Your AI security analyst, with a person approving every change.
Onam AI is the AI security analyst for Onam Security. Ask about your findings, attack paths and data security in plain language. It answers from your own Onam Security data, shows the evidence for every number, masks sensitive values, and suggests fixes for a person to decide. It never changes your cloud without that approval. Every step is recorded.
Drawing with sample data. Some capabilities are in early access or on the roadmap (see availability below). No change reaches your cloud without approval.
Evidence on every claim
Sensitive values masked
Suggests fixes; a person approves every change
Status
What you can use today, and what is still coming
Onam AI is new. We label every capability on this page so you never have to guess whether something exists. Nothing marked “On the roadmap” is available, and no date is promised for it.
Available
In Onam Security today, for every customer.
AI Assistant in Onam Security
Ask questions about your posture in plain language; specialists query your findings and cite them. Read-only.
Early access
Running on the Onam platform and enabled per organisation by invitation. Agents answer and propose; nothing changes your cloud.
Workspace
Ask Onam AI in plain language, each reply attributed to the agent that produced it, with a context panel for evidence, tasks and suggested fixes.
Orchestrator and visible plans
A multi-step question becomes a plan you can see — which agent, which skill, in which order — before and while it runs.
Asset Agent and Security Agent
Assets, relationships, crown jewels, findings, exposure and attack paths over the Onam Security inventory and findings, on AWS first.
Sensitive values masked
Answers name the resource and the finding; secrets, keys and sensitive data values are masked.
Evidence on every claim
Each number cites the skill, tool, query, rows and scan time that produced it.
Approval centre
One queue for every suggested change, diff first, with rollback and blast radius shown before the decision.
Activity and audit trail
Every turn, tool call, decision and approval recorded append-only, with a hash-chain check that nothing was edited.
Reports
A conversation or task exported with its evidence preserved.
Kill switch and autonomy ceiling
Stop all agent activity for your organisation; cap how far agents may go — read, analyse, recommend, simulate, propose.
In development
Built or specified; its data feed or enablement is not in place yet.
Compliance Agent and Data Agent
Built; waiting on the compliance-results, exposure and relationship feeds.
Change proposals with rollback
Automation Planner proposals with exact change, rollback and dry run; blast-radius inputs are being connected.
Pre-built workflows
Multi-step procedures such as audit preparation and exposure remediation, with approval steps built in.
On the roadmap
Designed, not offered. No date is promised.
Executing approved changes
The actor applies an approved change in an isolated sandbox, validates it and rolls back on failure. Built and tested; enabled for no customer.
Azure, Google Cloud and Kubernetes actions
AWS first; the design keeps provider specifics inside tools so agents do not change.
Event triggers and a workflow builder
Start investigations from events; compose workflows that cannot publish an execute step without an approval step.
Customer-authored agents
Needs a sandbox and certification model that does not exist yet.
The answer is in your findings. Getting it out takes an analyst.
Take a real question: “which internet-exposed production databases hold regulated data, and how could an attacker reach them?” The answer touches posture, identity, network, data security and attack paths. Today someone opens five views, combines filters and joins the results by resource by hand.
Today, by hand
Five views, several filters, one spreadsheet join
Skilled work that ties up a senior engineer
Stale the moment it is finished
No evidence anyone can audit, a screenshot at best
The fix happens out of band, unlogged
With Onam AI
Ask once; the orchestrator plans the steps across agents
Answers come from your Onam Security findings, not a model's recollection
Every number cites the query, rows and scan time behind it
Sensitive values are masked in every answer
Fixes are suggested with a diff and a rollback, and a person decides
In early access Onam AI reads the Onam Security inventory and findings, on AWS first.
The workspace
A team-chat layout with the controls of an operations console
The workspace looks familiar because chat is already in your muscle memory. But chat alone cannot carry a plan, an approval or an audit trail, so three rules set it apart.
Every claim is inspectable
Numbers and names in an agent’s reply link to the skill, query, rows and scan time that produced them.
The plan is visible before it runs
A multi-step request shows its steps first, so you can stop it before it starts.
Actions arrive as changes to review
A proposed change is a distinct card: bordered, diff first, with explicit decision buttons.
