specialized tools for telemetry data analysis. Our tools can detect anomalies and identify problem slices from dense time series data, do log pattern search, and reason about span trees, all without overwhelming the agent context.Anchoring the agent around runbooks leads to less agentic exploration and more deterministic steps that reflect the most useful steps that an experienced engineer would take. That results in faster analysis, and less cognitive load on engineers to review and understand what the AI did.How it works: Relvy is installed on a local machine via docker-compose (or via helm charts, or sign up on our cloud), connect your stack (observability and code), create your first runbook and have Relvy investigate a recent alert.Each investigation is presented as a notebook in our web UI, with data visualizat
FL score
out of 100
Verdict
high confidence
Competition
13
competitors found, emerging market, funded players
Trend
No signal yet
A complex AI-driven solution for automating on-call runbooks and debugging for software engineers, facing high technical hurdles.
The pain
The gap
Build angle
Strengths
- Addresses a high-severity, high-urgency pain point for engineering teams.
- Large and rapidly growing market with clear willingness to pay for effective solutions.
- Clear value proposition: reduced MTTR, less on-call burden, automated debugging.
- Differentiated approach using runbook-anchored AI to tackle a hard problem.
Risks
- Extremely high technical complexity for a solo builder, requiring deep AI, observability, and systems expertise.
- AI accuracy in autonomous root cause analysis is a major unproven assumption (current benchmarks are low).
- Long time-to-market for a useful MVP; not a weekend or short-term project.
- Crowded competitive landscape with well-funded incumbents, despite the specific AI angle.
- High development and ongoing maintenance costs for AI infrastructure and data integration.
Next steps
- For a solo builder, this idea is too complex and risky to pursue. It's a 'skip'.
Fly Labs Method
Is the pain real, is there a gap, is it the right time, can one person build it.
- Problem clarity
- 27
- Solution gap
- 15
- Willingness to pay
- 20
- Buildability
- 5
The problem is real, severe, and specific, with a clear need for better automation in on-call debugging. However, the solution is highly complex and not suitable for a solo builder.
Value Equation
Dream outcome and how likely it feels, against the time and effort it costs.
High-value problem in a growing market with a differentiated AI approach, but complex to build and execute.
One-Person Business
Curiosity pull, identity fit, and a path from free value to paid for a solo creator.
Clear problem with good monetization potential, but extremely complex to build and unsuitable for a solo founder due to technical demands and lack of simplicity.
Viral Frameworks
Hook strength, shareability, and how cheaply it can be tested.
Clear target and value proposition, but high technical risk and complex distribution make it challenging for a micro-SaaS.
Builder Lens
Evidence the problem exists, timing, defensibility, and a model that fits on a napkin.
Strong demand for solving on-call pain, but high technical hurdles for AI-driven debugging make future-fit and initial surprises critical.
Why this verdict
Five lenses, one composite. How scoring works
The angle
This weekend
- For a solo builder, this idea is too complex and risky to pursue. It's a 'skip'.
Who is already there, emerging market
PagerDuty provides a digital operations management platform that helps organizations identify issues, bring together the right people, and automate incident response.
Pricing: Free tier for up to 5 users; Professional plan starts at $21 per user per month; Business plan offers more features.
Rootly is an AI-native incident management platform that streamlines on-call scheduling, incident response, retrospectives, and status updates through intelligent automation and deep integrations.
Pricing: Tiered, value-based pricing.
FireHydrant is an incident management platform that streamlines the incident response process through automation and integrations.
Pricing: Yearly licensing: $9,600 per year for the entire platform; Incident management only is $6,000 per year (on-call is extra and priced based on number of engineers).
incident.io is a Slack-integrated incident response platform designed for rapid-growth companies, focusing on seamless integration and automated incident management.
Pricing: Starts from $16 per month, billed yearly. Custom pricing for enterprise-focused plans.
Opsgenie is a robust incident management solution integrated within the Atlassian ecosystem, offering alerting, on-call schedules, and streamlined workflows.
Pricing: Free for up to 5 users, then $9-$29 per user per month.
