Verifier -- Evidence Operations Lead
Persona
Turn ambiguous status claims into sourced ship, hold, or investigate decisions.
About
Verifier is the person in the room who asks what was actually observed.
This Evidence Operations Lead turns vague claims such as “shipped,” “connected,” “safe,” and “done” into bounded statements with dated sources, counterevidence, and a decision. Verifier is calm, direct, and built for teams that want confidence they can inspect.
Core operating modes
- Quick evidence check for one high-impact claim
- Release council for pre-demo, deployment, launch, or handoff decisions
- Reconciliation when README, implementation, provider state, and stakeholder wording disagree
- Executive brief when technical evidence needs a concise decision-ready form
Verifier leads with SHIP, SHIP WITH CONDITIONS, HOLD, or INVESTIGATE, then shows what is proven, what is not proven, the counterevidence, and the smallest next proof step.
Who this is for: technical leads, operators, consultants, and founders who cannot afford to confuse local validation with production completion.
Who this is not for: teams looking for an autonomous release bot. Verifier does not deploy, delete, publish, migrate, message, or rotate credentials without separate authorization. Pair with Ship It for execution after the evidence supports the decision.
Core Capabilities
- Separate proposed, configured, simulated, tested, live, sent, and delivered states
- Lead evidence-backed release and handoff decisions
- Reconcile contradictory documentation and operational sources
- Create concise executive decision briefs without hiding uncertainty
Customer ratings
0 reviews
No ratings yet
- 5 star0
- 4 star0
- 3 star0
- 2 star0
- 1 star0
No reviews yet. Be the first buyer to share feedback.
Version History
This persona is actively maintained.
September 26, 2026
v1.0.0 -- evidence-led release, migration, cleanup, and handoff decisions
One-time purchase
$39
By continuing, you agree to the Buyer Terms of Service.
Creator
Brian Gorzelic — SpookyJuice.AI
Evidence-led tools for AI agents, software releases, and technical operations
Built from real operating workflows, with provenance, safety boundaries, and human approval designed in.
View creator profile →Details
- Type
- Persona
- Category
- Ops
- Price
- $39
- Version
- 1
- License
- One-time purchase
Works With
Works with OpenClaw, Claude Projects, Custom GPTs, Cursor and other instruction-friendly AI tools.
Recommended Skills
Skills that complement this persona.
Agent Handoff Pack — five agent roles and the handoff contracts they have to satisfy
Ops
The roster slice of the Agent Company Kit: five role definitions (orchestrator, scout, analyst, builder, auditor), the handoff contract each one owes the next, and a validator that checks a handoff against its contract. Python stdlib only.
$9
Agent Skill Vetter — vet any agent skill or artifact before you install it
Ops
Point it at a skill, a handoff note or a report: it re-derives the equations written in text or markdown, requires a URL and a date on every source, and refuses unlabelled numbers. Tables and JSON get the source, date, label and absolute checks. PASS or CHANGES, offline, no key.
$0
Cost Ledger — token spend report for your agent's call log (Python, no key)
Ops
Reads a JSONL call log and prints cost by day, model and task, budget pace and heartbeat waste flags. One stdlib script, same log in / same numbers out — no API key, no network.
$2.99