Onam AI · ChatIllustrative · sample data
# Exposed production assets
Agents in this conversation: Asset · Security
Which production assets are reachable from the internet, and which of them have critical findings?
Plan · 2 stepscomplete
✓Assetdiscover_assets214
✓Securityquery_findings12
AsAsset Agentdiscover_assets · 214 rows
214 production assets in the selected accounts; 9 are classified as crown jewels.
SeSecurity Agentquery_findings · 12 rows
12 of them carry a critical finding. The top three allow SSH from 0.0.0.0/0. evidence E-101
1 recommended change · approval required · Review
Ask the agents… (@Security to target one)Send
Chat with the agents: navigation on the left, each agent’s reply in its own attributed card, and a context panel for evidence, tasks and actions. Illustrative mockup drawn from the design specification with sample data — not a screenshot of a customer environment.
Needs you
Home, the approval queue and your inbox
Ask
Chat, the assets the agents see, and the agent directory
Run
Tasks, workflows and reports
Govern
Knowledge you give the agents, the activity record, and settings including the kill switch
The specialist agents
Specialist agents, each with a declared job and a declared limit
Each agent is a versioned definition rather than a prompt: its purpose, level, skills, tools and permissions are data that can be reviewed. An agent invokes skills; skills invoke tools; only tools touch anything outside the platform. Automation works in two modes: a planner that proposes and an actor that may execute only from an approval.
Who may do what. L1 agents read and recommend; L2 agents write proposals only; the L3 actor runs only from an approval record.
Asset Agent
Early access
L1 · Investigator · Read and recommend
“What do we have, how is it connected, and what is a crown jewel?”
Finds and summarises assets by cloud, account, region, type, environment and criticality
Maps relationships and dependencies between resources, for the blast radius of a finding or a fix
Identifies crown-jewel assets and classifies assets
Proposal flow is built; blast-radius inputs are being connected.
Automation Agent — actor
On the roadmap
L3 · Actor · Execute an approved change
“Apply exactly what was approved, check it worked, undo it if not.”
Re-reads the target and aborts if it changed since approval
Applies the approved artifact — nothing wider — with short-lived, scoped credentials
Validates the result and rolls back automatically on failure
Tools
cloud.*.write (scoped, one hour)repo.pull_requestcloud.change.planevidence.store
Never: start from chat — only from an approval record.
Built and tested in the platform; not enabled for any customer.
Full definitions (skills, tools, permissions and known limits for every agent) are in the agent reference.
The orchestrator
The orchestrator routes the work and never answers on its own.
The orchestrator turns a request into a plan: it detects the intent, picks the agents, orders the steps (in parallel where nothing depends on anything else), passes each step the previous step’s result, and joins the answers. It has no access to security data itself, so it cannot answer a question unaudited.
Plan cardIllustrative · sample data
Plan · 4 stepspaused for approval
✓Assetdiscover_assets214
✓Securityquery_findings12
✓Securityrecommend_remediation1
…Automationbuild_change_artifact—
Step 4 changes the cloud, so the plan stops here until a person approves it.
A plan pauses where a step would change the cloud, and waits for a person. Illustrative mockup drawn from the design specification with sample data — not a screenshot of a customer environment.
QuestionAnswered by one agent.
“How many production instances are in this account?”
InvestigationSeveral agents, results joined.
“Which exposed assets have critical findings, and which attack paths run through them?”
Action requestA plan, a proposal and an approval.
“Close SSH from the internet on these instances.”
ReportA synthesised document with its evidence.
“Give me the exposure summary for the board.”
Conflicts reach you. If one agent says “close this port” and another says “a production service depends on it”, the orchestrator does not pick a winner. Both positions and their evidence are shown, and you decide. A silently resolved conflict is a wrong answer in a confident tone.
Approval and governance
No setting lets an agent skip the approval gate
There is no autonomy level, tenant setting or flag that lets an agent change your cloud without a recorded human approval. Risk is assigned by policy, never by the agent, and can only be raised automatically, never lowered: production targets, paths to high-value assets, regulated data, missing rollback and bulk changes all push a change up a class.
