OVERALL RATINGS
INSTALLS
1
SUPPORT
- Partner Supported
Key highlights of the appAI workflow automation for Jira — validators, conditions and post-functions, with your own AI key or zero-key Forge LLM
React to 68 Jira events, or run on a schedule
Listeners react to any of 68 Jira, Software and JSM events; scheduled jobs run on cron, once or per issue of a JQL scope. A plain-English AI condition gates each run; the work is code the AI wrote or an AI agent.
Validate meaning, not just structure
CogniRunner reads the meaning of your fields, attachments and issues, then blocks a transition when content fails your plain-English rule — and searches your project with JQL to catch duplicates.
Your AI, your key — local or cloud
Bring your own key for Anthropic, OpenAI, Azure, OpenRouter or Bedrock — or run models locally with LM Studio, or use the zero-key Atlassian Forge LLM. Switching providers never loses your settings.
Supporting media
More details
Listeners, Scheduled Jobs and a Rules REST API — two new ways to run, no transition needed.
- Listeners react to any of 68 Jira, Jira Software and JSM events, filtered by project, issue type, JQL, changed fields or a comment regex. An optional plain-English AI condition gates the run and fails closed. What runs is code steps (the same sandbox as static post-functions) or an AI agent with an allow-list of actions. Self-generated events are ignored by default, brakes stop loops, a redelivered event never runs twice, and you can test with a real issue in simulation.
- Scheduled jobs run on five-field cron in any IANA time zone — once, or per issue of a JQL scope — with a per-issue outcome in the history view.
- Rules REST API: mint a bearer token in Settings → API access and push listeners and jobs as JSON — single, batches of 100, partial updates, enable, test, run, logs.
- Also: serialized run counters, honest reporting of thrown non-Errors, atomic attachment capabilities.
Resources
App documentation
Comprehensive set of documentation from the partner on how this app works
Privacy and Security
Privacy and security questionnaire has been filled by the partner
Privacy policy
Atlassian's privacy policy is not applicable to the use of this app. Please refer to the privacy policy provided by this app's partner.
Partner privacy policySecurity program
This app is not part of the Marketplace Bug Bounty program.
Integration permissions
CogniRunner integrates with your Atlassian app
Version information
Version 3.3.0•for Jira Cloud
- Release date
- Sep 7th 2026
- Summary
- Listeners for 68 Jira events, cron scheduled jobs, AI agent mode, Rules REST API
- Details
CogniRunner is the AI workflow agent for Jira — three ways to run, one app. Native rules check structure; CogniRunner reads the meaning of fields, attachments and issues, then validates, decides and acts.
- On a transition: AI validators block with the reasoning shown; agentic JQL catches duplicates; post-functions write fields, comments, sub-tasks and documents — or run AI-written code at zero AI cost.
- On an event: listeners react to 68 Jira, Software and JSM events, filtered by project, JQL or changed fields, gated by an AI condition, with loop brakes built in.
- On a schedule: cron jobs in any time zone, once or per issue of a JQL scope, with a per-issue run report.
- Conditions: deterministic, zero AI cost, enforced everywhere.
- Bring your own AI: Anthropic, OpenAI, Azure OpenAI, OpenRouter, Bedrock — or local LM Studio, or the zero-key Atlassian Forge LLM.
- Provision listeners and jobs over a REST API.
Open source on Atlassian Forge (Apache-2.0).
- Payment model
- Paid via Atlassian
- License type
- Apache License, Version 2.0 (ASL)