Alert fatigue
Analysts read the same low-value alerts all shift, and the real one hides in the noise.
For SOCs and security teams
Triage at the speed of the alert queue
Alert summaries, incident timelines, phishing email analysis, detection rule explanations and policy drafts. Help analysts focus on the threats that matter.
Faster triage
alerts summarised with context
Clean timelines
incidents written up quickly
Auditable usage
every call recorded
The problem
What is slowing you down today
Write-ups after the fire
The incident is contained. The timeline and report take another two days.
Unvetted AI tools
Analysts paste logs into whatever tool is handy, with no keys and no record.
Capabilities
Everything you need, nothing you don't
Alert summaries
Condense raw alert data into what happened, affected assets and suggested next steps.
Incident timelines
Order notes, chat logs and findings into a clean timeline for the report.
Phishing analysis
Explain the indicators in a suspicious email's headers and body text.
Detection rule explanations
Route to capability code for plain-English explanations of queries and rules.
Governed access
Keys shown once and stored only as a hash, per-account rate limits, full request history.
You control the inputs
Only what you send is processed, so you can redact secrets before a prompt leaves your systems.
Use cases
What teams run on it
01
Tier-one triage assist
Summaries attached to each alert in your case tool.
02
Incident reports
Executive and technical write-ups from investigation notes.
03
User-reported phishing
Fast explanations for the analyst handling the report.
04
Policy and awareness drafts
Readable policies and staff guidance.
How it works
From sign-up to production
- 1
Set your redaction rules
Decide what may be sent, and strip secrets and credentials first.
- 2
Integrate with your SOAR
Call the endpoint from your playbooks with a dedicated key.
- 3
Monitor the monitor
Watch request history and usage for every key.
Control
Built so you stay in charge
Keys you control
API keys are shown once at creation and stored only as a hash. Revoke any key instantly from Settings.
Spend you can see
Every request carries its own receipt: tokens in, tokens out, latency and price. Nothing is billed that you cannot trace.
Limits you set
Per-account rate limits and a free monthly allowance keep experiments safe before they become production.
Data you decide on
You choose exactly what you send. Repeat prompts can be served from your cache, and cache hits are never billed.
For developers
One endpoint. Every model.
Send a prompt and a capability, or name a model. One bearer key, one small JSON body, and a full receipt on every response.
curl https://YOUR-DOMAIN/api/ainf/inference \
-H "Authorization: Bearer $AI_INFERENCE_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: order-1042" \
-d '{"prompt":"Summarise this ticket in one line","capability":"chat"}'Questions, answered
How are API keys protected?
Keys are shown once and stored only as a hash. Revoke a key at any time and create a new one.
Should we send raw logs?
Send only what the task needs and redact secrets, credentials and personal data. You control every prompt.
Can we audit usage?
Request history records the model, tokens, latency, price and a short preview for every call.
Will it make response decisions?
No. It summarises and drafts. Analysts decide and act.
Give your analysts a sharper first look
Pilot with sanitised alerts on the free allowance.