← All stories
● Covered by 1 source · 1 reportMedium impact1 neutral

Instacart launches Blueberry, an AI assistant for incident response

🔄 Updated 1d ago
New to BrevFeed? We gather this story from every outlet covering it into one summary — ranked by real-world impact, not just the latest headline — so you never miss what matters. What is BrevFeed? →

Key points

  • Blueberry is an AI-assisted incident response system.
  • It uses AI agents, operational data, and incident history.
  • The system provides root cause hypotheses in Slack within three minutes.
  • Diagnostic accuracy improved from mid-60% to high 90% range.

Introduction of Blueberry

Instacart has launched Blueberry, an AI-assisted system designed to help on-call engineers investigate and troubleshoot production issues. The system integrates multiple AI agents, operational data, and historical incident knowledge to offer engineers context and potential root causes during incidents.

Addressing Incident Response Challenges

Blueberry was developed to tackle the challenge of engineers spending significant time collecting context during the initial stages of an incident. This includes tasks such as identifying service ownership, reviewing deployments, analyzing logs and metrics, searching documentation, and comparing current symptoms with past incidents.

Performance and Integration

In April, Blueberry performed approximately 25,000 diagnostic passes across over 270 Slack channels. Instacart reported that grounding the system with 14 years of incident history improved diagnostic accuracy from the mid-60% range to the high 90% range. The system integrates with Slack-based incident workflows, allowing engineers to investigate issues directly within their existing collaboration channels.

AI Architecture and Functionality

Instacart CTO Anirban Kundu stated that Blueberry is part of the company’s exploration of agentic AI systems. When an alert is triggered, Blueberry launches about 10 subagents in parallel to generate a grounded root cause hypothesis in the Slack thread, typically within three minutes. The system combines AI reasoning with organization-specific operational knowledge, connecting agents with internal sources like incident history, service ownership data, logs, and deployments.

✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →

The daily brief

One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.

One email a day. Unsubscribe in one click, any time.

Today's brief

Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.

~7 min · 6 stories · Aug 15

▶ Play today's brief Listen on Spotify

New every morning, and the back catalogue is archived by date.

Reporting from

Instacart introduced Blueberry, an AI-powered incident response system that helps on-call engineers investigate production issues by providing context and root cause hypotheses. This system aims to reduce the time engineers spend gathering information during incidents, improving diagnostic accuracy by leveraging historical data and operational knowledge.