Domain Playbooks

Customer-Support Agents

Optimize deflection subject to a near-zero confident-wrong-answer rate: grounded answers autonomous, transactions gated, tone graded in the eval, clean handoff over a confident guess.

Data & Analytics Agents

The failure mode is a confidently wrong number: schema/semantic-layer grounding, read-only execution, verification as a separate stage, and abstention scored above confident error.

DevOps & SRE Agents

Read-only first because the blast radius is production: diagnosis before remediation, runbooks as tested tools, limits in the tool signature, change control unchanged by the operator being a model.

Research & Synthesis Agents

A fabricated source voids the whole deliverable: retrieve-then-write-then-verify, citation faithfulness as a hard constraint, disagreement preserved not averaged, depth vs breadth as a bounded budget.

Sales & GTM Agents

The failure mode is automated spam at scale: value in research/personalization not volume, consent as an upstream fail-closed gate, human sign-off scaling with reach, spam-risk weighted heavily in the eval.

Finance agents

Where agents earn their keep in finance — reconciliation, research synthesis, KYC review — and the hard rails (audit, determinism, regulator-readable trails) they must carry.

Healthcare agents

Charting, prior auth, intake triage — the few healthcare jobs where agents shave real labor, and the privacy + clinical-safety guardrails you cannot ship without.

Legal agents

Discovery, contract review, citation checking — where legal agents already work, where they hallucinate, and what supervision they need by jurisdiction.

Adapting a Playbook to Your Domain

The meta-method behind every playbook: derive a new vertical by answering five questions in order — job, autonomy by reversibility, tools as grounding-and-limit, eval mirroring the cost asymmetry, structural guardrails.