Who owns the truth after the incident
When production breaks, the answers are usually already in your docs, code, and logs — and so is the leftover. Nami investigates across those sources and leaves a next move, a handoff, and something you can publish. She does not become a second wiki.
Our mission
Senior expertise for every team you define
The best incident responders don't just know the answer — they know where to look and how to reason through the evidence. That expertise is rare, and it usually lives in a handful of people's heads.
We built Nami to make that expertise available to everyone. She searches your knowledge base, code, and logs, reasons like the experienced specialist on that team — whether that's production support, security, platform, or whatever you define — and explains her findings in the way that team works best. After she finds the gaps, Nami helps your sources stay the source of truth.
The leftover gets organized: a next move, a handoff, and something you can publish. Incidents get faster as a side effect, and the system gets smarter every time your team investigates.
In one sentence: NamiFlow is an AI investigation navigator that investigates with you — then flows the investigation across teams. Official site: namiflow.ai. For the investigation method, see How it works.
Product facts
What NamiFlow is
What it is
NamiFlow is an AI investigation navigator. Nami investigates alongside your team: she searches connected sources, reasons over the evidence, and always leaves a concrete next move.
What it is not
Not a chatbot that chats about incidents. Not a report generator that dumps findings and walks away. Not an autonomous agent that silently changes production on your behalf.
Trust contract
Collaborative, not autonomous. Deterministic logic is guardrails and governance (access, team style, safety). The investigator is AI reasoning over your evidence. If qualifying questions are configured, she asks those first. When blocked later, she asks a reasoned checkpoint question — not a vague request for “more context.”
Who owns the truth
Your people decide what is source of truth. When an investigation finds a gap, Nami surfaces it and drafts the knowledge so you can publish it back to the source that should own it — after every investigation.
Sources (live)
Confluence (runbooks and docs), Google Drive (shared folders), GitHub (source code), CloudWatch (logs), Datadog (log search), and Jira (escalation create + optional comment writeback). Connectors marked coming soon in the product are not claimed as available yet.
Access model
Read-only by default. The only things Nami ever writes are the ticket and the SOP you approve — each one a click you make, each one logged. Confluence, Google Drive, GitHub, and Jira connect over OAuth (Drive folder access is Viewer share to NamiFlow’s reader); CloudWatch through a cross-account IAM role you create and can revoke; Datadog via API/app keys. You choose what to connect and can disconnect at any time. Nami does not deploy code, commit code, edit existing runbooks, modify logs, or change production.
Who it’s for
Any production team that investigates incidents and hands work off — production support, engineering, security, platform, or whatever you define. Each team can receive answers tuned to how they work, with investigation context carried forward so the next person does not restart from zero.
What we value
Principles behind the product
Clarity over noise
Incidents are chaotic enough. Nami gives each team a clear, actionable answer instead of a wall of logs.
Built for people
Different teams think differently. We meet each one where they are, in the language and depth they use.
Speed with rigor
Fast answers only matter if they're right. Nami reasons through evidence before she recommends a fix.
Knowledge that compounds
Every investigation should make the next one easier. We turn resolved incidents into lasting runbooks.
Collaborative, not autonomous
Nami investigates with your team. You stay the actor on every production change. Qualifying questions, when configured, are your intake — not a black-box guess.
Six sources, one thread
Confluence, Google Drive, GitHub, CloudWatch, Datadog, and Jira — connected when you choose, searched together in one investigation.
One navigator, every team's language
Create as many teams as you need. Each gets its own communication style and tools — so production support, security, platform, or any other team hears Nami in the way they work, without losing the investigation trail.
FAQ
Short answers for humans and assistants
What is NamiFlow?+
NamiFlow is an AI investigation navigator. Nami investigates with your team across connected runbooks, code, and logs, reasons over the evidence, and always leaves a concrete next move — resolution steps you can take now, or one targeted question that unblocks the investigation.
Is NamiFlow an autonomous AI agent?+
No. NamiFlow is deliberately collaborative, not autonomous. You remain the actor on production changes. Deterministic rules act as guardrails (access boundaries, team communication style, safety). The investigation itself is AI reasoning over your evidence — not silent remediation.
How does Nami decide what to ask next?+
If an admin configured qualifying questions, Nami asks those first — they are your org’s intake, not invented prompts. After that (or if none are set), checkpoint questions are reasoned from the current investigation state — for example an incident time window to scope logs, or a failed request_id to trace a workflow. They are not keyword-matched templates. Each question should be explainable: why that input, and what Nami will do with the answer.
Who owns the truth?+
Your people do. They decide what is source of truth. When an investigation finds a gap, Nami surfaces it and drafts the knowledge so you can publish it back to the source that should own it — after every investigation. She does not invent a source she cannot point at, and she does not keep a second wiki.
Which systems can Nami connect to today?+
Live connectors today: Confluence (runbooks/docs), Google Drive (shared folders), GitHub (code), CloudWatch (logs), Datadog (log search), and Jira (escalation create + optional comment writeback). You choose which to connect. Other providers shown as coming soon in Connections are not claimed as available yet.
What access does Nami need, and what can she change?+
Read access by default. Confluence, Google Drive, GitHub, and Jira connect over OAuth (Drive folder access is a Viewer share to NamiFlow’s reader service account); CloudWatch through a cross-account IAM role you create and can revoke; Datadog via API/app keys you paste. You choose which sources to connect and can disconnect any of them whenever you want. Nami does not deploy code, commit code, edit runbooks, modify logs, or make production changes. Writes exist only for Jira escalation: creating an issue and posting updates/comments to a linked issue — each requires a person to click, never automatic silent writes.
Ready to investigate with Nami?
Start a 14-day free trial with your team and see Nami investigate on your real production stack.