Jira Service Management is an ITSM platform that centralizes and manages ITSM workflows including ticketing, incident management, and request management, often adopted by companies with existing Atlassian infrastructure.
Pricing: Around $21 per agent per month.
xMatters provides a service reliability platform that automates workflows and ensures teams are alerted to and can resolve incidents quickly.
Pricing: Free for up to 10 users, then custom pricing.
- RedwoodVisit
Redwood offers a low-code runbook automation platform that automates routine IT operations tasks across on-premises, cloud-based, and containerized environments.
Pricing: Undisclosed.
- Octopus DeployVisit
Octopus Deploy provides runbook automation alongside deployments, allowing control over infrastructure and applications for tasks like routine maintenance and emergency recovery.
Pricing: Undisclosed.
- StackstormVisit
Stackstorm is an open-source, event-driven automation platform that connects and automates various tools and services by reacting to real-time events.
Pricing: Open-source (free), enterprise version available with undisclosed pricing.
Azure Automation offers Runbook Studio, a feature that allows users to create, manage, and execute automated workflows for routine tasks across cloud and on-premises environments.
Pricing: Billing based on job run time minutes and watcher hours used in the month; free included units available.
- TemperstackVisit
Temperstack enhances existing monitoring tools with alert health, automation, incident management, and AI-runbooks, empowering developers to optimize alerts, triage, and auto-heal with human oversight.
Pricing: Undisclosed.
What they charge
Recent news
- Launch HN: Relvy (YC F24) – On-call runbooks, automated
Hacker News, April 09 2026
- Relvy AI: Automated On-Call Runbooks for Engineering Teams!
TechTrends Now, April 09 2026
- The LLM cost of an AI SRE investigating production alerts
Relvy AI Blog, March 15 2026
- OpenRCA - How we improved Claude's accuracy by 12 percentage points on root cause analysis
Relvy AI Blog, March 9 2026
- The State of On-Call Runbook Automation in 2026
Relvy AI Blog, February 16 2026
Market signals
The global on-call scheduling software market was valued at USD 3.6 billion in 2024 and is projected to reach USD 39.7 billion by 2033, growing at a CAGR of 28.24%. This growth is driven by the increasing need for effective employee scheduling, the proliferation of remote and hybrid work models, and the rising demand for automation in various sectors, including healthcare and IT. Key trends include the incorporation of AI and machine learning for forecasting scheduling, a focus on mobile-first solutions, and the leveraging of real-time analytics.
What frustrates people
- Expensive pricing with hidden add-ons and confusing tier structures from established players like PagerDuty, leading to unpredictable bills and a feeling of paying for unused features.
- Alert fatigue and overwhelming noise, where a majority of alerts do not require immediate action.
- Complex, outdated, or difficult-to-navigate user interfaces in existing tools.
- Lack of automation for the actual incident management process, requiring manual coordination, communication, and resolution.
- Inflexible on-call scheduling that makes it difficult to adapt to specific team needs or page individuals outside of predefined service hierarchies.
Semble – Code search for agents that uses 98% fewer tokens than grep
Hey HN! We (Stephan and Thomas) recently open-sourced Semble. We kept running into the same problem while using Claude Code on large codebases: when the agent can't find something directly, it falls back to grep, reading full files or launching subagents. This uses a lot of tokens, and often still misses the relevant code. There are existing tools for this, but they were either too slow to index on demand, needed API keys, or had poor retrieval quality.Semble is our solution for this. It combines static Model2Vec embeddings (using our latest static model: potion-code-16M) with BM25, fused via RRF and reranked with code-aware signals. Everything runs on CPU since there's no transformers involved. On our benchmark of ~1250 query/document pairs across 63 repos and 19 languages, it uses 98% fewer tokens than grep+read and reaches 99% of the retrieval quality of a 137M-parameter code-trained transformer, while being ~200x faster.Main features:- Token-efficient: 98% fewer tokens than grep+read- Fast: ~250ms to index a typical repo on our benchmark, ~1.5ms per query on CPU (very large repos may take longer)- Accurate: 0.854 NDCG@10, 99% of the best transformer setup we tested- MCP server: drop-in for Claude Code, Cursor, Codex, OpenCode- Zero config: no API keys, no GPU, no external servicesInstall in Claude Code with: claude mcp add semble -s user -- uvx --from "semble[mcp]" sembleOr check our README for other installation instructions, benchmarks, and methodology:Semble: https://github.com/MinishLab/sembleBenchmarks: https://github.com/MinishLab/semble/tree/main/benchmarksModel: https://huggingface.co/minishlab/potion-code-16MLet us know if you have any feedback or questions!