Approval centreIllustrative · sample data
Approval requiredHIGH
Restrict SSH ingress — sg-example · prod-web-tier
Requested by Automation planner · task T-example
Change
- 0.0.0.0/0 tcp/22
+ 10.20.0.0/16 tcp/22
Blast radius
4 instances · 1 auto-scaling group · 2 business services
⚠ 2 SSH sessions from outside 10.20.0.0/16 in the last 24h
Why
Critical finding F-example · on a path to a crown-jewel database · evidence E-101
Rollback
Restore the previous rule · pre-state captured · reversible
Bound to change hash (sample) · expires in 7 days · target re-checked before execution
ApproveRejectModifySimulate
The approval card leads with the exact change, then blast radius, reason and rollback, so the approver sees what will change before anything else. Illustrative mockup drawn from the design specification with sample data — not a screenshot of a customer environment.
Risk
Who must approve
For example
Low
None
Any read or analysis; adding a tag; enabling a log
Medium
One approver
Resizing a non-production instance; encrypting a new bucket
High
One approver plus a dry run
Narrowing a production security group; changing a production IAM policy
Critical
Two distinct approvers, one an organisation admin; dry run; change window
Deleting a production database; changing an organisation-level policy
An approval binds to the change’s hash, so approving one change cannot authorise another.
The target is re-read just before execution; if it drifted, the approval is superseded.
Approvals expire. Critical changes need two distinct people.
Agents can never hold approval authority. The database refuses to record it.
Review time is measured, so rubber-stamping becomes visible to admins.
Reading is cheap because it is safe. Changing your cloud is deliberately expensive.
Evidence and audit trail
Every claim links to its evidence
Every factual claim an agent makes carries the skill, the tool, the query, the rows and the scan it came from. When the data cannot support an answer, the agent says it cannot verify it. Every turn, tool call, decision and approval is written to an append-only record, chained so that an edit or a deletion is detectable.
Evidence cardIllustrative · sample data
Evidence E-101copy
Claim
12 production assets carry a critical finding
Agent
Security Agent · L1
Skill
query_findings v1.0
Tool
cei.query
Query
Q-example · show query
Rows
12 of 12 (not truncated)
As of
sample time · scan example
Source
security findings · inventory
Re-runOpen
Open any number to see how it was produced, and re-run it. Illustrative mockup drawn from the design specification with sample data — not a screenshot of a customer environment.
Activity · audit trailIllustrative · sample data
Hash chain: intact — no record edited or removed
Time
Actor
Event
Target
Risk
14:02:11
you
conversation.started
—
Low
14:02:13
Orchestrator
plan.created
4 steps
Low
14:02:19
Asset Agent
tool.called · cei.query
214 rows
Low
14:02:27
Security Agent
tool.called · cei.query
12 rows
Low
14:07:40
Automation planner
approval.requested
sg-example
High
14:21:05
you
approval.approved
hash (sample)
High
Who did what, when and why, for people and agents alike, with a check that the chain is intact. Illustrative mockup drawn from the design specification with sample data — not a screenshot of a customer environment.
Security architecture
Built on the assumption that the model can be fooled
The controls that protect your cloud do not rely on the model behaving well. They sit in code, in the call path, where a refusal stops the request and is itself recorded. These are design commitments of the platform.
Tenant isolation at every layer
Your data never crosses to another customer in a query, cache, memory, model call, event or log line. Each layer is isolated and tested on its own, so a bug in one layer does not on its own open your data to anyone else.
Zero-trust agents
An agent is an untrusted principal. Its scope is verified on every call, it cannot change its own definition or permissions, and it can never exceed the person it acts for.
Prompt-injection defence in code
Text from your cloud is labelled as data, never as instruction. The decisive control is the policy engine and tool gateway: a persuaded model still cannot call a tool its agent does not hold.
One model gateway
All inference goes through one gateway, to approved models only, in the region agreed with you. Customer data is never used to train a model.
Kill switch and budgets
Stop all agent activity for your organisation from settings. Every task has step, time and cost ceilings; when one is reached, the task stops and says what is left undone.
Fail safe
On ambiguity, timeout, missing data or policy doubt, the platform stops and reports. A domain that is unavailable is named in the answer, never hidden.
Five things it will never do
1No change to your cloud without a human approval recorded against a named person. There is no autonomy setting that removes it.
