Artificial intelligence startup Sazabi Inc. is emerging from stealth mode with a platform designed to replace conventional observability stacks. The company's approach focuses solely on log data, using AI agents to automate analysis and extract operational insights.
Sazabi argues that advances in AI make it possible to derive all necessary information from logs, thereby reducing complexity and storage expenses. "Fundamentally, logs are just events, metrics are aggregated events and traces are basically correlated events," stated founder Sherwood Callaway, a veteran of financial software firm Brex LLC and phone call automation platform Opkit Inc. "We only accept logs, and we create metrics and traces from those logs on the back end."
The platform, due for delivery by year-end, aims to simplify observability by minimizing the need for complex instrumentation and data pipelines. Sazabi collects log data and employs AI for large-scale interpretation. "That approach reduces the complexity around instrumentation and the complexity in our data pipeline and storage infrastructure," Callaway explained.
At its core, an AI agent continuously analyzes log streams, identifies anomalies, and determines issues warranting attention. The system automatically generates alerts based on historical patterns. "We have our agent running in perpetuity in the background, looking for anomalies, investigating them and deciding whether they’re worth your attention," Callaway said.
Agents manage alert generation and routing, ensuring fewer, more relevant alerts. Sazabi also offers a conversational interface, allowing engineers to query production systems using natural language. This enables "root cause in seconds what would typically require minutes or hours of digging through different screens in a traditional tool," according to Callaway.
The architecture combines log ingestion with an AI-optimized storage and query layer. Sazabi utilizes materialized views and summarized data representations to streamline information scanning. "We can take an hour’s worth of log data and summarize that into a much smaller package using language models," Callaway noted. "You only have to query the summary."
AI enhances storage efficiency by managing data retention, summarization, and tiering. Sazabi targets early-stage and growth-stage technology companies, recognizing their focus on rapid development and potential lack of specialized observability expertise. The platform is designed for integration with existing tools, allowing customers to adopt it without replacing their current infrastructure. "Just change the endpoint and we’ll be receiving logs," Callaway stated.
While incumbents add AI features, Callaway believes the shift toward AI-driven development necessitates entirely new observability models. "It will be very hard for legacy or incumbent vendors to completely retool their products," he concluded.
Sazabi is currently in the process of raising seed capital.