From the Cisco edition of November 2, 2026
Futurum: Cisco Project Quarry brings detection-as-code to AI agents, but value depends on rule quality, full traces and neutral governance
The Futurum Group · Industry analyst firm (independent of Cisco) · Global
- Publisher
- Futurum Group
- Original publication
- Futurum Group, Oct. 30, 2026
- Source retrieved
- 2026-11-03
What happened
Futurum describes Project Quarry (open-sourced Oct. 28) as a rule language and engine that evaluates whole agent sessions. It argues value is capped by rule-library quality, few SOC teams have tuned detections on agent traces, and Quarry looks like a Cisco-owned Snort-style format rather than a neutral Sigma-style standard. Its 1H2026 survey (N=929) found 55% lack technical ability to detect or contain a compromised AI agent. Futurum notes Cisco says Quarry does not replace runtime authorization.
Why it matters
Moderate for SLED agencies and universities piloting AI agents: provides an independent check on Cisco's agent-detection claims (archived Cisco blog, Oct. 28) and frames what to require before adopting.
Evidence and measured results
Analyst commentary plus a cross-industry survey; no testing of Quarry. Futurum discloses AI-assisted writing.
Limitations and uncertainty
Survey is not SLED-specific; no hands-on evaluation; analyst opinion; AI-assisted content disclosed.
Put this evidence to work
Lighthouse Advisory interpretation, grounded in this source. Enriched 2026-11-03; this does not change the original publication date. Each role follows the same checklist so takeaways compare across sources.
Sales
Role takeaway
- Customer problem
- SLED teams deploying AI agents cannot yet detect agent misuse.
- Stakeholders
- CISO
- SOC lead
- AI program lead
- Records/privacy officer
- Discovery questions
- Do your agent platforms log full sessions including tool calls?
- Who owns agent security monitoring?
- Is runtime authorization in place for agent tools?
- Value hypothesis
- Bounded: trace capture plus session rules may improve visibility into agent misuse.
- Potential engagement
- An agent-logging and detection readiness assessment for one use case.
- Unsupported claims
- That Quarry is an industry standard
- Any detection accuracy
- That detection replaces authorization
Pre-sales engineering
Role takeaway
- Fit
- Early-stage fit for SOCs already on Splunk piloting agents.
- Architecture and integration
- Rules evaluate agent session traces; findings can flow to Splunk per Cisco.
- Prerequisites
- Full agent trace logging
- Splunk or other SIEM ingestion
- Rule tuning capacity
- Constraints
- Cisco-owned format; no neutral governance yet
- Starter rules only
- Traces may contain regulated data
- Security
- Pair with least-privilege tool scopes and approval for consequential actions.
- Proof of value
- Replay recorded sessions through starter rules
- Measure false positives and misses
- Confirm trace completeness
Delivery
Role takeaway
- Work
- Trace capture, rule pilot and tuning record for one agent.
- Dependencies
- Agent platform logging
- SIEM capacity
- Privacy review
- Ownership
- Customer SOC with AI platform team.
- Skills and adoption
- Analysts need agent-trace literacy.
- Governance checkpoints
- Privacy review of trace retention
- Review of rule portability
- Acceptance criteria
- Proposed: 100% session trace coverage for pilot agent
- Proposed: documented false-positive rate after tuning
- Risks
- Trace gaps
- Rule maintenance burden
- Lock-in
Implementation considerations
Lighthouse Advisory interpretation across the operating dimensions a public-sector buyer must settle before this evidence becomes a design. Each note answers the question under its heading for this specific source.
Architecture and integration
What must connect, and where does the AI sit in the workflow?
Requires full agent session traces (messages, tool calls, MCP) to be logged to be useful.
Governance
Who approves, reviews and stays accountable for outcomes?
Watch for neutral governance; avoid committing to a single-vendor rule format without portability.
Security and privacy
What data, permissions and controls need testing?
Detection does not replace runtime authorization for agent actions.
Accessibility and workforce
Who is affected, and what skills or accommodations follow?
Agent-trace detection requires new analyst skills.
Procurement
What should contracts, pricing and exit terms secure?
Prefer portable formats; ask about governance roadmap in procurement.
Operating model
Which teams own the service once it runs?
Agent monitoring needs joint SOC and AI platform ownership.
Publication history
- 2026-11-02Cisco · Issue 054 resources
Stable resource ID: futurum-cisco-project-quarry-agent-detection-analysis-20261030