2No data derived from another customer, ever — not in a query, a cache, a prompt, a memory or a log line.
3No answer it cannot ground in a tool call. “Unable to verify” is a designed answer, not an error.
4No agent can widen its own permissions, call an unregistered tool or use a model that is not approved.
5No workflow continues past a failed validation step.
Each use case shows the agents involved, what you get back, and whether a person must approve anything.
Find internet-exposed critical assets
Early access
“Show me critical production assets reachable from the internet.”
Agents
Asset → Security
You get
A table of assets with exposure type and severity, with evidence on every row.
Approval
None — read only
Triage a new critical finding
Early access
“Is this finding real, and what does it actually reach?”
Agents
Security → Asset
You get
The finding in context: the resource, what depends on it (its blast radius), the attack paths it sits on and a suggested fix.
Approval
None — read only
Identify excessive IAM permissions
Early access
“Which identities have far more access than they use?”
Agents
Security
You get
Identities ranked by unused privilege, each with the policy and finding that shows it.
Approval
None — read only
Review a newly connected cloud account
Early access
“We just connected this account. What should I worry about first?”
Agents
Asset → Security
You get
An inventory summary, the crown jewels and the highest-risk findings for the new account, ready to export as a report.
Approval
None — read only
Prepare compliance evidence for an audit
In development
“Prove control 8.2 held all quarter.”
Agents
Compliance → Data → Security
You get
Control status with dated evidence assembled into an audit package.
Approval
None — read only
Find sensitive data exposed publicly
In development
“Which public buckets hold regulated data?”
Agents
Data → Security
You get
Data stores by classification and exposure, without ever reading the data itself.
Approval
None — read only
Create a remediation plan
In development
“Plan the fix for SSH open to the internet on these instances.”
Agents
Security → Automation planner
You get
An exact change, its rollback, its blast radius and a dry run, waiting in the approval queue.
Approval
A human decides
Execute an approved security remediation
On the roadmap
“Apply the approved change to the production security group.”
Agents
Automation actor
You get
Applied in a sandbox, validated, rolled back automatically if validation fails, with the evidence package stored.
Approval
Required; two people for critical changes
Questions
Common questions
What is Onam AI?+
Onam AI is your AI security analyst for Onam Security. You ask questions about your findings, attack paths and data security in plain language; it answers from your own Onam Security data, cites the evidence, masks sensitive values, and suggests fixes. It never changes your cloud without a person's approval.
Can I use Onam AI today?+
It is in early access: running on the Onam platform and enabled per organisation by invitation, starting with AWS and the Onam Security inventory and findings. The AI Assistant inside Onam Security is available to every customer today.
Will Onam AI show secrets or sensitive data in an answer?+
No. Answers name the resource and the finding behind them; secrets, keys and sensitive data values are masked. For data security questions it works from classifications and counts, never the content of your data.
Can Onam AI change my cloud?+
Not in early access. It suggests fixes; it does not apply them. Organisations start at the “propose” ceiling: agents answer, investigate and propose, and nothing touches your cloud. Executing an approved change is on the roadmap, and even then it needs a named person to approve the exact change, a write role you create in your own account, and it runs in an isolated sandbox that validates and rolls back.
How is this different from the AI Assistant?+
The AI Assistant answers questions about your findings inside the Onam Security console. Onam AI is a workspace above it: multi-step investigations with visible plans, evidence cards, tasks, an approval centre and an audit trail, run by specialist agents with declared permissions.
Is my data used to train models?+
No. Customer data is never used to train or fine-tune a model. Agents call approved models through one model gateway, in the region agreed with you, one customer's data per call.
What stops an agent being tricked by text in my cloud?+
Resource tags, policy descriptions and finding text are treated as untrusted data and labelled as such. The decisive control is in code: the policy engine and tool gateway check every call against the agent's declared scope, so a persuaded model still cannot call a tool its agent does not hold.
Onam
Onam AI works with Onam Security.
Onam Security finds and ranks risk across cloud, SaaS and code. Onam AI, your AI security analyst, answers questions about those findings and suggests fixes.
Early access is by invitation and starts on AWS with your Onam Security data. Onam AI answers and suggests fixes; nothing changes your cloud without your approval.