Does this security job need an agent or a workflow?

A job needs an agent only when the next step depends on what the last step found and cannot be written in advance. Split one real case into steps and mark each fixed or variable. Anthropic recommends "the simplest solution possible"; in the CVE-2021-44228 case below, 4 of 6 steps are fixed.

The question to ask

Q01. Does this security job need an agent at all, or would a fixed workflow with a model call inside it do the work? Put it to a builder as written. Put it to a vendor as: "Which steps of this job does your product decide for itself, and which run as fixed code?"

Anthropic separates the two shapes: "Workflows are systems where LLMs and tools are orchestrated through predefined code paths. Agents, on the other hand, are systems where LLMs dynamically direct their own processes and tool usage, maintaining control over how they accomplish tasks." Its rule for choosing: "we recommend finding the simplest solution possible, and only increasing complexity when needed. This might mean not building agentic systems at all." It also warns that "the autonomous nature of agents means higher costs, and the potential for compounding errors" (Building effective agents, read 19 Nov 2026).

Q01 comes first because every later question gets harder as the software gets more freedom. A workflow has a set of possible actions a reviewer can list. An agent that picks its own next tool call has a set bounded only by its permissions, which is why scope of change is the next page.

Worked example: one Log4j finding, step by step

Take a scanner finding for Apache Log4j2, CVE-2021-44228. NVD lists a CVSS 3.1 base score of 10.0 (vector AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H) and a publication date of 10 Dec 2021. CISA's Known Exploited Vulnerabilities catalog (release 2026.11.18) lists it as added on 10 Dec 2021 with a due date of 24 Dec 2021, 14 days later, and marks known ransomware campaign use as "Known". FIRST's EPSS lists it at 0.99999 with a percentile of 1.0 (100th) on 18 Nov 2026, the highest value the scale gives. Write down what a person does with that finding today and mark each step.

Steps written for this page from the vulnerability record data read on 19 Nov 2026 (NVD, CISA KEV).
#StepFixed or variableWhy
1Receive the finding and record asset, package and versionFixedSame fields every time
2Look up KEV status, CVSS base score and EPSS for the CVEFixedThree lookups by CVE identifier; for CVE-2021-44228 the answers are KEV listed, CVSS 10.0 and EPSS 0.99999
3Find every asset running an affected versionFixedOne query against the inventory
4Decide whether the affected code is used in a way that is exposed on this assetVariableWhich evidence to read next (build files, config, container layers, network exposure) depends on what the last read showed
5Choose upgrade, mitigation or exceptionVariable, within a tableThe choice follows a policy table once step 4 is answered
6Open the ticket with the due date from the policyFixedTemplate and date arithmetic

The result: 4 of 6 steps are fixed, one is variable and one is a lookup in a table. Step 4 is the only candidate for model judgment, and even there the evidence sources are a short list. The first version to build is a workflow: steps 1 to 3 and 6 in code, one model call at step 4 that is handed the build file and configuration and asked to summarize exposure, and a person who takes step 5. Its action set is two reads and one ticket write, and a reviewer can list it.

What would argue for an agent: on 30 past cases, step 4 needs a different evidence path in many of them, for example because the vulnerable library arrives through a vendored package in some repositories and a base image in others, and the workflow's fixed reads miss it. That is the test in the next section. The opposite case also exists: when every step is fixed and the inputs are structured, a model call adds cost and unpredictability, and a plain script or a playbook with no model is the right build. Steps 1 to 3 and 6 above are that kind of work.

A decision table from the result

Decision rule written for this page from Anthropic's definitions (read 19 Nov 2026).
What the 20 to 50 past cases showShape to carry forward
The workflow with one model call gets the right outcome in nearly every caseWorkflow. Stop here.
Failures come from model wording (a poor summary), not from the pathWorkflow, with a better prompt or a different model for that step. See choosing a model.
Failures come from the path: the needed evidence was in a place the fixed reads never visitedAgent for that step only, with a read-only tool list. Carry the failed cases into the tool register as the reason each tool exists.
The agent needs to write to production systems to get the benefitAgent, with every later question open, starting with approval points and stop and rollback.

Test it on your own findings

  1. Pick one finding type and write the steps a person takes, as above, with a real recent case.
  2. Build the workflow version with the model at one step. Run it on 20 to 50 past cases from your queue. Anthropic says "20-50 simple tasks drawn from real failures is a great start" (Demystifying evals for AI agents); how to label them is on success criteria and test sets.
  3. List each case the workflow got wrong and mark the cause: wrong path, or poor model answer. Only wrong-path cases argue for an agent.
  4. Record who accepted the extra cost and compounding-error risk, with the date.

A good vendor answer to the question above names the variable steps and shows the fixed ones. A weak one calls the whole job "agentic". Whether a playbook engine already does the fixed part is covered in agentic AI versus SOAR playbooks, and the choice to build or buy once the answer is agent is on build or buy.

Sources

  1. Anthropic, Building effective agents, read 19 Nov 2026
  2. Anthropic, Demystifying evals for AI agents, read 19 Nov 2026
  3. NVD, CVE-2021-44228, read 19 Nov 2026
  4. CISA, Known Exploited Vulnerabilities catalog (release 2026.11.18), read 19 Nov 2026
  5. FIRST, EPSS API, CVE-2021-44228 (values dated 18 Nov 2026), read 19 Nov 2026

Last reviewed 19 Nov 2026