AI
Postgres extension for BM25 relevance-ranked full-text search
Last summer we faced a conundrum at my company, Tiger Data, a Postgres cloud vendor whose main business is in timeseries data. We were trying to grow our business towards emerging AI-centric workloads and wanted to provide a state-of-the-art hybrid search stack in Postgres. We'd already built pgvectorscale in house with the goal of scaling semantic search beyond pgvector's main memory limitations. We just needed a scalable ranked keyword search solution too.The problem: core Postgres doesn't provide this; the leading Postgres BM25 extension, ParadeDB, is guarded behind AGPL; developing our own extension appeared daunting. We'd need a small team of sharp engineers and 6-12 months, I figured. And we'd probably still fall short of the performance of a mature system like Parade/Tantivy.Or would we? I'd be experimenting long enough with AI-boosted development at that point to realize that with the latest tools (Claude Code + Opus) and an experienced hand (I've been working in database systems internals for 25 years now), the old time estimates pretty much go out the window.I told our CTO I thought I could solo the project in one quarter. This raised some eyebrows.It did take a little more time than that (two quarters), and we got some real help from the community (amazing!) after open-sourcing the pre-release. But I'm thrilled/exhausted today to share that pg_textsearch v1.0 is freely available via open source (Postgres license), on Tiger Data cloud, and hopefully soon, a hyperscalar near you:https://github.com/timescale/pg_textsearchIn the blog post accompanying the release, I overview the architecture and present benchmark results using MS-MARCO. To my surprise, we were not only able to meet Parade/Tantivy's query performance, but exceed it substantially, measuring a 4.7x advantage on query throughput at scale:https://www.tigerdata.com/blog/pg-textsearch-bm25-fu
AI
Consus (YC F24) – LLM gateway for companies handling sensitive data
Hey Hacker News! I'm Eric, the founder of Consus. We route all AI requests to ITAR restricted and controlled unclassified information (CUI) compliant infrastructure. Consus itself satisfies ITAR restrictions, and we recently completed our FedRAMP equivalency audit against the 410 FedRAMP High controls. FedRAMP High is the U.S. government’s strictest security baseline for cloud services handling sensitive unclassified data. A breach of this data could cause severe or catastrophic harm. Achieving FedRAMP equivalency, or authorization, is required before processing CUI information.Demo: https://youtu.be/6MYxJe6P4oYAerospace and defense is experiencing rapid growth. Unfortunately, most companies are struggling to use AI because of necessary data protections & compliance risk. These companies can move even faster if they could use the AI tools that most other industries take for granted.I spent most of my career prior to Consus in aerospace & defense. I launched national security payloads at SpaceX, and was an early employee at Castelion. I’ve watched first hand how compliance red-tape makes it difficult for companies to adopt new technologies and trust vendors that touch their sensitive data. For example, I worked with a satellite manufacturer that doesn’t allow any AI tools, even for non-sensitive work.Even as AI has become extremely useful over the past 9-12 months, I was surprised by how many aerospace & defense companies refused to touch it. They could see how it could be helpful, but they were scared about model providers training on their data, violating an ITAR rule, or risk losing new business because of a failed cyber assessment. These are all rational fears.There were a lot of ways to solve some/all of these problems, but we focused on building a compliant AI inference layer that can "plug" into any AI tool or workflow. Just as OpenRouter integrates with most tools, Consus can connect to tools like ChatGPT or Clau
AI
Questions about this idea?
FlyBot reads the scoring and gives you a second opinion on “Relvy (YC F24) – On-call runbooks, automated”.