SECOPS
Agentic bot-surge investigator with enriched rule recommendation
An agent investigates a Cloudflare bot surge end to end — pulling edge data, enriching offending IPs and ASNs via threat intel.
How it runs
The automated pipeline, trigger to output.
- TriggerSurge investigation kicked off via webhookHTTP webhook
- ActionPull Cloudflare edge analytics for windowCloudflare
- ActionEnrich top IPs/ASNs with threat intelExa
- LogicWeigh legitimacy and draft rule + confidence
- OutputPost recommendation + evidence to SlackSlack
What it does
Runs an autonomous investigation rather than a fixed pipeline. Given a detected surge, the agent decides what to look at: it pulls Cloudflare traffic, enriches the top offenders with external reputation and ASN data, weighs false-positive risk, and writes a recommendation explaining whether to challenge, rate-limit, or hold.
When to use it
Use this for ambiguous surges where a simple threshold rule isn't enough — mixed legitimate-and-bot traffic, distributed sources, or new attack patterns. The agent's written reasoning helps a reviewer make a confident call instead of guessing from raw numbers.
How it works
- 1A webhook (from a detector or manual kick-off) starts the agent with the affected zone and time window.
- 2The agent pulls Cloudflare edge analytics and isolates candidate offenders.
- 3It enriches the top IPs and ASNs against an external threat-intel search to gauge reputation and known-bot status.
- 4A logic step has the agent weigh legitimacy signals and draft a recommended Cloudflare rule with a confidence rating.
- 5The recommendation and full evidence chain are posted to Slack for the operator to approve or override.
Set it up
What you configure once, before turning it on.
- 1Connect CloudflareWorkers, Pages, R2, KV — the edge stack.
- 2Connect ExaNeural search across the web.
- 3Connect SlackChannels, DMs, threads, mentions.
- 4Connect HTTP webhookTrigger any URL on agent actions.
- 5Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 6Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 7Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More SecOps workflows
Post-Revocation Verification and Audit Logging
After a key is revoked, it confirms the old credential actually fails, verifies the replacement works.
Page on-call when a WAF rule mass-blocks legitimate traffic
On demand or every few minutes, it detects a single Cloudflare WAF rule suddenly blocking a broad spread of ASNs and paths (a likely false-positive storm).
PII Content Scan on New Dropbox External Share
When a file gets an external Dropbox link, it reads the file content, uses an AI classifier to detect PII or secrets.
Compile a weekly WAF tuning review with trends to Confluence
Every week an agent rolls up Cloudflare WAF block clusters by rule and ASN, compares them to prior weeks for trend direction.
Sensitive Dropbox Link Owner Remediation Loop
When a newly created Dropbox shared link points to a sensitive file, this workflow DMs the file owner, gives them a deadline to justify or revoke it.
GitLab Push Secret Detection to Block and History Purge
On a GitLab push that contains a detected secret, it revokes the exposed credential, opens a tracking issue with git-history purge instructions.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.